# ZeroWidth Workbench (remote · api.zerowidth.ai) Build, run and publish Workbench flows, tasks, shims and knowledge bases. - Trust score: 73/100 (medium) - Change this week: +3 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-24 ## Components - remote · `api.zerowidth.ai`: 73/100 (this document), [markdown](https://verifymcp.io/servers/ai-zerowidth-workbench/mcp-x-workbench.md), [page](https://verifymcp.io/servers/ai-zerowidth-workbench/mcp-x-workbench) ## Channel facts - Endpoint: `https://api.zerowidth.ai/mcp/x/workbench` - Transports: `streamable-http` - Auth: `none` - Version: `1.0.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-24. - **Endpoint Security**: 57/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (workbench_flows_update). - HTTPS is enforced; there's no plaintext access path. - HSTS check failed: the Strict-Transport-Security header is absent. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 86/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (excellent). - Tool/resource definitions use about 15689 tokens (~80/item across 195 items; 61 tools + 134 resources), lean. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 53/100 - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 96/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 89% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 9 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 62 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the ZeroWidth Workbench MCP server? ZeroWidth Workbench is a hosted endpoint at https://api.zerowidth.ai/mcp/x/workbench, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http ai-zerowidth-workbench 'https://api.zerowidth.ai/mcp/x/workbench' ``` ### Cursor ```json { "mcpServers": { "ai-zerowidth-workbench": { "url": "https://api.zerowidth.ai/mcp/x/workbench" } } } ``` ### VS Code ```json { "servers": { "ai-zerowidth-workbench": { "type": "http", "url": "https://api.zerowidth.ai/mcp/x/workbench" } } } ``` ### Codex ```toml [mcp_servers.ai-zerowidth-workbench] url = "https://api.zerowidth.ai/mcp/x/workbench" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "ai-zerowidth-workbench": { "type": "remote", "url": "https://api.zerowidth.ai/mcp/x/workbench", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add ai-zerowidth-workbench --url 'https://api.zerowidth.ai/mcp/x/workbench' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: ai-zerowidth-workbench: url: "https://api.zerowidth.ai/mcp/x/workbench" ``` ### Netclaw ```json { "McpServers": { "ai-zerowidth-workbench": { "Transport": "http", "Url": "https://api.zerowidth.ai/mcp/x/workbench" } } } ``` ### Vellum ```bash assistant mcp add ai-zerowidth-workbench -t streamable-http -u 'https://api.zerowidth.ai/mcp/x/workbench' ``` ### Other ```json { "mcpServers": { "ai-zerowidth-workbench": { "type": "http", "url": "https://api.zerowidth.ai/mcp/x/workbench" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-23 (score 73, 0) - [security] Tool “search_docs” rewrote its description, which is the text the model reads - [security] Tool “workbench_flows_publish” rewrote its description, which is the text the model reads - [security] Tool “workbench_flows_schedule” rewrote its description, which is the text the model reads - [security] Tool “workbench_tasks_compile” rewrote its description, which is the text the model reads - [security] Tool “workbench_tasks_create” rewrote its description, which is the text the model reads - [security] Tool “workbench_tasks_get” rewrote its description, which is the text the model reads - [security] Tool “workbench_tasks_start” rewrote its description, which is the text the model reads - [functional] New tool “workbench_tasks_set_sites” - [cosmetic] “workbench_flows_publish” added an optional parameter “untried” - [cosmetic] “workbench_flows_schedule” added an optional parameter “recurrence” - [cosmetic] “workbench_flows_schedules_update” added an optional parameter “recurrence” - [cosmetic] “workbench_flows_schedule” reworded the description of “interval” - [cosmetic] “workbench_flows_schedule” made “interval” optional ### 2026-10-22 (score 73, +1) No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-20 (score 72, +1) No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-18 (score 71, +1) No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-17 (score 70, 0) - [security] Tool “search_workspace” rewrote its description, which is the text the model reads - [cosmetic] “search_workspace” added an optional parameter “folderId” - [cosmetic] “search_workspace” reworded the description of “kinds” - [cosmetic] “search_workspace” reworded the description of “q” ### 2026-10-16 (score 70, +1) - [functional] Server version: 0.0.0 → 1.0.0 ### 2026-10-15 (score 69, 0) - [security] Tool “workbench_kb_create” rewrote its description, which is the text the model reads - [functional] New tool “workbench_flows_attach_knowledge_base” ### 2026-10-14 (score 69, +1) - [security] New tool “workbench_flows_scenarios_delete”, which the server declares destructive - [security] New tool “workbench_flows_scenarios_update”, which the server declares destructive - [functional] New resource “prism/synthetic-panels” - [functional] New tool “workbench_flows_scenarios_create” - [functional] New tool “workbench_flows_scenarios_list” - [cosmetic] “workbench_flows_scaffold” added an optional parameter “variables” ## MCP tools (61) ### `search_docs` (~111 tokens) Search ZeroWidth docs Search ZeroWidth product documentation. Returns matching pages with title, slug, public URL, and a query-relevant snippet. Use this when the user asks about a ZeroWidth product (Compass, Workbench, Caliper, Prism, Ledger, Napkin, the assistant), an API behavior, or a policy. No authentication required — the docs corpus is public. Input parameters: - `limit` (integer): Max number of results. Defaults to 10. - `query` (string, required): Search query — keywords or natural-language phrase. ### `get_doc` (~73 tokens) Fetch ZeroWidth doc by slug Fetch the full Markdown body of a specific docs page by its slug. Use this after `search_docs` when the user needs the complete content of a page. No authentication required. Input parameters: - `slug` (string, required): Page slug. Accepts 'compass/api', '/compass/api', or 'docs/compass/api'. ### `list_docs` (~75 tokens) List ZeroWidth docs pages Enumerate all available docs pages, optionally filtered by product (e.g. 