Mcp Wikidata
About
A server implementation for Wikidata API using the Model Context Protocol (MCP).
Details
- Author
- zzaebok
- GitHub stars
- 47
- Downloads
- 274
- Categories
- Other
Jump to
- Search for a Wikidata entity ID by query string.
- Search for a Wikidata property ID by query string.
- Retrieve all properties associated with a given entity ID.
- Execute arbitrary SPARQL queries on Wikidata.
- Fetch the label and description for an entity in a specified language.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Mcp WikidataCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via Smithery (npx -y @smithery/cli install @zzaebok/mcp-wikidata --client claude) or manually using uv after cloning the repository. Run the server with uv run src/server.py. The server exposes five tools that the LLM can invoke to answer queries about Wikidata entities and properties.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp wikidata": {
"mcp-wikidata": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@zzaebok/mcp-wikidata",
"--client",
"claude"
]
}
}
}
}McpServers
{
"mcp-wikidata": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@zzaebok/mcp-wikidata",
"--client",
"claude"
]
}
}if you want to run client example together
$ uv sync --extra example
---
Run
Run the server with:
$ uv run src/server.py
If you want to test it with a simple client code (with langchain-mcp-adapters), run the client with:
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
