# @thinkrun/mcp

Let your AI coding agent test its own frontend work. Connects Claude Code, Cursor, and any MCP client to your real Chrome browser — real sessions, real cookies, no headless conflicts.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.3.8
- **Author:** ThinkRun
- **License:** MIT
- **npm:** @thinkrun/mcp
- **Source:** https://github.com/dundas/thinkrun
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 19 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-08-09T13:40:33.679Z
- **Version scanned:** 0.3.12
- **CVEs:** none found by OSV at scan time

## Tools

40 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `agent_identity`
- `browser_request_control`
- `browser_grant_status`
- `browser_release_control`
- `browser_snapshot`
- `browser_extract`
- `browser_click`
- `browser_fill`
- `browser_type_text`
- `browser_wait_for_text`
- `browser_screenshot`
- `browser_navigate`
- `session_create`
- `session_status`
- `session_delete`
- `session_list`
- `session_artifacts`
- `session_wait_ready`
- `session_use`
- `set_auditing`
- `set_mode`
- `page_cache_html`
- `page_cache_text`
- `page_cache_screenshot`
- `navigate`
- `go_back`
- `go_forward`
- `wait_for_element`
- `click`
- `click_at`
- `type_text`
- `fill`
- `press_key`
- `scroll`
- `hover`
- `select_option`
- `snapshot`
- `screenshot`
- `extract`
- `evaluate`

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@thinkrun/mcp\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Extensive to critical — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: deletes data; runs on your machine.
- Floor 37, ceiling 61 (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/%40thinkrun%2Fmcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40thinkrun%2Fmcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40thinkrun%2Fmcp
- HTML page: https://forgeregistry.com/registry/%40thinkrun%2Fmcp
- 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.