About Wikipedia MCP Server
A Python MCP server that provides Wikipedia content for a requested topic in generative AI contexts. Clients can retrieve the page title, content, and URL.
Key features
- 01Fetch Wikipedia content by topic
- 02Return page title, content, and URL
- 03Accept requests at the HTTP /mcp endpoint
- 04Provide success and error response formats
Use cases
- 01Supply Wikipedia content for AI question answering
- 02Look up topic information in Cursor Composer
MCP support
The server accepts requests containing a topic and returns a Wikipedia page title, content, and URL to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEWikipedia MCP Server
This is an MCP (Model Control Protocol) server that provides Wikipedia content for the requested topic.
Setup
- Install the required dependencies:
pip install -r requirements.txt
- Start the server:
python src/server.py
The server will run on http://localhost:5000.
API Usage
Using the API from the CLI
Send a POST request to /mcp with a JSON body containing a topic field:
curl -X POST http://localhost:5000/mcp \
-H "Content-Type: application/json" \
-d '{"topic": "Python_(programming_language)"}'
Using the API from Cursor Composer
- Ask a question about a topic on Wikipedia
- Cursor will display a proposed MCP request and ask for your permission to run the tool
- After approving, Cursor will execute the request to the MCP Server
- The prompt result will be based on the selected models analysis of the MCP Server response
Response Format
Successful response:
{
"status": "success",
"data": {
"title": "Page Title",
"content": "Page Content",
"url": "Wikipedia URL"
}
}
Error response:
{
"status": "error",
"error": "Error message"
}
Testing
Run the test script to verify the server is working:
python src/test_server.py
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.