wikipedia-mcp
MCP server for Wikipedia API
What it is and what it does
Wikipedia-mcp is a Model Context Protocol server that bridges Wikipedia and large language models, allowing AI assistants to retrieve factual information directly from Wikipedia during conversation. It wraps the Wikipedia API behind the MCP interface, exposing tools for article search, full-text retrieval, summaries, section extraction, link discovery, and related-topic suggestions. The server supports multiple languages and regional variants (e.g., Simplified vs. Traditional Chinese, Serbian scripts) via country codes or explicit language tags, and can run over stdio (for Claude Desktop), HTTP, or streamable-HTTP transports with optional static or JWT authentication.
The package is designed for developers integrating LLMs with reliable reference sources. It handles Wikipedia's API directly through wikipedia-api and fastmcp, manages HTTP requests via requests, and supports environment configuration through python-dotenv. Installation is straightforward via pipx (recommended for Claude Desktop) or pip, and the server runs as a command-line tool with extensive configuration options for transport, language, caching, and security.
Use it for:
- Integrate Claude Desktop with Wikipedia so it can cite and verify factual claims during conversations.
- Ground LLM responses in real-time Wikipedia content for research, tutoring, or fact-checking applications.
- Deploy a multi-language Wikipedia MCP server in Kubernetes or Docker for AI frameworks requiring strict function schemas.
- Cache Wikipedia queries to reduce API calls and improve response latency in high-volume LLM deployments.
- Secure network MCP transports with static bearer tokens or JWT validation for production AI agent infrastructure.
Worth the install?
AI-flagged interpretation of the facts on this page — verify before relying
Exposes Wikipedia search, article retrieval, and content extraction as a Model Context Protocol server for LLMs to access factual information in real time.
Yes, if you are building an LLM application (especially Claude Desktop) that needs reliable factual grounding. The package is actively maintained, has no known vulnerabilities, installs cleanly, and offers rich Wikipedia integration with multi-language support and flexible transport options. Install via pipx for Claude Desktop or pip for programmatic use.
Install
wikipedia-mcp on PyPI
pip
pip install wikipedia-mcpuv
uv add wikipedia-mcppoetry
poetry add wikipedia-mcpInstalling wikipedia-mcp
Before you install
Low friction: pure Python wheel with four runtime dependencies (fastmcp, wikipedia-api, requests, python-dotenv). Active maintenance with recent commits and no known vulnerabilities.
License in practice
MIT license permits commercial and private use with minimal restrictions—suitable for most deployment scenarios.
Quickstart
pip install wikipedia-mcp
wikipedia-mcp --transport stdio
# In Claude Desktop config:
# {"mcpServers": {"wikipedia": {"command": "wikipedia-mcp"}}}
Requires Python >=3.10. For Claude Desktop use, wikipedia-mcp command must be in PATH or full path specified in config.
Verify before relying
- Whether caching (--enable-cache) persists across server restarts and what storage backend it uses.
- Rate-limiting behavior when accessing Wikipedia without a personal access token.
- Performance characteristics for large article retrievals or high-volume queries.
Package facts
| License | MIT (permissive) |
| Python support | supports the current Python release (>=3.10) |
| Install friction | low — pure-Python wheel |
| Runtime dependencies | 4 — fastmcp, wikipedia-api, requests, python-dotenv |
| Maintenance | actively maintained — 105 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 118,638/month — #12,108 on PyPI (30-day window, as of 2026-08-14) |
| Known vulnerabilities | none known (OSV.dev, checked 2026-08-14) |
Evidence: wikipedia_mcp-2.0.1-py3-none-any.whl
Keywords: mcp, wikipedia, model-context-protocol, ai, llm
Tags
More Python Modules packages
Converts domain names between Unicode and…
permissive · top 100 on PyPI
setuptoolsSetuptools is a Python build backend and…
permissive · top 100 on PyPI
PyYAMLPyYAML parses and emits YAML 1.1 data format,…
permissive · top 100 on PyPI
pydanticPydantic validates Python data structures…
permissive · top 100 on PyPI
annotated-typesProvides reusable metadata objects for use with…
permissive · top 100 on PyPI
typing-inspectionProvides runtime tools to inspect and…
permissive · top 100 on PyPI
duckduckgo-mcp-serverProvides web search and content fetching…
permissive · top 15,000 on PyPI
mcp-server-qdrantExposes Qdrant vector search as a Model Context…
permissive · top 5,000 on PyPI
office-word-mcp-serverA Model Context Protocol server that exposes…
permissive · top 15,000 on PyPI
tilt-mcpTilt MCP Server exposes Tilt development…
permissive · top 15,000 on PyPI
django-mcp-serverExposes Django models and custom logic as Model…
permissive · top 15,000 on PyPI
cli-mcp-serverProvides a secure Model Context Protocol (MCP)…
unclear · top 15,000 on PyPI
wikipediaProvides simple Python access to Wikipedia…
permissive · top 5,000 on PyPI
mcp-atlassianAn MCP server that exposes Jira and Confluence…
unclear · top 5,000 on PyPI
Wikipedia-APIWikipedia-API is a Python wrapper for…
permissive · top 5,000 on PyPI
lexisnexisapiProvides a Python interface to the LexisNexis…
permissive · top 15,000 on PyPI