# ai.webrun/webrun

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

- **Type:** MCP server
- **Trust:** 30/100 (D), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.0.2
- **Author:** ai.webrun
- **License:** Unknown
- **Endpoints:** streamable-http https://api.webrun.ai/mcp
- **Source:** https://webrun.ai
- **Endpoint health:** reachable (last checked 2026-09-18T11:50:07.962Z, 4 samples) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

30/100 (D), scored on the content rubric
- Publisher verified: no
- Install scripts: suspicious script found
- Prompt-injection scan: findings present
- Obfuscation scan: clean
- Evidence age: 0 days

## Security scan

- **Status:** warnings
- **Scanned:** 2026-09-18T11:50:07.962Z
- **Version scanned:** live
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.
**Findings**
- injection-shaped content (warning) in the `browser_task` tool: Exfiltration-shaped instruction
- injection-shaped content (warning) in the `send_task` tool: Exfiltration-shaped instruction
- injection-shaped content (warning) in the `guardrail_response` tool: Exfiltration-shaped instruction

## Tools

21 declared. Observed from a live `tools/list` probe.
- `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-te
- `create_session` — 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 sessionI
- `send_task` — 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 
- `pause_session_task` — Pause the task currently running in a browser session. Resume it later with resume_session_task.
- `resume_session_task` — Resume a previously paused task in a browser session.
- `stop_session_task` — Cancel the task currently running in a browser session, keeping the session alive for new tasks.
- `terminate_session` — End a browser session and free its resources. The session and any running task cannot be resumed afterwards.
- `guardrail_response` — Respond to a guardrail trigger when the browser agent needs human input (credentials, clarification, approval). The response is handed to the live agent, which 
- `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 affe
- `screenshot` — Capture a screenshot of the current browser page in an active session. Returns the screenshot as an inline image. Read-only.
- `list_sessions` — List all active browser sessions for this account. Read-only.
- `list_environments` — List available browser environments (persistent profiles) for this account. Returns environment IDs needed for persistent sessions in browser_task or create_ses
- `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. Sco
- `get_workflow` — Full detail of one workflow: prompt template, {{variables}} and their defaults, trigger + schedule, run settings (starting URL, timezone, model, proxy, output c
- `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, deli
- `update_workflow` — Update an existing workflow. Supply workflowId plus only the fields to change: prompt, trigger, schedule, run settings, variables, presentation. Object and arra
- `trigger_workflow` — 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, 
- `create_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 sc
- `list_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 t
- `pause_agent` — Pause an active scheduled agent — it stops firing until resumed. Get agentId from list_agents.
- `resume_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'

## Install

**Verdict: do-not-install** — Do not install: 3 injection-shaped patterns found in this entry's own text — it may try to steer the model that loads it.
**Blocking**
- 3 injection-shaped patterns found in this entry's own text — it may try to steer the model that loads it. — tool:browser_task#files: Exfiltration-shaped instruction · tool:send_task#files: Exfiltration-shaped instruction · tool:guardrail_response#files: Exfiltration-shaped instruction
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Client configuration withheld.** Client configs are withheld because this entry has a blocking finding. Show the warnings below to the person installing it.
If they have seen the findings and still want to proceed, request the plan again with acknowledge_warnings=true.

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface.
- Floor 9, ceiling 27 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/ai.webrun%2Fwebrun
- Install plan: https://forgeregistry.com/api/v1/packages/ai.webrun%2Fwebrun/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/ai.webrun%2Fwebrun
- HTML page: https://forgeregistry.com/registry/ai.webrun%2Fwebrun
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.