WebRun Browser Automation MCP server
ai.webrun/webrunwebrun.aistreamable-httpv1.0.2Scanned
Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover.
23 tools: 13 can delete or cancel things, 1 do something that can't be undone, 2 change things and 7 only read.
- Reads private data · 2
- Reads text others write · 15
- Can send data out · 1
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
13 tools here can delete or cancel things and 1 does something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the WebRun Browser Automation MCP server can do
The WebRun Browser Automation MCP server is published by webrun.ai, a domain the MCP Registry verified. It has 23 tools. It can delete or cancel things (13 tools: browser_task, create_session, send_task, pause_session_task and 9 more), do things that cannot be undone, such as sending, paying or publishing (screenshot) and create or change data (2 tools: create_workflow and create_agent). 7 tools only read.
2 tools read private data (list_workflows and get_workflow); 15 tools bring in text other people can write (browser_task, create_session, send_task and 12 more); 1 tool can send data out of your system (send_task). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 3 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.0.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
23 tools
Deletes or cancels 13Claude Code: deny
browser_taskExecute a browser automation task in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai).Reads text others writeNo findings
Why it is in this group
- The description's first verb is "execute": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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 that no saved workflow covers. May navigate, fill forms, and submit data on third-party websites as the task requires. Do NOT use this to run or test a saved workflow — use trigger_workflow instead: only a workflow run carries the workflow's own rules, tracking and memory, so a session run will behave differently. If the user says "run it", "run it once", "test it" or "try it" about a workflow, that means trigger_workflow, not this tool.
Annotations the server declares
- title: Run browser task
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
create_sessionCreate a persistent session in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai), for multi-step interactive work.Reads text others writeNo findings
Why it is in this group
- The name "create_session" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Create a persistent session in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai), for multi-step interactive work. Returns a sessionId for subsequent commands. With an initial task the browser may act on third-party websites immediately. Do NOT use this to run or test a saved workflow — use trigger_workflow instead: only a workflow run carries the workflow's own rules, tracking and memory, so a session run will behave differently.
Annotations the server declares
- title: Create browser session
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
guardrail_responseRespond to a guardrail trigger when the browser agent needs human input (credentials, clarification, approval).Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...en the browser agent needs human input (credentials, clarification, approval). The response..."
Description, as the server wrote it 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.
Annotations the server declares
- title: Answer guardrail prompt
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
pause_agentPause an active scheduled agent — it stops firing until resumed.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Pause an active scheduled agent — it stops firing until resumed. Get agentId from list_agents.
Annotations the server declares
- title: Pause scheduled agent
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
pause_session_taskPause the task currently running in a browser session.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Pause the task currently running in a browser session. Resume it later with resume_session_task.
Annotations the server declares
- title: Pause session task
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
resume_agentResume a paused scheduled agent — recomputes its next run and reactivates it.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it 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).
Annotations the server declares
- title: Resume scheduled agent
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
resume_session_taskResume a previously paused task in a browser session.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Resume a previously paused task in a browser session.
Annotations the server declares
- title: Resume session task
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
send_taskSend a new task to an existing browser session (from create_session).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "send_task" says "send": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "send_task" says "send": it sends or publishes something to other people.
Description, as the server wrote it 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.
Annotations the server declares
- title: Send task to session
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
stop_session_taskCancel the task currently running in a browser session, keeping the session alive for new tasks.Reads text others writeNo findings
Why it is in this group
- The name "stop_session_task" says "stop": a word for a change.
- The description's first verb is "cancel": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Cancel the task currently running in a browser session, keeping the session alive for new tasks.
Annotations the server declares
- title: Stop session task
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
terminate_sessionEnd a browser session and free its resources.Reads text others writeNo findings
Why it is in this group
- The name "terminate_session" says "terminate": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it End a browser session and free its resources. The session and any running task cannot be resumed afterwards.
Annotations the server declares
- title: Terminate session
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
trigger_workflowRun a workflow now in its deployed environment.Reads text others writeNo findings
Why it is in this group
- The name "trigger_workflow" says "trigger": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Run a workflow now in its deployed environment. This is the ONLY correct way to run or TEST a saved workflow — a run started here carries the workflow's rules, tracking and memory; browser_task/create_session runs do not. When the user says "run it", "run it once", "test it" or "try it" about a workflow, this is the tool they mean. 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.
