Mosaic Pre-Clinical Intelligence MCP server

mosaic-mcp

<!-- mcp-name: io.github.sourabhnk/mosaic-mcp -->

Pre-clinical drug discovery intelligence as an MCP server. Query 760+ drug targets, 70K+ compounds, 48K+ papers, 18K+ clinical trials, and 16K+ patents through 44 specialized tools — 16 free for discovery, 28 Pro for competitive landscapes, whitespace, and thesis-grade analysis.

Which one do you want?

This package is bring-your-own-database. It is the MCP tool layer only — it ships the queries, not the data. You point it at a PostgreSQL instance you control and it serves 44 tools over it. There is no public read-only credential for Mosaic's knowledge graph, and earlier versions of these docs implied otherwise.

If you want Mosaic's actual curated KG — 760+ targets, 70K+ compounds, 48K+ papers, 18K+ trials, 16K+ patents, kept current by a monthly refresh — use the hosted server instead. It needs no database and no local install:

• Remote MCP: https://mcp.getmosaic.dev/sse
• Sign in / API keys:

Quick Start (self-hosted)

pip install mosaic-mcp

With Claude Desktop

Add to your claudedesktopconfig.json:

{
  "mcpServers": {
    "mosaic": {
      "command": "mosaic-mcp",
      "env": {
        "DATABASE_URL": "postgresql://USER:PASSWORD@YOUR-HOST:5432/mosaic_db?sslmode=require"
      }
    }
  }
}

With Claude Code

claude mcp add mosaic -- mosaic-mcp

Standalone

export DATABASE_URL="postgresql://..."   # your own Postgres
export MOSAIC_API_KEY="msk_..."          # Optional — for Pro tools
mosaic-mcp                               # stdio transport

This package is stdio-only. --transport sse exits with NotImplementedError; remote transport is served by the hosted endpoint above, not by this package. The flag was previously documented as working.

Tools

Free Tier (16 tools) — discovery + workspace

Pro Tier (28 additional tools) — analysis + whitespace

The committed-verdict layer. Includes the whitespace and differentiation tools: mosaicsyntheticlethalwhitespace, mosaicmodalitygaps, mosaicresistancebypassmap, mosaicfindundruggabletargets, mosaictalentmigration, mosaicemergingsignals, and mosaicassess_druggability.

Plus the full analysis set: competitive landscape, pathway context, compound selectivity, indication landscape, target validation, clinical pipeline, compound analogs, target comparison, similar-target search, opportunity finding, organization portfolio, target network, mechanism of action, evidence maps, relation search, polypharmacology, clinical trial results, FDA regulatory status, drug comparison, drug repurposing candidates, and KOL discovery.

Data Coverage

Shortened. The full README is on GitHub.