Wikidata MCP Server
A community-driven MCP server that enables AI agents to interact with Wikidata's knowledge graph. It provides tools to search for entities, fetch detailed entity data, resolve external identifiers (such as DOI, PMID, ORCID), and execute SPARQL queries against the Wikidata Query Service. It supports both STDIO and Streamable HTTP transports and requires no API key.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Search for Wikidata items or properties by text query
- Fetch full entity details by QID or PID with language filtering
- Execute SPARQL SELECT queries against the Wikidata Query Service
- Resolve external identifiers like DOI or ORCID to Wikidata items
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
@cyanheads/wikidata-mcp-server 0.3.0
{
"version": "0.3.0",
"transport": "stdio",
"identifier": "@cyanheads/wikidata-mcp-server",
"runtimeHint": "npx",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"environmentVariables": [
{
"name": "WIKIDATA_USER_AGENT",
"format": "string",
"default": "wikidata-mcp-server/0.1 (https://github.com/cyanheads/wikidata-mcp-server)",
"description": "User-Agent string for Wikimedia requests. Wikimedia policy requires a descriptive value."
},
{
"name": "WIKIDATA_SPARQL_TIMEOUT_MS",
"format": "string",
"default": "55000",
"description": "Max time to wait for a SPARQL response in milliseconds."
},
{
"name": "WIKIDATA_REST_TIMEOUT_MS",
"format": "string",
"default": "10000",
"description": "Max time to wait for REST API responses in milliseconds."
},
{
"name": "MCP_LOG_LEVEL",
"format": "string",
"default": "info",
"description": "Sets the minimum log level for output (e.g., 'debug', 'info', 'warn')."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"wikidata-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/wikidata-mcp-server@0.3.0"
],
"env": {
"WIKIDATA_USER_AGENT": "<YOUR_WIKIDATA_USER_AGENT>",
"WIKIDATA_SPARQL_TIMEOUT_MS": "<YOUR_WIKIDATA_SPARQL_TIMEOUT_MS>",
"WIKIDATA_REST_TIMEOUT_MS": "<YOUR_WIKIDATA_REST_TIMEOUT_MS>",
"MCP_LOG_LEVEL": "<YOUR_MCP_LOG_LEVEL>"
}
}
}
}Cline
{
"mcpServers": {
"wikidata-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/wikidata-mcp-server@0.3.0"
],
"env": {
"WIKIDATA_USER_AGENT": "<YOUR_WIKIDATA_USER_AGENT>",
"WIKIDATA_SPARQL_TIMEOUT_MS": "<YOUR_WIKIDATA_SPARQL_TIMEOUT_MS>",
"WIKIDATA_REST_TIMEOUT_MS": "<YOUR_WIKIDATA_REST_TIMEOUT_MS>",
"MCP_LOG_LEVEL": "<YOUR_MCP_LOG_LEVEL>"
}
}
}
}VS Code
{
"servers": {
"wikidata-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyanheads/wikidata-mcp-server@0.3.0"
],
"env": {
"WIKIDATA_USER_AGENT": "<YOUR_WIKIDATA_USER_AGENT>",
"WIKIDATA_SPARQL_TIMEOUT_MS": "<YOUR_WIKIDATA_SPARQL_TIMEOUT_MS>",
"WIKIDATA_REST_TIMEOUT_MS": "<YOUR_WIKIDATA_REST_TIMEOUT_MS>",
"MCP_LOG_LEVEL": "<YOUR_MCP_LOG_LEVEL>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"wikidata-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/wikidata-mcp-server@0.3.0"
],
"env": {
"WIKIDATA_USER_AGENT": "<YOUR_WIKIDATA_USER_AGENT>",
"WIKIDATA_SPARQL_TIMEOUT_MS": "<YOUR_WIKIDATA_SPARQL_TIMEOUT_MS>",
"WIKIDATA_REST_TIMEOUT_MS": "<YOUR_WIKIDATA_REST_TIMEOUT_MS>",
"MCP_LOG_LEVEL": "<YOUR_MCP_LOG_LEVEL>"
}
}
}
}Let your agent find its tools
Find servers like Wikidata MCP Server from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.