New · Dimensions Analytics MCP

Query Dimensions from any AI assistant

The Dimensions Analytics MCP is now available. It connects AI clients directly to the Dimensions Analytics API, giving analysts, researchers, and developers a natural-language interface to the world's largest linked research database — without writing a single line of integration code.

What you can do

• Ask questions across 450M+ interconnected records — publications, grants, patents, clinical trials, datasets, and policy documents — and get structured, citable answers in seconds

• Run aggregations and trend analyses: funding by funder, output by year, citation networks, geographic breakdowns

• Profile researchers, organizations, and funders by querying across linked records

• Resolve identifiers (DOIs, PMIDs, Dimensions IDs) and look up affiliations and grant numbers

• Execute raw DSL queries for advanced, programmatic use cases

• Introspect the schema to understand available fields and filters

Works with your existing tools

Compatible with Claude Desktop, Claude Code, ChatGPT, VS Code (GitHub Copilot), Cursor, and any MCP-compatible client.

1. Get your API key - Log in to Dimensions and retrieve your API key from your My Account page.

2. Install the MCP server - Configuration instructions are available here.

3. Restart your client - Restart your AI client to activate the server.

If you're on a special Dimensions instance, configure your base URL via the DIMENSIONS_BASE_URL environment variable — full details in the reference docs.

Read more: Digital Science connects AI agents to world-leading research data with new Dimensions MCP servers — the launch announcement, which also covers the companion Dimensions Semantic Search MCP.