# run-mcp

> run-mcp — funkyfunc-run-mcp. Use this tool when you need to interact with Model Context Protocol servers, call tools, and read stderr output in a seamless and reconnectable way. It solves problems of manual client configuration and restarts, providing a flexible interface for humans and agents through REPL, headless CLI, or MCP server integration. Ideal for use cases involving frequent edits and version control with git.

Canonical page: https://skillsregistry.net/skills/funkyfunc-run-mcp  
JSON: https://api.skillsregistry.net/v1/skills/funkyfunc-run-mcp

## Description

A thin MCP client for humans and agents — run any Model Context Protocol server, call its tools, read its stderr, and reconnect after each edit. REPL, headless CLI, or an MCP server your agent drives. No client config edits, no restarts.

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/funkyfunc/run-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "funkyfunc-run-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/funkyfunc-run-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/funkyfunc-run-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt