mosaic-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mosaic-mcpsearch for targets related to KRAS"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mosaic-mcp
Pre-clinical drug discovery intelligence as an MCP server. Query 800+ drug targets, 12K+ compounds, 46K+ 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.
Quick Start
pip install mosaic-mcpWith Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"mosaic": {
"command": "mosaic-mcp",
"env": {
"DATABASE_URL": "postgresql://reader:password@ep-xxx-pooler.neon.tech/mosaic_db?sslmode=require"
}
}
}
}With Claude Code
claude mcp add mosaic -- mosaic-mcpStandalone
export DATABASE_URL="postgresql://..."
export MOSAIC_API_KEY="msk_..." # Optional — for Pro tools
mosaic-mcp # stdio transport (default)
mosaic-mcp --transport sse --port 3001 # SSE for remote clientsRelated MCP server: pubmed-search
Tools
Free Tier (16 tools) — discovery + workspace
Tool | Description |
| Search drug targets by name, gene symbol, or keyword |
| Comprehensive target dossier (biology, compounds, scores) |
| Compounds tested against a target with SAR data |
| Patent landscape for a target |
| Literature for a target |
| 3D structure and ligandability summary for a target |
| Knowledge graph overview statistics |
| Available disease indications |
| Sub-indications within an indication area |
| Per-target activity across sub-indications |
| Target attractiveness scoring |
| Add a target to your personal wishlist |
| Create a watchlist |
| Add an item to a watchlist |
| Retrieve a watchlist |
| List your watchlists |
Pro Tier (28 additional tools) — analysis + whitespace
The committed-verdict layer. Includes the whitespace and differentiation tools:
mosaic_synthetic_lethal_whitespace, mosaic_modality_gaps,
mosaic_resistance_bypass_map, mosaic_find_undruggable_targets,
mosaic_talent_migration, mosaic_emerging_signals, and
mosaic_assess_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
Entity | Count |
Drug Targets | 801 (oncology + neuroscience + cardiovascular) |
Compounds | 12,756 |
Clinical Trials | 18,324 |
Papers | 46,354 |
Patents | 16,168 |
Semantic Relations | 13,704 |
Indications | 15,013 |
Organizations | 45,496 |
Configuration
Variable | Required | Description |
| Yes | PostgreSQL connection string (Neon hosted or self-hosted) |
| No | API key for Pro tool access |
| No | Override tier ( |
License
Apache 2.0 for the MCP server tools. The hosted knowledge graph data requires a subscription for Pro-tier access.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sourabhnk/mosaic-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server