# WebRun Browser Automation (remote · api.webrun.ai)

Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.

- Trust score: 76/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-14

## Components

- remote · `api.webrun.ai`: 76/100 (this document), [markdown](https://verifymcp.io/servers/ai-webrun-webrun/api.md), [page](https://verifymcp.io/servers/ai-webrun-webrun/api)

## Channel facts

- Endpoint: `https://api.webrun.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.2`

## 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 2026-08-14.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 7822 tokens (~372/item across 21 items; 21 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-webrun-webrun https://api.webrun.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-webrun-webrun]
url = "https://api.webrun.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-webrun-webrun": {
      "type": "remote",
      "url": "https://api.webrun.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-webrun-webrun --url https://api.webrun.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-webrun-webrun:
    url: "https://api.webrun.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-webrun-webrun": {
      "type": "http",
      "url": "https://api.webrun.ai/mcp"
    }
  }
}
```

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.

### 2026-08-14 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “list_environments” rewrote its description, which is the text the model reads
- [security] Tool “create_agent” rewrote its description, which is the text the model reads
- [security] Tool “create_workflow” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 273 → 372
- [cosmetic] “create_workflow” reworded the description of “workListEnabled”
- [cosmetic] “create_workflow” reworded the description of “environmentId”
- [cosmetic] “create_workflow” reworded the description of “variableValues”
- [cosmetic] “create_workflow” reworded the description of “templateVariables”
- [cosmetic] “create_agent” reworded the description of “environmentId”
- [cosmetic] “create_agent” reworded the description of “memory”
- [cosmetic] “create_agent” reworded the description of “prompt”
- [cosmetic] “create_agent” reworded the description of “variables”
- [cosmetic] “create_workflow” reworded the description of “promptTemplate”
- [cosmetic] “create_workflow” reworded the description of “memoryContract”
- [cosmetic] “create_workflow” reworded the description of “memory”
- [cosmetic] “update_workflow” reworded the description of “workListEnabled”
- [cosmetic] “update_workflow” reworded the description of “variableValues”
- [cosmetic] “update_workflow” reworded the description of “templateVariables”
- [cosmetic] “update_workflow” reworded the description of “promptTemplate”
- [cosmetic] “update_workflow” reworded the description of “memoryContract”
- [cosmetic] “update_workflow” reworded the description of “memory”

### 2026-08-13 (score 76, −1)

- [security] New tool “trigger_workflow”, which the server declares destructive
- [security] New tool “pause_agent”, which the server declares destructive
- [security] New tool “resume_agent”, which the server declares destructive
- [security] New tool “update_workflow”, which the server declares destructive
- [functional regression] Schema quality: 137 → 273
- [functional] Schema quality: good → excellent
- [functional] New tool “create_agent”
- [functional] New tool “create_workflow”
- [functional] New tool “get_workflow”
- [functional] New tool “list_agents”
- [functional] New tool “list_workflows”

### 2026-08-11 (score 77, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-10 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03

### 2026-08-09 (score 76, +40)

- [security improvement] Transport: unverified → pass
- [security improvement] Authorization: fail → pass
- [security] First check of Authorization: partial
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100

### 2026-08-08 (score 36)

First indexed and scored.

## MCP tools (21)

### `browser_task` (~533 tokens)

Run browser task

Execute a browser automation task in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai). Creates a session, runs the task, and auto-terminates. Best for simple one-off tasks. May navigate, fill forms, and submit data on third-party websites as the task requires.

Input parameters:

- `debugC` (boolean): Enable debug mode on the instance (default: false)
- `environmentId` (string): Environment ID for persistent profile session. Use list_environments to find available IDs. Without this, a disposable instance is used.
- `files` (array): Optional file IDs to attach (from /files/upload). Max 5 files.
- `maxDuration` (number): Max duration in minutes (default: 5)
- `model` (string): Optional model name or profile key (from global config). Falls back to the configured default.
- `outputSchema` (object): JSON Schema for structured output (required if outputType is structured_json)
- `outputType` (string): Response format (default: text)
- `policyId` (string): Policy ID to apply automation guardrails (domain restrictions, capability controls, LLM role). Optional.
- `prompt` (string, required): Task description in natural language
- `proxy` (object): Proxy configuration. WebRun-managed: { source: "WebRun", country: "GB" }. Custom: { source: "custom", type: "http"|"socks", host, port, username?, password? }. Omit for no proxy.
- `reach_out_mode` (string): Controls proactive chat-platform messages (Telegram/WhatsApp/Slack/Discord/Teams) to bot users on the same environment. Default: "off" — no messages are sent unless this is set explicitly. "guardrail…
- `secrets` (array): Domain-matched secrets [{match, fields}] passed to instance (not stored)
- `startingUrl` (string): Optional starting URL
- `timezone` (string): IANA timezone name for the session, e.g. "America/New_York", "Europe/London", "Asia/Tokyo". Date/time-sensitive instructions (e.g. "tomorrow morning", "today", "in 2 hours") are interpreted in this t…
- `webhook` (object): Webhook configuration for task completion notification

Output parameters:

- `data` (object): Task output payload (instance-authored shape)
- `environment` (object)
- `error` (string)
- `message` (string)
- `pending` (boolean): True when the task is still running — poll get_task_status
- `sessionId` (string)
- `status` (string): Present on guardrail results: 'awaiting_input'
- `success` (boolean)
- `taskId` (string|null)
- `type` (string): Result type, e.g. 'task_completed', 'task_failed', 'guardrail_trigger'

### `create_session` (~410 tokens)

Create browser session

Create a persistent session in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai), for multi-step workflows. Returns a sessionId for subsequent commands. With an initial task the browser may act on third-party websites immediately.

Input parameters:

- `debugC` (boolean): Enable debug mode on the instance (default: false)
- `environmentId` (string): Environment ID for persistent profile session. Use list_environments to find available IDs. Without this, a disposable instance is used.
- `mode` (string): Session mode (default: default)
- `model` (string): Optional model name or profile key (from global config). Falls back to the configured default.
- `policyId` (string): Policy ID to apply automation guardrails (domain restrictions, capability controls, LLM role). Optional.
- `proxy` (object): Proxy configuration. WebRun-managed: { source: "WebRun", country: "GB" }. Custom: { source: "custom", type: "http"|"socks", host, port, username?, password? }. Omit for no proxy.
- `reach_out_mode` (string): Controls proactive chat-platform messages (Telegram/WhatsApp/Slack/Discord/Teams) to bot users on the same environment. Default: "off" — no messages are sent unless this is set explicitly. "guardrail…
- `task` (object): Initial task configuration
- `timezone` (string): IANA timezone name for the session, e.g. "America/New_York", "Europe/London", "Asia/Tokyo". Date/time-sensitive instructions (e.g. "tomorrow morning", "today", "in 2 hours") are interpreted in this t…

Output parameters:

- `environment` (object): Environment this session is bound to, when one was requested
- `message` (string)
- `sessionId` (string): Session ID for subsequent commands
- `streaming` (object): Live-view endpoints for the running browser
- `taskId` (string|null): Task ID when an initial task was provided

### `send_task` (~166 tokens)

Send task to session

Send a new task to an existing browser session (from create_session). The real Chrome browser may navigate, fill forms, and submit data on third-party websites as the task requires.

Input parameters:

- `files` (array): Optional file IDs to attach (from /files/upload). Max 5 files.
- `outputSchema` (object): JSON Schema for structured output (required if outputType is structured_json)
- `outputType` (string): Response format
- `prompt` (string, required): Task description
- `secrets` (array): Domain-matched secrets [{match, fields}] (not stored)
- `sessionId` (string, required): Session ID from create_session
- `terminateOnCompletion` (boolean): Auto-terminate after task (default: false)
- `webhook` (object): Webhook configuration

Output parameters:

- `data` (object): Task output payload (instance-authored shape)
- `environment` (object)
- `error` (string)
- `message` (string)
- `pending` (boolean): True when the task is still running — poll get_task_status
- `sessionId` (string)
- `status` (string): Present on guardrail results: 'awaiting_input'
- `success` (boolean)
- `taskId` (string|null)
- `type` (string): Result type, e.g. 'task_completed', 'task_failed', 'guardrail_trigger'

### `pause_session_task` (~37 tokens)

Pause session task

Pause the task currently running in a browser session. Resume it later with resume_session_task.

Input parameters:

- `sessionId` (string, required): Session ID

Output parameters:

- `action` (string): The control action that was applied
- `message` (string)
- `sessionId` (string)
- `success` (boolean)

### `resume_session_task` (~29 tokens)

Resume session task

Resume a previously paused task in a browser session.

Input parameters:

- `sessionId` (string, required): Session ID

Output parameters:

- `action` (string): The control action that was applied
- `message` (string)
- `sessionId` (string)
- `success` (boolean)

### `stop_session_task` (~37 tokens)

Stop session task

Cancel the task currently running in a browser session, keeping the session alive for new tasks.

Input parameters:

- `sessionId` (string, required): Session ID

Output parameters:

- `action` (string): The control action that was applied
- `message` (string)
- `sessionId` (string)
- `success` (boolean)

### `terminate_session` (~38 tokens)

Terminate session

End a browser session and free its resources. The session and any running task cannot be resumed afterwards.

Input parameters:

- `sessionId` (string, required): Session ID

Output parameters:

- `action` (string): The control action that was applied
- `message` (string)
- `sessionId` (string)
- `success` (boolean)

### `guardrail_response` (~135 tokens)

Answer guardrail prompt

Respond to a guardrail trigger when the browser agent needs human input (credentials, clarification, approval). The response is handed to the live agent, which continues acting on it.

Input parameters:

- `files` (array): Optional file IDs to attach (from /files/upload). Max 5 files.
- `newState` (string): How to continue: 'resume' (default) provides the requested input and continues the task; 'deny' declines the request (response text optional).
- `response` (string): Your response/instructions to the agent. Required when newState is 'resume'.
- `sessionId` (string, required): Session ID

Output parameters:

- `message` (string): What happened and what to do next (poll get_task_status)
- `sessionId` (string)
- `success` (boolean)
- `taskId` (string|null)

### `get_task_status` (~65 tokens)

Get task status

Check the status of a task previously started in a browser session. Use to poll for completion or detect guardrails. Read-only: reports on the task without affecting it.

Input parameters:

- `sessionId` (string, required): Session ID
- `taskId` (string, required): Task ID to check

Output parameters:

- `data` (object): Task output payload when completed (instance-authored shape)
- `message` (string)
- `sessionId` (string)
- `status` (string): Task/session state: 'completed', 'failed', 'awaiting_input', 'pending', 'active', 'paused', 'orphaned', or 'not_found'
- `taskId` (string)
- `type` (string): Raw result type when the task finished

### `screenshot` (~41 tokens)

Take screenshot

Capture a screenshot of the current browser page in an active session. Returns the screenshot as an inline image. Read-only.

Input parameters:

- `sessionId` (string, required): Session ID

Output parameters:

- `error` (string)
- `message` (string)
- `sessionId` (string)
- `success` (boolean)

### `list_sessions` (~20 tokens)

List sessions

List all active browser sessions for this account. Read-only.

Output parameters:

- `count` (number)
- `sessions` (array)

### `list_environments` (~69 tokens)

List environments

List available browser environments (persistent profiles) for this account. Returns environment IDs needed for persistent sessions in browser_task or create_session. Read-only. NOTE: workflows and agents use the connection's environment automatically — you rarely need this tool for those, and should not ask the user to choose an environment.

Output parameters:

- `boundEnvironment` (object)
- `count` (number)
- `environments` (array)
- `hint` (string)

### `list_workflows` (~104 tokens)

List workflows

List the user's saved workflows (prompt-templated browser automations, docs.webrun.ai). Shows each workflow's title, schedule, {{variables}}, and run stats. Scoped to the bound environment when this connection has one; pass scope "all" for every environment. Read-only.

Input parameters:

- `scope` (string): 'environment' (default when this connection is bound to one) lists workflows deployed to the bound environment; 'all' lists every workflow on the account.

Output parameters:

- `count` (number)
- `scope` (string)
- `workflows` (array)

### `get_workflow` (~114 tokens)

Get workflow details

Full detail of one workflow: prompt template, {{variables}} and their defaults, trigger + schedule, run settings (starting URL, timezone, model, proxy, output contract, files), memory state, and any pending logins. Identify by workflowId or exact title. Read-only; proxy credentials are masked.

