MCP Server

What is MCP?

The Model Context Protocol (MCP) is an open standard that lets AI assistants -- like Claude Desktop, Claude Code, and other MCP-aware clients -- connect to external data sources and tools. BRC Analytics runs a public MCP server that exposes our full catalog (organisms, assemblies, workflows) and ENA sequencing-data search as a set of tools your assistant can call directly.

Once connected, you can ask questions like "What assemblies do you have for Plasmodium falciparum?" or "Find me Illumina RNA-seq runs for taxonomy ID 5833" in plain language, and the assistant will pull live answers from BRC Analytics instead of guessing.

This is an experimental feature -- the tool surface and connection details may change.

Connecting

The MCP endpoint is:

https://brc-analytics.org/api/v1/mcp

Claude Desktop

Edit your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows) and add:

{
  "mcpServers": {
    "brc-analytics": {
      "url": "https://brc-analytics.org/api/v1/mcp"
    }
  }
}

Restart Claude Desktop. You should see the brc-analytics server listed in the tools panel.

Other clients

Any MCP-compliant client that supports HTTP transport can connect using the same URL. Consult your client's documentation for the exact config format.

Running locally

If you're running the BRC Analytics backend yourself (see the project README), swap the URL for http://localhost:8000/api/v1/mcp (or http://localhost:8080/api/v1/mcp when using the Docker stack).

What you can do with it

The server provides two groups of tools:

Catalog tools -- explore curated BRC content:

• Search organisms by name, taxonomy ID, or taxonomic group
• List and inspect genome assemblies, including ploidy and annotation status
• Browse workflow categories and individual workflow details
• Check whether a given workflow is compatible with a given assembly
• Resolve the inputs (reference genome URL, gene model) that a workflow needs for a particular assembly

ENA tools -- search the European Nucleotide Archive for raw sequencing data:

• Find sequencing runs by NCBI taxonomy ID
• Search by keywords (organism names, library strategies like RNA-Seq or WGS, platforms like Illumina or PacBio)

Results from ENA searches are capped at 50 records per call, with a has_more flag if additional results exist.

Things to try

Once connected, try prompts like:

• "Which BRC organisms are in the Apicomplexa group?"
• "Show me the diploid assemblies you have, and tell me which variant-calling workflows are compatible with them."
• "For assembly GCF_000002765.6, resolve the inputs for the variant-calling workflow. What still needs to be provided?"
• "Find paired-end Illumina runs in ENA for taxonomy ID 5833."
• "What's in the Transcriptomics workflow category?"

The assistant will chain tool calls together as needed -- e.g., look up an organism, list its assemblies, check compatibility, and resolve inputs in a single conversation.

Limitations

• Read-only. The server exposes catalog and ENA data but cannot launch workflows on Galaxy. Use the BRC Analytics web interface to actually start an analysis.
• Snapshot of the catalog. Catalog data is the same as what powers the website -- it updates when we publish a new build, not in real time.
• ENA is a live external API. ENA searches go directly to the European Nucleotide Archive and can fail or rate-limit independently of BRC.

Feedback

The MCP server is new and we're actively iterating on the tool surface. If something is missing, broken, or confusing, email help@brc-analytics.org.