Wikipedia MCP

Access Wikipedia via MCP — search articles, get summaries, random facts, and dinosaur-specific facts. Great for research, hooks, and general knowledge lookups.

Security Scan

The skill is internally consistent: it implements a local MCP server that queries the public Wikipedia APIs, requires only the requests Python package, and its instructions match the code's behaviour.

Purpose & Capability

Name/description, SKILL.md, README, and src/server.py all align: this is a local MCP adapter that searches and summarizes Wikipedia via the public REST/Wikipedia API endpoints. No unrelated credentials, binaries, or services are requested.

Instruction Scope

Runtime instructions are limited to installing the requests library and registering the included Python server with mcporter. The server code reads JSON-RPC requests from stdin, calls Wikipedia endpoints, and returns results — behaviour that matches the documented tools. As a precaution, the README/SKILL.md ask the user to point mcporter at a local file path; you should inspect the full src/server.py before running to confirm the distributed copy is the one you expect.

Install Mechanism

No install spec in the registry; SKILL.md suggests 'pip install requests' (a minimal, expected dependency). No remote downloads, archive extraction, or third‑party install scripts are used.

Credentials

The skill declares no required environment variables or credentials. The code sets a User-Agent string with a contact email/URL (harmless metadata). All external network calls go to Wikipedia's public APIs, which require no secrets.

Persistence & Privilege

The skill does not request 'always: true' and is user-invocable. It runs as a local MCP server process you register; it does not modify other skills or system-wide configs. Autonomous invocation (disable-model-invocation=false) is the platform default and not in itself suspicious here.

Assessment

This skill appears to do exactly what it says: run a local MCP server that queries Wikipedia. Before installing, verify the src/server.py file you will execute (the distributed listing was truncated in the packaging log here — confirm the full file contents). Run it from a trusted path, review the code for any unexpected network calls or file I/O, and consider running it in a sandboxed environment if you have concerns. Note: it performs outbound HTTP requests to wikipedia.org (no secrets required). If you prefer to avoid any autonomous background activity, keep the skill user-invocable only or disable autonomous invocation in your agent settings.

Access Wikipedia via Model Context Protocol (MCP). No API key required.

Tools

Tool	Description
search	Search Wikipedia for articles
summary	Get article summary + image by title
random	Random Wikipedia article
did_you_know	Random "Did You Know" fact
dino_fact	Dinosaur/prehistory fact (specific species or random)

Setup

# Install dependency
pip install requests

# Add to mcporter (in ~/.openclaw/workspace/config/mcporter.json)
{
  "mcpServers": {
    "wikipedia": {
      "command": "python3",
      "args": ["/path/to/projects/wikipedia-mcp/src/server.py"]
    }
  }
}

Restart mcporter (openclaw gateway restart) or reconnect the MCP connection.

Usage

mcporter call wikipedia search --args '{"query": "velociraptor", "limit": 5}'
mcporter call wikipedia summary --args '{"title": "Tyrannosaurus"}'
mcporter call wikipedia dino_fact --args '{"species": "Spinosaurus"}'
mcporter call wikipedia dino_fact
mcporter call wikipedia did_you_know