# run_skill_script

A execute tool on the Skill Management MCP Server MCP server.

Agent View of the PolicyLayer registry record for `run_skill_script`. HTML page: https://policylayer.com/tools/fkesheh-skill-mcp/run-skill-script

## Facts

- Tool: `run_skill_script`
- Server: Skill Management MCP Server (`fkesheh/skill-mcp`) — https://policylayer.com/tools/fkesheh-skill-mcp.md
- Homepage: https://github.com/fkesheh/skill-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run_skill_script",
    "arguments": {}
  }
}
```

## Why run_skill_script is rated High

This tool executes scripts, which is an Execute category action. The severity is high because script execution can have broad side effects depending on script contents (file access, network calls, system operations), though the local nature and skill-management context provide some sandboxing compared to unrestricted shell access.

From the tool's own definition: "Tool name 'run_skill_script' combined with server description stating it 'executes scripts with automatic dependency management and environment variables' indicates arbitrary code execution capability."

## Use case

AI agents invoke run_skill_script to trigger actions in Skill Management MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Skill Management MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_skill_script": {
      "limits": [
        {
          "counter": "run_skill_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Skill Management MCP Server (4)

- `execute_python_code` — Execute — https://policylayer.com/tools/fkesheh-skill-mcp/execute-python-code.md
- `skill_crud` — Execute — https://policylayer.com/tools/fkesheh-skill-mcp/skill-crud.md
- `skill_env_crud` — Execute — https://policylayer.com/tools/fkesheh-skill-mcp/skill-env-crud.md
- `skill_files_crud` — Execute — https://policylayer.com/tools/fkesheh-skill-mcp/skill-files-crud.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=fkesheh-skill-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/fkesheh-skill-mcp