Annotations the server declares
- title: Trigger workflow
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
update_work_listChange the work list a workflow keeps between runs.No findings
Why it is in this group
- The name "update_work_list" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Change the work list a workflow keeps between runs. op: add (items; on a watch list, new watched items), remove (items; on a watch list, stop watching them), mark_handled or unmark (items), skip_approval (drafts waiting for approval), clear (empty the list; keepHandled keeps handled items on a collect list; a watch list keeps its watched items and drops their readings). Confirm with the user before remove or clear. Refused while a run of this workflow is in progress. To change what the list records, use update_workflow.
Annotations the server declares
- title: Update work list
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
update_workflowUpdate an existing workflow.No findings
Why it is in this group
- The name "update_workflow" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it 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). memoryContract is the exception to whole-replace: supplying its three fields updates them while platform tracking details are preserved. On a workflow that keeps a typed list: an outputSchema change needs workList keep or empty (ask the user); listType and queue mode can't change; a different result type goes through resultType, previewed first and applied once the user confirms.
Annotations the server declares
- title: Update workflow
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Can't be undone 1Claude Code: ask
screenshotCapture a screenshot of the current browser page in an active session.Reads text others write1 finding
Why it is in this group
- The name "screenshot" says "screenshot": a word for reading.
- The description's first verb is "capture": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "capture" and "browser": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "screenshot" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "screenshot" says "screenshot": a word for reading.
Description, as the server wrote it Capture a screenshot of the current browser page in an active session. Returns the screenshot as an inline image. Read-only.
Annotations the server declares
- title: Take screenshot
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 2Claude Code: ask
create_agentCreate a scheduled agent — a recurring or one-time automation that runs on a timer in a real Chrome browser.No findings
Why it is in this group
- The name "create_agent" says "create": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Create scheduled agent
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_workflowCreate a new saved workflow.No findings
Why it is in this group
- The name "create_workflow" says "create": a word for a change.
Description, as the server wrote it 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), memoryContract is REQUIRED — three plain-English fields addressed to the agent: groundRules, memoryInstruction and itemIdentity (see the field descriptions); the platform wires the tracking itself — never write memory or tracking 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. To run or TEST the workflow, use trigger_workflow ONLY — never browser_task or create_session.
Annotations the server declares
- title: Create workflow
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 7Show 7 read-only tools
get_task_statusCheck the status of a task previously started in a browser session.Reads text others writeNo findings
Why it is in this group
- The name "get_task_status" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "browser": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get task status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_work_listPage through the work list a workflow keeps between runs.No findings
Why it is in this group
- The name "get_work_list" says "get": a word for reading.
Description, as the server wrote it Page through the work list a workflow keeps between runs. Each item comes with its band: on a watch list failing, unreadable, changed_today or watching; on a collect list needs_approval, new_today, handled or seen. Identify the workflow by workflowId or exact title; filter by band or a search query; pass nextCursor back as cursor for the next page. Read-only.
Annotations the server declares
- title: Get work list
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_workflowFull detail of one workflow: prompt template, {{variables}} and their defaults, trigger + schedule, run settings (starting URL, timezone, model, proxy, output contract, files), mem…Reads private dataReads text others write1 finding
Why it is in this group
- The name "get_workflow" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...flowId or exact title. Read-only; proxy credentials are masked."
Description, as the server wrote it 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, any pending logins, and a summary of its work list when it keeps one (for a typed list: its bands, counts and newest or watched items — page it with get_work_list). Identify by workflowId or exact title. Read-only; proxy credentials are masked.
Annotations the server declares
- title: Get workflow details
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_agentsList the account's scheduled agents (cron deployments): schedule, status, next/last run, and whether each is standalone or deployed from a workflow.No findings
Why it is in this group
- The name "list_agents" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: List scheduled agents
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_environmentsList available browser environments (persistent profiles) for this account.Reads text others writeNo findings
Why it is in this group
- The name "list_environments" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "browser": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: List environments
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_sessionsList all active browser sessions for this account.Reads text others writeNo findings
Why it is in this group
- The name "list_sessions" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "browser": it reads web pages, which anyone can write.
Description, as the server wrote it List all active browser sessions for this account. Read-only.
Annotations the server declares
- title: List sessions
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_workflowsList the user's saved workflows (prompt-templated browser automations, docs.webrun.ai).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_workflows" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "list" and "browser": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: List workflows
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
30 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write15
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__webrun__send_task"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:28 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 16
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.webrun.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://app.webrun.ai
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 16 tools that change things (13 destructive, 1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.webrun.ai/mcp: tools/list returned 23 tools to an anonymous client, including browser_task (destructive), create_session (destructive), send_task (destructive), pause_session_task (destructive), resume_session_task (destructive) and 11 more
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 15 to 16
Findings
Matches of fixed checks, with the text they matched.
- Warnscreenshot
The server marks "screenshot" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "screenshot" says "screenshot": a word for reading.
The description mentions "credentials".
What this check looks forMatched text
description: "...en the browser agent needs human input (credentials, clarification, approval). The response..."
- Infoget_workflow
The description mentions "credentials".
What this check looks forMatched text
description: "...flowId or exact title. Read-only; proxy credentials are masked."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 added, 3 changed.+2 added~3 changedView diff
- Added:get_work_listOnly reads
- Added:update_work_listDeletes or cancels
- Changed:get_workflowOnly readsdescription
- Changed:guardrail_responseDeletes or cancelsinputSchema
- Changed:update_workflowDeletes or cancelsdescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 15 -> 16.View diff
- Tools that change things, listed without credentials: 15 to 16
Install
Pinned to version 1.0.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http webrun https://api.webrun.ai/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http webrun https://api.webrun.ai/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__webrun__get_task_status",
"mcp__webrun__list_sessions",
"mcp__webrun__list_environments",
"mcp__webrun__list_workflows",
"mcp__webrun__get_workflow",
"mcp__webrun__get_work_list",
"mcp__webrun__list_agents"
],
"ask": [
"mcp__webrun__screenshot",
"mcp__webrun__create_workflow",
"mcp__webrun__create_agent"
],
"deny": [
"mcp__webrun__browser_task",
"mcp__webrun__create_session",
"mcp__webrun__send_task",
"mcp__webrun__pause_session_task",
"mcp__webrun__resume_session_task",
"mcp__webrun__stop_session_task",
"mcp__webrun__terminate_session",
"mcp__webrun__guardrail_response",
"mcp__webrun__update_workflow",
"mcp__webrun__update_work_list",
"mcp__webrun__trigger_workflow",
"mcp__webrun__pause_agent",
"mcp__webrun__resume_agent"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as webrun. Review it before you use it.
Capability tags behind 15 rules
- mcp__webrun__browser_task untrusted-input
- mcp__webrun__create_session untrusted-input
- mcp__webrun__send_task untrusted-input, outbound
- mcp__webrun__pause_session_task untrusted-input
- mcp__webrun__resume_session_task untrusted-input
- mcp__webrun__stop_session_task untrusted-input
- mcp__webrun__terminate_session untrusted-input
- mcp__webrun__guardrail_response untrusted-input
- mcp__webrun__get_task_status untrusted-input
- mcp__webrun__screenshot untrusted-input
- mcp__webrun__list_sessions untrusted-input
- mcp__webrun__list_environments untrusted-input
- mcp__webrun__list_workflows private-data, untrusted-input
- mcp__webrun__get_workflow private-data, untrusted-input
- mcp__webrun__trigger_workflow untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.webrun/webrun/verify?hash=3eabc3b62c87890cf44afe4e6c277c9e66460da8205c21814829644e01b3dedb" | jq -e '.changed == false'Pinned hash 3eabc3b62c87, from Nov 11, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.webrun/webrun/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.webrun/webrun)Source: MCP Registry. Synced Oct 21, 2026, 17:44 UTC.
WebRun Browser Automation MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the WebRun Browser Automation MCP server safe?
- No scan can promise that. What its definitions show: 23 tools, 16 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the WebRun Browser Automation MCP server delete data?
- Yes. 13 tools can delete, cancel or revoke something: browser_task, create_session, send_task, pause_session_task, resume_session_task, stop_session_task and 7 more.
Can the WebRun Browser Automation MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: screenshot.
What tools does the WebRun Browser Automation MCP server have?
- 23 tools: 13 destructive, 1 irreversible, 2 write, 7 read. browser_task, create_session, send_task, pause_session_task, resume_session_task, stop_session_task, terminate_session, guardrail_response and 15 more.
Does the WebRun Browser Automation MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the WebRun Browser Automation MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_task.
Has the WebRun Browser Automation MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.