'compass', 'legal', 'overview'). Use this to discover what slugs exist before calling `get_doc`. No authentication required. Input parameters: - `product` (string): Optional product slug filter (e.g. 'compass', 'legal', 'overview'). ### `workbench_flows_revisions_list` (~159 tokens) List a flow's versions (publish history) The flow's revision history, newest first: published versions carry a `version` label and note; entries with version null are draft autosaves. Use it to answer 'is this published?' (any entry with a version), to find a revision id for caliper_evals_create's flowRevisionId, or to see when the draft last changed. Input parameters: - `flowId` (string, required): Flow id. - `limit` (integer): Entries to return, default 20. - `publishedOnly` (boolean): true = only labeled published versions (default false). - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_update` (~263 tokens) Rename / describe / archive / re-scope a Workbench flow Changes a flow's name, description, visibility, tags, or archived state — the metadata around the flow, NOT its orchestration (prompts and nodes change through workbench_flows_edit_text). Pass only what changes. Archiving hides the flow from the default gallery but leaves it runnable, scheduled, and shared; pass archived: false to restore. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `archived` (boolean): true archives, false restores. - `description`: New description; null clears it. - `flowId` (string, required): Flow id, from workbench_flows_list. - `flowName` (string): New name. - `tags` (array): Replacement tag set (lowercase labels). The whole set, not a diff. - `visibility` (string): Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_publish` (~298 tokens) Publish a Workbench flow version Snapshots the flow's current DRAFT as a named published version — the version schedules (workbench_flows_schedule), guest share links (workbench_flows_share_create), public-API runs, and 'published'-stage evals execute. The draft keeps evolving after this; runs on the published side don't change until the next publish. Publishing does NOT run the flow, but any eval set to runOnPublish starts a run (that spends credit — mention it when one exists). Refused when the draft hasn't been run since it last changed: try it first with workbench_flows_run on a few real questions, including one it should decline, and read the answers. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): Flow to publish. - `note` (string): What changed — a commit message. - `untried` (boolean): true only when the person asked to publish this draft without trying it first. - `version` (string, required): Version label, e.g. '1.0.0' or '2026-09-04'. Re-using a label retags it to this snapshot. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_delete` (~166 tokens) Delete a Workbench flow Deletes a flow. Its schedules stop, guest share links die, and evals targeting it can no longer run (their binding shows flowOk: false) — check caliper_flow_performance for evals and workbench_flows_schedules_list before proposing, and prefer workbench_flows_update with archived: true when the user just wants it out of the way. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): Flow id, from workbench_flows_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_fork` (~191 tokens) Fork a public flow into the workspace Copies a PUBLIC flow from another workspace (a template) into this one as a new draft the user owns. Identify it by its flowUuid (the id on Workbench's public template pages and in `workbench_flows_get` output); optionally pin which published version to copy. Flows already in this workspace can't be forked — open them instead. Counts toward the plan's flow cap. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowUuid` (string, required): The source flow's public uuid. - `forkedFromVersion` (string): Published version label to copy. Default: the latest published. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_schedules_list` (~142 tokens) List a flow's schedules Every schedule on one flow: cadence, whether it's paused (`enabled: false`), the next fire time, delivery, and the last run's status. Read this before workbench_flows_schedule (don't create a duplicate) and to get the scheduleId for workbench_flows_schedules_update / workbench_flows_schedules_delete / workbench_flows_schedules_run_now. Input parameters: - `flowId` (string, required): Flow id, from workbench_flows_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_schedules_update` (~541 tokens) Pause / resume / re-time a flow schedule Changes one schedule: `enabled: false` pauses it (configuration kept), `enabled: true` resumes and recomputes the next fire time from now; `interval` / `scheduleTime` / `scheduleTimezone` / `scheduleDayOfWeek` change the cadence; `label`, `delivery`, and `input` can change too. Pass only what changes. Get the scheduleId from workbench_flows_schedules_list. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `delivery` (string) - `enabled` (boolean): false pauses, true resumes. - `flowId` (string, required): Flow the schedule belongs to. - `input`: New fixed input envelope — {"kind":"chat","messages":[…]} or {"kind":"form","values":{…}}. - `interval` (string): New cadence: hourly, daily, or weekly. - `label` - `recurrence`: When it runs, like a calendar event repeats; use it for anything beyond a plain hourly/daily/weekly at one time (then omit interval). {"freq":"hourly"|"daily"|"weekly"|"monthly"|"yearly","every":N,"t… - `scheduleDayOfWeek` - `scheduleId` (string, required): Schedule id, from workbench_flows_schedules_list. - `scheduleTime` - `scheduleTimezone` - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_schedules_delete` (~135 tokens) Delete a flow schedule Removes a schedule for good. Prefer workbench_flows_schedules_update with enabled: false when the user might want it back. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): Flow the schedule belongs to. - `scheduleId` (string, required): Schedule id, from workbench_flows_schedules_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_schedules_run_now` (~208 tokens) Fire a flow schedule once, now Runs one iteration of a schedule immediately through the real scheduled pipeline (same input, same delivery — the email or channel it normally posts to) without moving its cadence. Works on paused schedules. Use it to test a schedule the user just set up. Spends workspace credit and delivers for real, so it sits behind the approval gate — may return `needs_confirmation`. The run is fire-and-forget: check workbench_flows_schedules_list for lastStatus, or workbench_executions_get for the trace. