Skip to content
mcp/skillhub

Run MCP Server

by funkyfunc

An MCP server your coding agent uses to run, test, and diagnose the MCP server it is writing — spawn it, call its tools, restart it after an edit and see what changed, read how it died. Also a headless CLI with persistent sessions for agents that work fro

0Node.jsstdio

context tax

pending

security

97/100

cold start

pending

freshness

Maintained35d ago

Our reading of Run, from the data

Run is a browser automation MCP server from funkyfunc.

We haven't measured its tool list yet, so its token cost is unknown.

Maintenance is maintained: the last public signal was 35 days ago (2026-09-13). For comparison, 67% of browser automation servers are active or maintained.

With 0 GitHub stars it ranks #560 of 1,199 browser automation servers we index.

It runs locally on your machine over stdio.

Install Run MCP server

Install in Claude Code

claude mcp add run-funkyfunc -- npx -y run-mcp

Security signals

97/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.

Deductions

  • No security policy (SECURITY.md)-3

Checks

  • ✓Repository hygiene (archived, activity, license, security policy)
  • ○Package metadata (install scripts, provenance) — pending
  • ○Tool descriptions (prompt-injection and hidden-text heuristics) — pending
  • ○Source scan (secrets, CVEs, risky code) by vectra-guard — pending

Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules

Freshness

Maintained — last maintenance signal 35d ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-09-13 · 35d ago · GitHub

  2. Latest release

    no data · GitHub

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    no data · official registry

How it compares in Browser Automation

Against the most-starred browser automation servers we index. Token cost is per model turn, measured from each server's live tool list.

ServerStarsToolsTokens / turnFreshnessRuns
Run (this)0—not measuredMaintainedlocal
Browser Use118,444—not measuredActivelocal
Scrapling88,517—not measuredActivelocal
Browser39,318—not measuredActivelocal + hosted
Playwright38,349—not measuredActivelocal
Browser36,690—not measuredActive—
All browser automation MCP servers

FAQ

›How do I install the Run MCP server in Claude Code?

Run: claude mcp add run-funkyfunc -- npx -y run-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Run require an API key?

No required environment variables are declared in its published metadata.

›Can I use Run as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Run in the official MCP registry?

No. It was indexed from npm.

Sources and method

GitHub repository
fetched 2026-10-19
Package registry (npm / PyPI)
listed
Last checked against all sources
2026-10-19

The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.

Alternatives to Run

Other browser automation MCP servers.

View all