ZeroWidth Workbench
REMOTE · API.ZEROWIDTH.AI
Build, run and publish Workbench flows, tasks, shims and knowledge bases.
Available components
Last scanned (4 hours ago)
Scores higher than 64% of remote servers
Reachable. Last reached 24 Oct 2026.
Category AI and Machine Learning
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. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (workbench_flows_update). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability86
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 15689 tokens (~80/item across 195 items; 61 tools + 134 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management53
- Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 89% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 9 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 62 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 23 Oct 26 0
- 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 security
- New tool “workbench_tasks_set_sites” functional
- “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 cosmetic
- 22 Oct 26 +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.
- 20 Oct 26 +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.
- 18 Oct 26 +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.
- 17 Oct 26 0
- Tool “search_workspace” rewrote its description, which is the text the model reads security
- “search_workspace” added an optional parameter “folderId” cosmetic
- “search_workspace” reworded the description of “kinds” cosmetic
- “search_workspace” reworded the description of “q” cosmetic
- 16 Oct 26 +1
- Server version: 0.0.0 → 1.0.0 functional
- 15 Oct 26 0
- Tool “workbench_kb_create” rewrote its description, which is the text the model reads security
- New tool “workbench_flows_attach_knowledge_base” functional
- 14 Oct 26 +1
- New tool “workbench_flows_scenarios_delete”, which the server declares destructive security
- New tool “workbench_flows_scenarios_update”, which the server declares destructive security
- New resource “prism/synthetic-panels” functional
- New tool “workbench_flows_scenarios_create” functional
- New tool “workbench_flows_scenarios_list” functional
- “workbench_flows_scaffold” added an optional parameter “variables” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 24 Oct 2026 · Probed https://api.zerowidth.ai/mcp/x/workbench
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.zerowidth.ai | CN=WR3,O=Google Trust Services,C=US | 20 Sept 2026 | 19 Dec 2026 | RSA 2048 | SHA256-RSA | ef3f24a330d02ed80992778a6ead44bf |
| SANs: api.zerowidth.ai | ||||||
| CN=WR3,O=Google Trust Services,C=US (CA) | CN=GTS Root R1,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | RSA 2048 | SHA256-RSA | 7ff005a91568d63abc22861684aa4b5a |
| CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 19 Jun 2020 | 28 Jan 2028 | RSA 4096 | SHA256-RSA | 77bd0d6cdb36f91aea210fc4f058d30d |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.zerowidth.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| zerowidth.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.zerowidth.ai/mcp/x/workbench | Verified | 200 | |
| http (plaintext) | http://api.zerowidth.ai/mcp/x/workbench | HTTPS enforced |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
workbench_tasks_act Act on a Task gate (record a verdict) ~191
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | Task run id that is waiting_human. |
| verdict | string | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_compile Compile a sentence into a Task plan ~209
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.
| Name | Type | Req | Description |
|---|---|---|---|
| approvalId | string | – | Re-call with the approvalId from a needs_confirmation response after the user approves. |
| sentence | string | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_create Create a draft Task ~244
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.
| Name | Type | Req | Description |
|---|---|---|---|
| approvalId | string | – | Approval id from a prior needs_confirmation response. Omit on the first call. |
| sentence | string | yes | The process sentence, in the user's words. |
| taskName | string | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_delete Delete a Workbench Task ~136
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`.
| Name | Type | Req | Description |
|---|---|---|---|
| approvalId | string | – | Approval id from a prior needs_confirmation response. Omit on the first call. |
| taskId | string | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_freeze Freeze a compiled plan (activate the Task) ~194
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.
| Name | Type | Req | Description |
|---|---|---|---|
| approvalId | string | – | Approval id from a prior needs_confirmation response. Omit on the first call. |
| plan | – | yes | The plan object from workbench_tasks_compile, verbatim. |
| sentence | string | yes | The sentence this plan was compiled from. |
| taskId | string | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_get Read one Workbench Task (definition + recent runs) ~168
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.
| Name | Type | Req | Description |
|---|---|---|---|
| taskId | string | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_list List Workbench Tasks ~107
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
No output schema declared.
No examples provided.
workbench_tasks_run_view View a Task run (the lit sentence) ~108
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.
| Name | Type | Req | Description |
|---|---|---|---|
| runId | string | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_set_sites Set the sites a Task can reach ~207
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.
| Name | Type | Req | Description |
|---|---|---|---|
| approvalId | string | – | Approval id from a prior needs_confirmation response. Omit on the first call. |
| sites | array | yes | Every site the Task may reach. |
| taskId | string | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_start Start a Task run ~195
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | 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. |
No output schema declared.
No examples provided.
workbench_tasks_update Rename a Workbench Task ~135
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`.
| Name | Type | Req | Description |
|---|---|---|---|
| approvalId | string | – | Approval id from a prior needs_confirmation response. Omit on the first call. |
| taskId | string | yes | Task id, from workbench_tasks_list. |
| taskName | string | yes | 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. |
No output schema declared.
No examples provided.
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.
remote · api.zerowidth.ai
claude mcp add --transport http ai-zerowidth-workbench 'https://api.zerowidth.ai/mcp/x/workbench'
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.