Input parameters:

- `title` (string): Exact workflow title (case-insensitive) — alternative to workflowId
- `workflowId` (string): 24-hex workflow id (from list_workflows or create_workflow)

Output parameters:

- `environmentId` (string|null)
- `notes` (array)
- `outputType` (string)
- `promptTemplate` (string)
- `schedule` (object|null)
- `scheduleDescription` (string|null)
- `slug` (string)
- `title` (string)
- `totalTriggers` (number)
- `trigger` (object|null)
- `variables` (array)
- `workflowId` (string)

### `create_workflow` (~1941 tokens)

Create workflow

Create a new saved workflow. READINESS BAR: if you could not execute the prompt yourself as a human in a browser — which site, which records, which fields, delivered where, matched to each recipient how — it is not ready; first collect the missing business facts from the user (see the TASK INTERVIEW in the server instructions), then create. Requires title and promptTemplate — write the prompt as a browsing runbook following the Goal / Ground rules / Stages / Output contract in the promptTemplate field description. For tasks that must handle each new item exactly once (new messages, forward once, skip seen), set workListEnabled + listType 'monitor' AND author memoryContract {mode:'dedupe', key, emit} — the platform injects the tracking; never write memory steps into the prompt. Created in the connection's environment automatically — omit environmentId and never ask the user to choose one. Write the user's concrete values (names, URLs, numbers) directly into the prompt; use {{variables}} ONLY when the user explicitly wants a reusable template with per-run inputs. Everything else is optional and defaults sensibly — do not quiz the user about settings. A supplied schedule is stored as a setting only — the workflow does not run on a timer until deployed via create_agent; use trigger_workflow to run it now.

Input parameters:

- `compatibleTools` (array): Sites/tools the workflow uses: [{ name, loginUrl, domain, role }].
- `conciergeNotify` (string): Where the concierge announces results (e.g. 'Telegram', 'Slack', 'WhatsApp', 'Microsoft Teams', 'concierge').
- `department` (string): Free-text department label (e.g. "inventory").
- `deployedPolicyId` (string): Policy id to run under (must be owned by you).
- `destination` (object): Result destination chip: { type, sub, description }. Types seen: 'custom-api', 'slack', 'sheets', 'email', 'messaging', 'telegram', 'crm'.
- `environmentId` (string): Rarely needed — OMIT it: the connection's bound environment (or your only environment) is applied automatically. Pass only when the user explicitly names a different environment. Never ask the user t…
- `fileDeferred` (boolean): Dashboard flag: file selection deferred to run time.
- `flow` (object): Dashboard flow diagram: { trigger: {kind, phrase}, steps: [{ primary: {label, domain}, verb }] }.
- `listType` (string): Work-list traversal policy: 'static' (one sweep), 'dynamic' (list refreshes each cycle), 'monitor' (persistent parents + consume-once children).
- `memory` (string): The agent's private notebook: shown to it at the start of every run, updated automatically after each run. Seed it ONLY with durable facts the next run must already know — the exact description of a…
- `memoryContract` (object): Tracking policy — AUTHOR THIS whenever the task must remember what it already handled (forward once, skip seen items, only new messages): { mode: 'dedupe', key: 'what uniquely identifies one handled…
- `memoryEnabled` (boolean): Persist per-workflow agent memory across runs (default true).
- `model` (string): Model profile key. Omit for the account default.
- `orchestrateFirst` (boolean): Discovery mode: one run gathers the WHOLE work list up front, later runs claim one item each.
- `outputSchema` (object|array): JSON Schema object (outputType "structured") or array of column-name strings (outputType "structured_csv").
- `outputType` (string): Output contract: 'text' (default), 'structured' (JSON matching outputSchema), 'structured_csv' (rows for the outputSchema column names).
- `policyOptedOut` (boolean): Opt this workflow out of the environment's default policy.
- `promptTemplate` (string, required): The task the browser agent runs, written as a BROWSING RUNBOOK. Structure it as: `Goal:` — one sentence naming the outcome. `Ground rules (every stage, every turn):` — bullet invariants when the task…
- `proxy` (object): Proxy for runs. {source:"WebRun", country?} or {source:"custom", type:"http"|"socks", host, port, username?, password?}. Custom passwords are encrypted at rest and never returned.
- `publicDraftId` (string): Dashboard public-draft correlation id.
- `reachOutMode` (string|null): Proactive-chat policy for runs: 'off', 'guardrail_only', or 'full'. Omit (or pass null) to inherit the account default (MCP-initiated runs treat inherit as 'off').
- `refineMessages` (array): Dashboard builder refinement thread rows: [{ role, content }].
- `requiredFiles` (array): Per-run file attachments. Each row may name its own environmentId; ownership is enforced per-file at dispatch.
- `roiHourlyRate` (number|null): Hourly rate for the ROI card.