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): Flow the schedule belongs to. - `scheduleId` (string, required): Schedule id, from workbench_flows_schedules_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_shares_list` (~141 tokens) List a flow's guest share links Every guest link on one flow, newest first: label, whether it's still live, the shareUrl (live links only — dead ones have no URL), expiry, and how many guests and messages it has seen. Use it to answer 'who has access', to recover a link the user lost, and to get the shareId for workbench_flows_shares_revoke. Input parameters: - `flowId` (string, required): Flow id, from workbench_flows_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_shares_revoke` (~151 tokens) Revoke a flow's guest share link Kills one guest link immediately — anyone holding it gets a closed page from then on. Conversations already had stay in the flow's history. Get the shareId from workbench_flows_shares_list. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): Flow the link belongs to. - `shareId` (string, required): Share id, from workbench_flows_shares_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_scenarios_list` (~113 tokens) List a flow's variables and scenarios A flow's variables (each {{token}} in an agent's prompt, with its type) and every saved scenario with its values. Read this before creating or updating a scenario, so the values use the flow's real variable names. Input parameters: - `flowId` (string, required): Flow id, from workbench_flows_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_scenarios_create` (~236 tokens) Save a scenario for a flow Saves a named scenario: values for the flow's variables, e.g. one demo customer. It shows in the test pane's Scenarios menu, and Caliper evals can run as it. Use the person's details from what the user shared (a CRM screenshot, a profile) and say which ones you made up. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): Flow id. - `scenarioName` (string, required): What it's called in the menu, e.g. 'Lexi Taylor, Platinum'. - `values` (object): Values by variable name, e.g. { member_first_name: "Lexi", plan_type: "Platinum" }. Names come from workbench_flows_scenarios_list's `variables`; a name the flow doesn't have is left out and reported… - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_scenarios_update` (~222 tokens) Change a flow's scenario Renames a scenario or changes its values. `values` MERGES into what's saved: pass only the variables that change, and null to clear one. Get the scenarioId from workbench_flows_scenarios_list. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): Flow id. - `scenarioId` (string, required): Scenario id, from workbench_flows_scenarios_list. - `scenarioName` (string): New name. - `values` (object): Values by variable name, e.g. { member_first_name: "Lexi", plan_type: "Platinum" }. Names come from workbench_flows_scenarios_list's `variables`; a name the flow doesn't have is left out and reported… - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_scenarios_delete` (~124 tokens) Delete a flow's scenario Deletes one scenario. A design session running as it goes back to no scenario. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): Flow id. - `scenarioId` (string, required): Scenario id, from workbench_flows_scenarios_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_attach_knowledge_base` (~281 tokens) Give an agent flow a knowledge base to search Attaches a knowledge base to an AGENT flow's draft, the same way picking it in the agent editor does: a docs knowledge base becomes a search tool the model calls when a question needs it; a tabular one also puts its tables in the prompt and adds a query tool. The flow needs a system prompt (scaffold it with one). Attaching one that's already there changes nothing. Do it BEFORE workbench_flows_publish: a published version is what interfaces and schedules run, so attach, try it with workbench_flows_run, then publish — and if something already pins an older version (an interface grant), re-grant the new version. Tell the model in its system prompt what the knowledge base holds and when to search it. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `flowId` (string, required): The agent flow, from workbench_flows_scaffold or workbench_flows_list. - `knowledgeBaseId` (string, required): The knowledge base id, from workbench_kb_create or workbench_kb_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_flows_run` (~227 tokens) Run a Workbench flow Execute a flow and return its outputs synchronously. Runs the draft by default; pass source:"published" (optionally a version) to run the live published version. Spends workspace LLM budget, bounded by the token's cost cap. `input` is the flow's input envelope, e.g. {"kind":"chat","messages":[…]} or {"kind":"form","values":{…}}. Input parameters: - `approvalId` (string): Re-call with the approvalId from a needs_confirmation response after the user approves. - `flowId` (string, required): Flow id to run. - `input` (object): Flow input envelope (RunFlowInput). Omit for a flow that needs none. - `source` (string): Which version to run. Default: draft. - `timeoutMs` (integer): Max runtime in ms (also the hard cost ceiling). - `version` (string): Published version label (only with source:"published"). - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this. Ignored for workspace API keys. ### `workbench_flows_schedule` (~600 tokens) Schedule a Workbench flow Set a specific built flow to run automatically on a cadence — the deterministic counterpart to a routine. Each run executes the flow's latest PUBLISHED revision with the fixed `input` envelope and routes the output per `delivery`. USE THIS when the user wants a flow they've built to run on a schedule ("run my digest flow every morning"). Do NOT create a routine for this — a routine runs a free-form instruction, not a built flow. The schedule runs the PUBLISHED flow, so the flow must be published (check workbench_flows_revisions_list; publish with workbench_flows_publish if it isn't). `input` is fixed for every run, so the flow itself should fetch anything time-varying at run time. Manage existing schedules with workbench_flows_schedules_list / workbench_flows_schedules_update. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `delivery` (string) - `flowId` (string, required): Flow to schedule (id from workbench_flows_list). - `input` (required): Fixed input envelope every run executes with — {"kind":"chat","messages":[…]} or {"kind":"form","values":{…}}, the same shape workbench_flows_run takes. Constant across runs. - `interval` (string): Plain cadence: hourly, daily, or weekly. Omit when passing recurrence. - `label` - `recurrence`: When it runs, like a calendar event repeats; use it for anything beyond a plain hourly/daily/weekly at one time (then omit interval). {"freq":"hourly"|"daily"|"weekly"|"monthly"|"yearly","every":N,"t… - `scheduleDayOfWeek` - `scheduleTime` - `scheduleTimezone` - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this. Ignored for workspace API keys. ### `workbench_flows_list` (~92 tokens) List Workbench flows Lists every flow in the active workspace the caller can see. Returns summaries (id, name, visibility, updatedAt) — fetch one with `workbench_flows_get` for the full orchestration body. Input parameters: - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys (workspace is intrinsic). ### `workbench_executions_get` (~218 tokens) Inspect a flow's executions (debug traces) The flow's stack traces: recent executions with per-node timelines — what each node received, produced, how long it took, and the exact error when one failed. USE THIS when a run misbehaves instead of guessing: read the failing node's inputs/error, then propose a fix (workbench_flows_edit_text) grounded in what actually happened. Pass executionId to inspect one run, or just flowId for the most recent runs. Node inputs/outputs are truncated for transport — the full record is in the flow's dev drawer. Input parameters: - `executionId` (string): Specific execution to inspect. Omit for the latest runs. - `flowId` (string, required): Workbench flow id. - `limit` (integer): How many recent executions (default 3, max 10). Ignored when executionId is set. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys (workspace is intrinsic). ### `workbench_flows_get` (~233 tokens) Read one Workbench flow One flow. Default `view: summary` lists its nodes and links so you can pick one; `view: node` with a nodeId returns that node's full settings and prompt — read THAT before workbench_flows_edit_text, and copy `find` text from it character-for-character, never from memory. `view: full` returns the whole orchestration body. Input parameters: - `flowId` (string, required): Flow id. - `nodeId` (string): With view `node`: which node. - `view` (string): `summary` (default): the flow's fields plus one line per node (id, type, label, and how long its prompt is) and the links — enough to pick a node. `node`: the full settings of one node (pass nodeId)… - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys (workspace is intrinsic). ### `workbench_flow_authoring_guide` (~77 tokens) Workbench flow-authoring guide READ THIS FIRST before writing or editing any raw flow orchestration JSON. Covers the document shape, the settings-vs-input-ports rule (temperature, max_tokens, tools, response_format are PORTS, not settings — constants reach ports via value nodes), exact link format, plugin links, and three complete worked examples. ### `workbench_node_catalog_get` (~258 tokens) Search the Workbench node catalog The ground truth for what nodes exist and what their ports actually are — verify against this instead of recalling. Search by keyword/category for summaries; pass `slug` for one node's full detail (inputs, outputs, settings). Inputs are PORTS fed by links; settings live on the node — see `workbench_flow_authoring_guide`. The catalog is the WORKSPACE'S: model nodes the workspace's inference policy forbids come back with `allowed: false` — never author with those; pick an allowed model. Pass `flowId` to include the flow's pinned imports as nodes. Input parameters: - `category` (string): Filter by category. - `flowId` (string): A flow whose pinned imports should appear as `imported-` nodes. - `limit` (integer): Results per page, 1-50. Default 20. - `offset` (integer): Pagination offset. - `q` (string): Keyword over slug / name / tagline / description. - `slug` (string): Exact node slug → full detail for that one node (ports + settings). - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; the catalog's policy annotation is per workspace. ### `workbench_flows_scaffold` (~713 tokens) Scaffold a first-draft Workbench flow Creates a runnable first-draft flow from a spec you author: pick the simplest pattern that fits (classifier for read-and-bucket, structurer for transform/extract/draft-for-review, agent for genuinely conversational), write a production-quality system prompt grounded in what the user told you, and mark anything stubbed with [STUB: ...] markers plus stubNotes. The draft opens in Workbench's simple editor at /w//flows/ — give the user that path. May return `needs_confirmation`; show the user what you're proposing and wait for their approval, then re-call with the approvalId. When the draft comes from a Compass change, pass its opportunityId so the flow and the change point at each other (Compass shows 'Open in Workbench'; the flow shows where it came from). Then: workbench_flows_run to try it, workbench_flows_publish when it's ready for schedules and share links. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `categories` (array): classifier only: 2-12 buckets. The classifier asks the systemPrompt as one pick-one question with these as the options, and returns `values.category` plus `answers.category` (probabilities and confid… - `description` (string): 1-2 sentences: what it does, where it fits. - `flowName` (string, required): Imperative + specific, ≤80 chars. - `inputDescription` (string): What the flow's single input carries. - `mode` (string, required): Pattern editor the draft opens in. Pick interviewer for conversations that LEARN something from a person (research calls, intake, retros) — pair it with workbench_flows_share_create so non-account hu… - `model` (string): The model node slug the draft runs on, from workbench_node_catalog_get, that the workspace allows. For a classifier, a `decision` entry (Jev, Kev, Solar Decide); defaults to TypeSafe: Jev Latest. Oth… - `opportunityId` (string): Compass change (from compass_opportunities_list) this draft implements. Sets the flow ↔ change link; refused when the change already has a draft. - `responseSchemaJson` (string): structurer only: the output JSON Schema, JSON-encoded as a string (object root, required fields, additionalProperties false). - `stubNotes` (string): What's stubbed / missing / worth wiring next. - `systemPrompt` (string): The draft's behavior — production-quality first attempt with [STUB: ...] / [FILL IN: ...] markers where reality is missing. Required for structurer and classifier. Leave it out of an agent to get the… - `variables` (array): agent / interviewer: types and descriptions for the {{tokens}} in systemPrompt. Every {{token}} becomes a variable on its own (the test pane and scenarios list it, the app fills it per user at run ti… - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this. ### `workbench_flows_edit_text` (~381 tokens) Surgically edit text inside a flow Applies ONE precise text replacement to a flow's DRAFT orchestration — Edit-tool semantics: `find` must be the EXACT current text, copied character-for-character from workbench_flows_get, and must occur exactly once anywhere in the flow (system prompts, node settings, metadata, a node's type). `find` is text inside ONE value, not JSON: to change a model, find the model slug alone (`anthropic-claude-haiku-4-5`) and replace it with another `llm` slug from workbench_node_catalog_get. It can't add or remove nodes or links. Zero or multiple matches return an error instead of guessing. This is the improvement primitive: check receipts first with caliper_flow_performance, cite the run id in `note`, apply the edit after approval, then re-run the eval with caliper_evals_run and report the score delta — never claim improvement without the before/after. Edits land on the draft only; the published version changes when someone publishes (workbench_flows_publish, after the user has seen the result). May return `needs_confirmation` — show the user the exact find/replace diff and wait. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation envelope. - `find` (string, required): EXACT current text (≥3 chars), copied verbatim — never reconstructed from memory. - `flowId` (string, required): Flow to edit. - `note` (string, required): Why this edit. Cite eval run ids when it follows a measurement (e.g. 'refund answers scored 1/5 on accuracy in run cer_abc — adds the manager-approval rule'). Lands in the audit log. - `replace` (string, required): Replacement text. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this. ### `workbench_flows_share_create` (~228 tokens) Mint a guest share link for a flow Creates a no-account guest link where anyone can chat with the flow's latest PUBLISHED revision at workbench's /s/ page — the fastest way to put a working flow in a stakeholder's hands ('here, try it'). The flow must have a published version (workbench_flows_revisions_list shows it; publish with workbench_flows_publish if not). Conversations are capped per guest; the link can expire, and you can list links with workbench_flows_shares_list and kill one with workbench_flows_shares_revoke. May return `needs_confirmation` — say who the link is for and wait. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation envelope. - `expiresInDays` (integer): Days until the link dies. Omit = revoke-only. - `flowId` (string, required): Flow to share. - `label` (string): Who/what this link is for, e.g. 'support pilot'. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this. ### `workbench_kb_get` (~112 tokens) Read one knowledge base One knowledge base: name, recipe (docs / tabular / graph), status, document and chunk counts, embedding model, and ingestion settings. Read it to confirm a KB has content before pointing a flow at it. Get the kbId from workbench_kb_list. Input parameters: - `kbId` (string, required): Knowledge base id. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_kb_documents_list` (~145 tokens) List the documents in a knowledge base Every document ingested into the KB's current content: id, name, type, size, chunk count. Empty for a KB with nothing ingested yet (or one whose ingestion is still running — check workbench_kb_ingestion_status). Use it before workbench_kb_add_documents to avoid re-adding a document, and to get the documentId for workbench_kb_document_delete. Input parameters: - `kbId` (string, required): Knowledge base id, from workbench_kb_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_kb_ingestion_status` (~162 tokens) Check an ingestion run The state of one ingestion run started by workbench_kb_add_documents: PENDING / RUNNING / DONE / FAILED, chunks written, and the error when it failed. Read it when the user asks whether their documents are in yet, or before a search that needs them — don't poll in a loop; ingestion of a few documents takes under a minute. Pass the runId the add-documents call returned. Input parameters: - `kbId` (string, required): Knowledge base id. - `runId` (string, required): Ingestion run id, from workbench_kb_add_documents. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_kb_delete` (~136 tokens) Delete a knowledge base Deletes a knowledge base and everything in it. Flows that search it will find nothing — check which agents use it (the user knows; the KB page in Workbench lists them) and say so before proposing. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `kbId` (string, required): Knowledge base id, from workbench_kb_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_kb_document_delete` (~152 tokens) Remove a document from a knowledge base Removes one ingested document and all its chunks; searches stop returning it at once. Get the documentId from workbench_kb_documents_list. To replace a document, remove it then workbench_kb_add_documents the new version. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `documentId` (string, required): Document id, from workbench_kb_documents_list. - `kbId` (string, required): Knowledge base id. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_kb_list` (~97 tokens) List knowledge bases Lists every knowledge base in the active workspace the caller can see. Returns summaries (id, name, description, status, doc/chunk counts, embedding model). Use an id with `workbench_kb_search` to retrieve content. Input parameters: - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys (workspace is intrinsic). ### `workbench_kb_search` (~205 tokens) Search a knowledge base Retrieves the most relevant chunks from one knowledge base — the core RAG primitive. `mode:"semantic"` (default) embeds the query and ranks by meaning (spends a small amount of workspace credit); `mode:"keyword"` is a free case-insensitive substring match. Each hit carries the chunk text, its document, and a score (cosine similarity 0-1 for semantic, match count for keyword). Get a kbId from `workbench_kb_list`. Input parameters: - `kbId` (string, required): Knowledge base id (from workbench_kb_list). - `limit` (integer): Max hits to return, 1-50. Default 10. - `mode` (string): semantic (embed + rank by meaning, default) or keyword (free substring match). - `query` (string, required): What to search for. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this. Ignored for workspace API keys. ### `workbench_kb_create` (~201 tokens) Create a knowledge base Creates an empty knowledge base. Recipe 'docs' (default) for reference material an agent searches at runtime; 'tabular' for spreadsheet-style data queried with SQL; 'graph' for entity/relationship extraction. After creating, add content with workbench_kb_add_documents, then give an agent flow a search tool over it with workbench_flows_attach_knowledge_base (before publishing the flow). May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation envelope. - `description` (string) - `name` (string, required): Knowledge base name (1-200 chars). - `recipe` (string): Default 'docs'. - `visibility` (string): Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE. - `workspace` (string): Workspace slug override. ### `workbench_kb_add_documents` (~245 tokens) Add documents to a knowledge base Adds documents to a knowledge base and starts ingestion (chunk + embed; graph KBs also extract entities; tabular KBs load CSV as tables). Text goes inline (Markdown, plain text, CSV — encoding utf8); binary files (PDF, .docx) go base64-encoded with their mimeType. Up to 50 sources per call, ~10 MB each. Ingestion runs in the BACKGROUND — the result carries a runId; check it with workbench_kb_ingestion_status when the user asks, don't poll. workbench_kb_search works once it finishes. Content from blocks is ideal source material. Check workbench_kb_documents_list first so you don't add a document twice. Embedding spends workspace inference credit, so this sits behind the approval gate: may return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation envelope. - `kbId` (string, required): Knowledge base id (from workbench_kb_list or workbench_kb_create). - `sources` (array, required): Documents to ingest (1-50). - `workspace` (string): Workspace slug override. ### `workbench_shim_list` (~110 tokens) List shims Every shim the user can see: id, name, the question it answers, how many answers and examples it has, and the published version's held-out accuracy (null until something is published). A shim is a small decision model that runs inside an app with no model call. Start here to get a shimId. Input parameters: - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_shim_get` (~156 tokens) Read one shim One shim in full: the question, where its inputs come from, every answer with its description and examples, what the shim still needs before it can build, and the newest build's report — held-out accuracy, recall per answer, which answers get mistaken for which, and the compiler's notes. Read it before writing examples: match the setting and the existing examples' register, and put new examples where recall is low or the compiler says an answer is thin. Input parameters: - `shimId` (string, required): Shim id, from workbench_shim_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_shim_create` (~181 tokens) Create a shim Creates a shim from a name, the question it answers, and its answers. Add examples afterwards with workbench_shim_add_examples — three or more per answer and it builds on its own. May return `needs_confirmation`. Input parameters: - `answers` (array, required) - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `inputsComeFrom` (string): One line on where the inputs come from, in the user's words. - `name` (string, required): A short name, e.g. "Support triage". - `question` (string, required): The question, e.g. "Which team should read this message?" - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_shim_add_answer` (~141 tokens) Add an answer to a shim Adds one answer (a label and, optionally, when it applies). The shim needs three examples of it before it builds again with the new answer. May return `needs_confirmation`. Input parameters: - `answer` (string, required) - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `description` (string): When this answer applies. - `shimId` (string, required): Shim id, from workbench_shim_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_shim_add_examples` (~205 tokens) Add examples to an answer Adds example inputs to one answer. Write inputs a real person would actually type in the shim's setting — varied in length, register and specifics, each one clearly this answer and not another — never paraphrases of the answer's name. Read the shim first so new examples fit alongside the existing ones and land where recall is low. Exact duplicates are skipped. The shim rebuilds on its own afterwards; read it again for the new report. May return `needs_confirmation`. Input parameters: - `answer` (string, required): The answer these examples belong to, exactly as labelled. - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `examples` (array, required) - `shimId` (string, required): Shim id, from workbench_shim_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `comments_list` (~105 tokens) Read an entity's comment threads Lists the comment threads on one workspace entity (open first, then resolved) with authors and timestamps. Read this before weighing in on contested work — the threads are where disagreement lives before it becomes a decision. Input parameters: - `entityId` (string, required) - `entityKind` (string, required): What the thread hangs on. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `comments_create` (~184 tokens) Comment on an entity Posts a comment on a workspace entity — a new thread, or a reply when rootId is given. Use it to leave findings where the discussion already lives (an eval result on the flow being debated, a summary on a long thread). Mention people via mentionedUserIds (from workspace member ids) to ring their notification bell; never mention someone who didn't ask to be pulled in. Input parameters: - `approvalId` (string) - `body` (string, required) - `entityId` (string, required) - `entityKind` (string, required): What the thread hangs on. - `mentionedUserIds` (array) - `rootId` (string): Reply into this thread; omit to start a new one. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `comments_resolve` (~118 tokens) Resolve or reopen a thread Sets a comment thread's resolved state (rootId = the thread's root comment id). Resolve ONLY when the human asked or the thread's question is demonstrably settled — and say what settled it in a reply first. Reopening is for new evidence. Input parameters: - `approvalId` (string) - `resolved` (boolean, required) - `rootId` (string, required) - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_get` (~168 tokens) Read one Workbench Task (definition + recent runs) One Task in full: its sentence, status, the latest saved plan (the clauses — which run flows, which the assistant handles, who decides at each gate) with the flow and people names the plan refers to, and its recent runs, plus the sites its machine may reach (allowedSites) and the sites its plan names or past runs were refused (computer.sites). Read this before editing a task's sentence (workbench_tasks_compile with taskId) and when the user asks what a task does. Get the taskId from workbench_tasks_list. Input parameters: - `taskId` (string, required): Task id. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_update` (~135 tokens) Rename a Workbench Task Changes a task's name — the gallery label only. The sentence and plan are versioned and change through workbench_tasks_compile + workbench_tasks_freeze, never here. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `taskId` (string, required): Task id, from workbench_tasks_list. - `taskName` (string, required): New name. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_delete` (~136 tokens) Delete a Workbench Task Deletes a task. Runs still in flight are stopped (a gate waiting on someone is closed), and its schedule trigger stops firing; past runs stay in history. Check workbench_tasks_get for live runs and say so before proposing. May return `needs_confirmation`. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `taskId` (string, required): Task id, from workbench_tasks_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_set_sites` (~207 tokens) Set the sites a Task can reach Sets the full list of sites a Task's machine may reach (example.com, or *.example.com for its subdomains; up to 20), for steps that have to use a site like a person would. It replaces the list, so read workbench_tasks_get first (allowedSites, and computer.sites for what the plan names) and pass every site to keep. Always waits for approval, and only a workspace admin's approval applies it; for anyone else it says who can. The latest saved version runs with the new list. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `sites` (array, required): Every site the Task may reach. - `taskId` (string, required): Task id, from workbench_tasks_list. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_list` (~107 tokens) List Workbench Tasks Lists the workspace's Tasks — sentence-orchestrated processes — with their sentence, status, and recent runs (id, status, who a waiting run is on). Use this to find a task the user names ('claims intake') and to see what's in flight; workbench_tasks_get reads one in full. Input parameters: - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_create` (~244 tokens) Create a draft Task Creates a DRAFT Task from a name + sentence. A Task is for work with people in the loop (someone approves, decides or acts on each item before anything else happens) or a specific process mapped in Compass; its runs are measured. When nobody but you acts on it and you'd just do the same thing each time on a schedule, make a routine instead (routines_create). Use this once the user's sentence feels settled after you've refined it together — then compile it. The sentence should be THEIR words: trigger first ('When a claim arrives…'), then steps, branches, and who decides what. Name rooms, sheets, tables, flows and people by their names, never by id: people read the sentence on the Task's page. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `sentence` (string, required): The process sentence, in the user's words. - `taskName` (string, required): Short task name. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_compile` (~209 tokens) Compile a sentence into a Task plan Runs the compiler over a sentence and returns the PROPOSED plan (or repair-grade problems — fix by refining the sentence with the user, not by guessing). Nothing persists. Present the proposal in plain terms: which clauses run flows, which you will handle, who decides, what the compiler noted. `computer.sites` lists sites the plan names and whether the Task allows them; workbench_tasks_set_sites asks an admin to allow the rest. Then iterate or freeze. Compile may take ~15s. Input parameters: - `approvalId` (string): Re-call with the approvalId from a needs_confirmation response after the user approves. - `sentence` (string, required): The sentence to compile. - `taskId` (string): The task this sentence belongs to, when compiling an edit — keeps it out of the child-task candidates. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_freeze` (~194 tokens) Freeze a compiled plan (activate the Task) Freezes a reviewed plan as the Task's next version and activates it. Pass the EXACT plan object a compile returned — never hand-edit it (change the sentence and recompile instead). Freeze ONLY after the user has seen the proposal and said go; echo what you're freezing in one line first. In-flight runs keep their pinned versions. After freezing, offer to start a first run. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `plan` (required): The plan object from workbench_tasks_compile, verbatim. - `sentence` (string, required): The sentence this plan was compiled from. - `taskId` (string, required): The task id (create a draft first if none). - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_start` (~195 tokens) Start a Task run Kicks off a run of a Task and returns at once; the run carries on by itself and is live on the task's page. When the task expects an input document (its trigger has an input), pass the user's material as `input` — pasted text, extracted attachment text, or JSON. Tell the user it has started and what it does next. Check where it stands with workbench_tasks_run_view when they ask; don't poll it in a loop. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `input`: Trigger payload — the document text / JSON the task starts from. - `taskId` (string, required): Task id (from workbench_tasks_list). - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_run_view` (~108 tokens) View a Task run (the lit sentence) The run's current state rendered as its sentence: what ran (with timings), which path each gate took, what's waiting on whom and for how long, what's coming up. Use whenever the user asks where something stands, and after acting on a gate. Input parameters: - `runId` (string, required): Task run id. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `workbench_tasks_act` (~191 tokens) Act on a Task gate (record a verdict) Records THIS user's verdict on a run that is waiting on them — the labels come from the gate (workbench_tasks_run_view shows them via the plan; a wrong label errors listing the real options). Echo the verdict + note back to the user in one line BEFORE calling; that echo is the confirmation. Refuses when the gate is assigned to someone else. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `note` (string): The user's reasoning, attached to the verdict. - `runId` (string, required): Task run id that is waiting_human. - `verdict` (string, required): One of the gate's verdict labels, e.g. "confirmed". - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `search_workspace` (~431 tokens) Search the whole workspace Finds anything in the workspace in one call — uploaded files (searching the text inside them), folders, Workbench flows, shims, knowledge bases and tasks, Compass pages and changes, Caliper datasets, evals, rubrics, reviews, specs and sources, Ledger entries, Napkin sketches, decks, docs, sheets, diagrams and interfaces. The same search the person uses in Home. Use it FIRST whenever the user mentions something without saying where it lives ('the SOW', 'the dispatch interviews', 'that invoice'). The query is words in any order: each word must appear in the thing's name, its tags, the names of the folders it's filed under, or the text inside it — so 'northwind sow' finds the SOW filed in the Northwind folder, and 'dispatch interview' finds 'Dispatcher interview 1.md'. Results are ranked best first. Each hit carries its id, kind, path (for a link), folderPath (where it's filed, top-down), tags, and a snippet when the words were found inside it rather than in its name — say where a thing lives using folderPath. A file's id feeds workspace_files_read; other ids feed the kind's *_get tool. Pass folderId to search only inside one folder and everything under it. If nothing comes back, try fewer or different words before telling the user it doesn't exist. Results only include what the user can see, and only kinds this token may read. Input parameters: - `folderId` (string): Only search inside this folder and the folders under it (ids from workspace_folders_browse or a folder hit). - `kinds` (array): Restrict to these kinds (file, folder, flow, page, doc, dataset, …). Omit to search everything. - `limit` (integer) - `q` (string, required): Words, any order, case-insensitive. Fewer words find more. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `entity_tags_get` (~130 tokens) Read the tags on entities Returns the tags on a batch of entities of one kind — the labels galleries organize by. Ids come from the kind's list/get tool or from search_workspace. Use it before entity_tags_set so you replace the full set knowingly, and to answer 'what is this filed under'. Entities the user can't see are omitted. Input parameters: - `entityKind` (string, required): Which kind the ids belong to. - `ids` (array, required) - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `entity_tags_browse` (~149 tokens) Browse the workspace's tags Without a tag: every tag in use across the workspace with how many entities carry it, most-used first — the vocabulary the team already organizes by. With a tag: everything filed under it across every tool, each with its kind, id, title, and path. Use it to reuse existing labels instead of inventing near-duplicates, and to answer 'show me everything about X' when X is a label. Input parameters: - `tag` (string): A tag to expand into its items. Omit to list tags. - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ### `entity_tags_set` (~173 tokens) Set an entity's tags Replaces the FULL tag set on one entity (an empty list clears it). Read the current tags with entity_tags_get first and pass the merged list — this is not additive. Tags are lowercase letters, numbers, spaces, and hyphens; prefer labels already in use (entity_tags_browse) so the workspace's vocabulary stays small. The id comes from the kind's list/get tool or search_workspace. Input parameters: - `approvalId` (string): Approval id from a prior needs_confirmation response. Omit on the first call. - `entityId` (string, required) - `entityKind` (string, required) - `tags` (array, required) - `workspace` (string): Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-zerowidth-workbench/mcp-x-workbench#diagnostics ## Score history - 2026-10-24: 73 - 2026-10-23: 73 - 2026-10-22: 73 - 2026-10-21: 72 - 2026-10-20: 72 - 2026-10-19: 71 - 2026-10-18: 71 - 2026-10-17: 70 - 2026-10-16: 70 - 2026-10-15: 69 - 2026-10-14: 69 - 2026-10-13: 68 - 2026-10-12: 68 - 2026-10-11: 67 - 2026-10-10: 66 - 2026-10-08: 65 ## Common questions ### What is the ZeroWidth Workbench MCP server? ZeroWidth Workbench is an MCP server listed in the public MCP registry as ai.zerowidth/workbench. Build, run and publish Workbench flows, tasks, shims and knowledge bases. This page covers its hosted endpoint (https://api.zerowidth.ai/mcp/x/workbench). ### Is the ZeroWidth Workbench MCP server safe to use? ZeroWidth Workbench scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the ZeroWidth Workbench MCP server expose? ZeroWidth Workbench exposes 61 tools: search_docs, get_doc, list_docs, workbench_flows_revisions_list, workbench_flows_update, and 56 more. Their descriptions and schemas cost roughly 12,089 tokens of context every time the server is loaded. ### Does the ZeroWidth Workbench MCP server require authentication? No. We connected to ZeroWidth Workbench without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the ZeroWidth Workbench MCP server still maintained? ZeroWidth Workbench is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://api.zerowidth.ai/mcp/x/workbench - Website: https://zerowidth.ai/docs/overview/mcp#connect-to-one-product - Changelog RSS feed: https://verifymcp.io/servers/ai-zerowidth-workbench/mcp-x-workbench.xml - Changelog JSON feed: https://verifymcp.io/servers/ai-zerowidth-workbench/mcp-x-workbench.json - HTML version of this page: https://verifymcp.io/servers/ai-zerowidth-workbench/mcp-x-workbench