About un-datacommons-mcp
un-datacommons-mcp provides MCP tools and sample agents for retrieving public indicators and observations from Data Commons. It is intended for applications that need to query either base or custom Data Commons data.
Key features
- 01Query Data Commons public information
- 02Retrieve indicators and observations
- 03Support base and custom data
- 04Includes sample agents
Use cases
- 01Fetch public indicator data
- 02Look up observations for an application
- 03Build an agent using sample code
MCP support
The MCP server exposes tools for querying Data Commons indicators and observations.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx un-datacommons-mcpDC_API_KEYSecretData Commons API key from apikeys.datacommons.orgDC_TYPEType of Data Commons to use: base|custom (default: base)CUSTOM_DC_URLCustom DC base URL when DC_TYPE=customDC_ROOT_TOPIC_DCIDSComma-separated root topic DCIDs for custom DCsDC_SEARCH_SCOPESearch scope for custom DCs: base_only|custom_only|base_and_customLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEData Commons Agent Toolkit
This repo contains MCP tools and sample agents for fetching public information from Data Commons.
Docs
MCP Server
Sample agents
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.