- `roiMinutesPerTask` (number|null): Minutes saved per run (dashboard ROI card).
- `schedule` (object): Saved schedule setting. NOTE: record-only — the workflow does NOT run on a timer until deployed as a scheduled agent (dashboard or Telegram bot).
- `shortDescription` (string): One-line summary shown in workflow lists.
- `skills` (array): Workflow-scoped skill entries (dashboard shape).
- `startingUrl` (string): Page Chrome opens at the start of each run. Omit to let the prompt decide.
- `templateVariables` (array): ONLY for explicitly dynamic workflows (the user asked for a reusable template): metadata for the {{variables}} used in promptTemplate (drives the dashboard fill-in UI). Omit entirely when the prompt…
- `timezone` (string): IANA timezone for runs of this workflow (e.g. "America/New_York").
- `title` (string, required): Workflow title (shown on the dashboard).
- `trigger` (object): How the workflow is meant to be invoked (informational — see notes). Defaults to {type:'manual', source:'manual'}.
- `triggerPhrase` (string): Natural-language phrase that invokes this workflow in chat.
- `useCaseTags` (array): Categorisation tags.
- `variableValues` (object): ONLY for explicitly dynamic workflows: default values for {{variables}}, keyed by variable name. NOTE: applied only when triggering via MCP trigger_workflow (merged under caller-supplied variables);…
- `wizardPreset` (object): Dashboard wizard preset: { technology, useCases[], destination, destinationSub }.
- `workListEnabled` (boolean): Work-list mode: the agent works a page list one item per run, reporting each back. SET THIS (with listType 'monitor') for watch-and-handle-once tasks — 'forward each new message', 'reply to new comme…

Output parameters:

- `environment` (object)
- `notes` (array): Caveats the caller should relay (e.g. the schedule is record-only)
- `slug` (string)
- `success` (boolean)
- `title` (string)
- `workflowId` (string)

### `update_workflow` (~1788 tokens)

Update workflow

Update an existing workflow. Supply workflowId plus only the fields to change: prompt, trigger, schedule, run settings, variables, presentation. Object and array fields are replaced whole; pass null to clear an optional field. Renaming via title keeps the slug stable. The stored schedule stays a saved setting — scheduled agents already deployed from this workflow keep their own timing. promptTemplate follows the same Goal / Ground rules / Stages / Output runbook contract as create_workflow (see that field's description).

Input parameters:

- `compatibleTools` (array): Sites/tools the workflow uses: [{ name, loginUrl, domain, role }].
- `conciergeNotify` (string): Where the concierge announces results (e.g. 'Telegram', 'Slack', 'WhatsApp', 'Microsoft Teams', 'concierge').
- `department` (string): Free-text department label (e.g. "inventory").
- `deployedPolicyId` (string): Policy id to run under (must be owned by you).
- `destination` (object): Result destination chip: { type, sub, description }. Types seen: 'custom-api', 'slack', 'sheets', 'email', 'messaging', 'telegram', 'crm'.
- `environmentId` (string): Move the workflow to a different environment you own.
- `fileDeferred` (boolean): Dashboard flag: file selection deferred to run time.
- `flow` (object): Dashboard flow diagram: { trigger: {kind, phrase}, steps: [{ primary: {label, domain}, verb }] }.
- `listType` (string): Work-list traversal policy: 'static' (one sweep), 'dynamic' (list refreshes each cycle), 'monitor' (persistent parents + consume-once children).
- `memory` (string): The agent's private notebook: shown to it at the start of every run, updated automatically after each run. Seed it ONLY with durable facts the next run must already know — the exact description of a…
- `memoryContract` (object): Tracking policy — AUTHOR THIS whenever the task must remember what it already handled (forward once, skip seen items, only new messages): { mode: 'dedupe', key: 'what uniquely identifies one handled…
- `memoryEnabled` (boolean): Persist per-workflow agent memory across runs (default true).
- `model` (string): Model profile key. Omit for the account default.
- `orchestrateFirst` (boolean): Discovery mode: one run gathers the WHOLE work list up front, later runs claim one item each.
- `outputSchema` (object|array): JSON Schema object (outputType "structured") or array of column-name strings (outputType "structured_csv").
- `outputType` (string): Output contract: 'text' (default), 'structured' (JSON matching outputSchema), 'structured_csv' (rows for the outputSchema column names).
- `policyOptedOut` (boolean): Opt this workflow out of the environment's default policy.
- `promptTemplate` (string): The task the browser agent runs, written as a BROWSING RUNBOOK. Structure it as: `Goal:` — one sentence naming the outcome. `Ground rules (every stage, every turn):` — bullet invariants when the task…
- `proxy` (object): Proxy for runs. {source:"WebRun", country?} or {source:"custom", type:"http"|"socks", host, port, username?, password?}. Custom passwords are encrypted at rest and never returned.
- `publicDraftId` (string): Dashboard public-draft correlation id.
- `reachOutMode` (string|null): Proactive-chat policy for runs: 'off', 'guardrail_only', or 'full'. Omit (or pass null) to inherit the account default (MCP-initiated runs treat inherit as 'off').
- `refineMessages` (array): Dashboard builder refinement thread rows: [{ role, content }].
- `requiredFiles` (array): Per-run file attachments. Each row may name its own environmentId; ownership is enforced per-file at dispatch.
- `roiHourlyRate` (number|null): Hourly rate for the ROI card.
- `roiMinutesPerTask` (number|null): Minutes saved per run (dashboard ROI card).
- `schedule` (object): Saved schedule setting. NOTE: record-only — the workflow does NOT run on a timer until deployed as a scheduled agent (dashboard or Telegram bot).
- `shortDescription` (string): One-line summary shown in workflow lists.
- `skills` (array): Workflow-scoped skill entries (dashboard shape).
- `startingUrl` (string): Page Chrome opens at the start of each run. Omit to let the prompt decide.
- `templateVariables` (array): ONLY for explicitly dynamic workflows (the user asked for a reusable template): metadata for the {{variables}} used in promptTemplate (drives the dashboard fill-in UI). Omit entirely when the prompt…
- `timezone` (string): IANA timezone for runs of this workflow (e.g. "America/New_York").
- `title` (string): Workflow title (shown on the dashboard).
- `trigger` (object): How the workflow is meant to be invoked (informational — see notes). Defaults to {type:'manual', source:'manual'}.
- `triggerPhrase` (string): Natural-language phrase that invokes this workflow in chat.
- `useCaseTags` (array): Categorisation tags.
- `variableValues` (object): ONLY for explicitly dynamic workflows: default values for {{variables}}, keyed by variable name. NOTE: applied only when triggering via MCP trigger_workflow (merged under caller-supplied variables);…
- `wizardPreset` (object): Dashboard wizard preset: { technology, useCases[], destination, destinationSub }.
- `workListEnabled` (boolean): Work-list mode: the agent works a page list one item per run, reporting each back. SET THIS (with listType 'monitor') for watch-and-handle-once tasks — 'forward each new message', 'reply to new comme…
- `workflowId` (string, required): 24-hex id of the workflow to update (from list_workflows or create_workflow). Required — the title property here is the NEW title for renames, never an identifier.

Output parameters:

- `changes` (array): Human-readable field: old → new summaries of what was applied (empty when everything supplied matched the current values)
- `notes` (array): Caveats to relay (record-only schedule, linked scheduled agents, prompt-structure advice)
- `slug` (string)
- `success` (boolean)
- `title` (string)
- `workflowId` (string)

### `trigger_workflow` (~172 tokens)

Trigger workflow

Run a workflow now in its deployed environment. Drives a real Chrome browser: the run may navigate, fill forms, and submit data on third-party websites as the workflow's prompt requires. Pass values for the workflow's {{variables}} in `variables` (stored variableValues defaults fill any gaps). Returns a sessionId — poll get_task_status for the result.

Input parameters:

- `force` (boolean): Work-list workflows only: when the list reports complete, re-open it for a fresh full pass.
- `title` (string): Exact workflow title (case-insensitive) — alternative to workflowId
- `variables` (object): Values for the workflow's {{variables}}, keyed by exact variable name. Merged over the workflow's stored variableValues defaults.
- `workflowId` (string): 24-hex workflow id

Output parameters:

- `listComplete` (boolean): Work-list workflows: every item has been visited (no run started)
- `message` (string)
- `sessionId` (string): Poll get_task_status with this id
- `success` (boolean)
- `taskId` (string|null)
- `workflowId` (string)

### `create_agent` (~968 tokens)

Create scheduled agent

Create a scheduled agent — a recurring or one-time automation that runs on a timer in a real Chrome browser. Two modes. WORKFLOW MODE: pass workflowId plus a schedule — the platform copies everything else (prompt, starting URL, output contract, model, proxy, policy, files) from the workflow and bakes your variables into the prompt; results and memory stay centralised on the workflow. STANDALONE MODE: omit workflowId and provide name, prompt (a Goal / Ground rules / Stages / Output browsing runbook — see the prompt field description), and a schedule; the connection's environment is used automatically. Ask the user only what it should do and when it should run, in plain language — pick sensible defaults for everything else and state them; never ask about environments or technical settings. Results are delivered to your connected chat and appear in session history.

Input parameters:

- `environmentId` (string): STANDALONE MODE, rarely needed — OMIT it: the connection-bound environment (or your only one) is applied automatically; never ask the user to choose. Workflow mode always uses the workflow's deployed…
- `expiresAt` (string): ISO 8601 date-time after which the agent auto-pauses (recurring schedules).
- `memory` (string): STANDALONE MODE: the agent's private notebook, shown to it every run and updated automatically after each run. Seed ONLY durable facts the next run must know (target descriptions, preferences, known…
- `name` (string): Agent name. Required standalone; defaults to the workflow title in workflow mode.
- `outputSchema` (object|array): STANDALONE MODE: JSON Schema object (structured) or column-name array (structured_csv).
- `outputType` (string): STANDALONE MODE: output contract (same rules as create_workflow).
- `prompt` (string): STANDALONE MODE (required there): The task the browser agent runs, written as a BROWSING RUNBOOK. Structure it as: `Goal:` — one sentence naming the outcome. `Ground rules (every stage, every turn):`…
- `schedule` (object, required): When the agent fires. Required.
- `startingUrl` (string): STANDALONE MODE: page Chrome opens at the start of each run.
- `variables` (object): WORKFLOW MODE, and only when the workflow's prompt actually contains {{variables}}: values for them, BAKED IN at deploy and reused every run (stored variableValues defaults fill gaps). Every template…
- `workflowId` (string): WORKFLOW MODE: 24-hex id of the workflow to deploy (from list_workflows). The prompt, starting URL, output contract, model, proxy, policy, and files are all copied from it.

Output parameters:

- `agentId` (string)
- `mode` (string)
- `name` (string)
- `nextRunAt` (string|null): ISO 8601 timestamp of the first fire
- `notes` (array)
- `schedule` (string): Humanized schedule
- `success` (boolean)
- `timezone` (string)
- `workflow` (object): Present in workflow mode: the workflow this agent was deployed from

### `list_agents` (~92 tokens)

List scheduled agents

List the account's scheduled agents (cron deployments): schedule, status, next/last run, and whether each is standalone or deployed from a workflow. Scoped to the bound environment when this connection has one; pass scope "all" for every environment. Read-only.

Input parameters:

- `scope` (string): 'environment' (default when bound) lists agents in the bound environment; 'all' lists every agent on the account.

Output parameters:

- `agents` (array)
- `count` (number)
- `scope` (string)

### `pause_agent` (~48 tokens)

Pause scheduled agent

Pause an active scheduled agent — it stops firing until resumed. Get agentId from list_agents.

Input parameters:

- `agentId` (string, required): 24-hex agent id (from list_agents or create_agent)

Output parameters:

- `agentId` (string)
- `message` (string)
- `name` (string)
- `status` (string)
- `success` (boolean)

### `resume_agent` (~74 tokens)

Resume scheduled agent

Resume a paused scheduled agent — recomputes its next run and reactivates it. A completed work-list agent restarts with a fresh full pass. Refuses if the agent's expiry has passed (extend it on the dashboard first).

Input parameters:

- `agentId` (string, required): 24-hex agent id (from list_agents)

Output parameters:

- `agentId` (string)
- `message` (string)
- `name` (string)
- `nextRunAt` (string|null)
- `status` (string)
- `success` (boolean)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-webrun-webrun/api#diagnostics

## Score history

- 2026-08-14: 76
- 2026-08-13: 76
- 2026-08-12: 77
- 2026-08-11: 77
- 2026-08-10: 76
- 2026-08-09: 76
- 2026-08-08: 36

## Links

- Remote endpoint: https://api.webrun.ai/mcp
- Authorisation metadata: https://api.webrun.ai/.well-known/oauth-protected-resource/mcp
- Website: https://webrun.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-webrun-webrun/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-webrun-webrun/api.json
- HTML version of this page: https://verifymcp.io/servers/ai-webrun-webrun/api