Log inSubmit server
Mosaic Pre Clinical Intelligence logo

Mosaic Pre Clinical Intelligence

Query a PostgreSQL-backed drug discovery knowledge graph for targets, compounds, patents, papers, trials, and watchlists.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Mosaic Pre Clinical Intelligence

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mosaic-pre-clinical-intelligence-2": {
      "command": "uvx",
      "args": [
        "mosaic-mcp"
      ],
      "env": {
        "DATABASE_URL": "YOUR_VALUE_HERE",
        "MOSAIC_API_KEY": "YOUR_VALUE_HERE",
        "MOSAIC_TIER": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 11 tools correctly (15d ago).

Overview

Mosaic Pre-Clinical Intelligence MCP server exposes pre-clinical drug discovery queries through MCP, covering targets, compounds, patents, papers, indications, scores, and watchlists. The package is a self-hosted stdio tool layer that connects to a PostgreSQL database you provide; it does not include Mosaic's curated dataset. Use it for target research and workspace tracking when you have a compatible database, or use Mosaic's hosted endpoint for the curated knowledge graph without local installation. Free tools support discovery, while an API key can enable Pro analysis and whitespace tools.

Use cases

  • Search targets by gene symbol or keyword
  • Review compounds and SAR data for a target
  • Inspect patents and papers around a target
  • Compare target activity across sub-indications
  • Track targets and research items in watchlists

Key features

  • Target profiles, scores, structures, and ligandability
  • Compound, patent, paper, and indication queries
  • Sub-indication activity breakdowns
  • Target wishlists and watchlists
  • Pro competitive, whitespace, and drug discovery analysis
  • PostgreSQL-backed stdio MCP transport

Tools11

What Mosaic Pre Clinical Intelligence lets your agent do. Expand a tool for its parameters.

Verified live~3.1k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

6/6 checks healthy over the last 45d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · mosaic-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

Last commit5d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed11Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Mosaic Pre Clinical Intelligence works

What Mosaic Pre-Clinical Intelligence does

The Mosaic Pre-Clinical Intelligence MCP server provides an MCP interface for querying and analyzing pre-clinical drug discovery data. Its discovery tools cover target search, target profiles, compounds and SAR data, patent landscapes, scientific papers, structures, ligandability, indications, sub-indications, and target attractiveness scores.

It also includes workspace features for adding targets to a personal wishlist and creating, updating, listing, and retrieving watchlists. The broader package includes Pro tools for competitive landscapes, whitespace analysis, target validation, clinical pipelines, compound comparisons, drug repurposing, KOL discovery, and related research questions.

The repository describes data coverage for targets, compounds, clinical trials, papers, patents, semantic relations, indications, and organizations. These figures apply to the curated hosted knowledge graph; the self-hosted package itself supplies query tools rather than bundled data.

How it works

The Mosaic Pre-Clinical Intelligence MCP server runs as a standard-input/standard-output process and sends database queries and results through MCP. It requires access to a PostgreSQL instance controlled by the operator. The package does not provide a public read-only credential or automatically connect to Mosaic's hosted dataset.

Install the package with pip install mosaic-mcp, configure the database connection, and start the mosaic-mcp executable. MCP clients can then invoke the registered tools. mosaic_kg_stats can be used to inspect the knowledge graph available through the configured database rather than relying on published counts.

The package separates free discovery and workspace functions from Pro analysis. Pro access uses an optional API key, and the configured tier can also be overridden with an environment variable. The hosted service is a separate option at https://mcp.getmosaic.dev/sse and provides access to Mosaic's maintained knowledge graph without a local database or package installation.

Setup and configuration

Set DATABASE_URL to a PostgreSQL connection string for the database that the server will query. MOSAIC_API_KEY is optional and enables Pro tool access. MOSAIC_TIER can override the selected tier with values such as free, pro, or enterprise.

Claude Desktop can launch the executable through its MCP server configuration, with DATABASE_URL supplied in the environment. Claude Code can add the server with claude mcp add mosaic -- mosaic-mcp. A standalone launch uses the same environment variables followed by mosaic-mcp.

Limitations and notes

The Mosaic Pre-Clinical Intelligence MCP server is stdio-only. Passing --transport sse is not supported by this package and raises NotImplementedError; remote transport is provided by the hosted endpoint instead.

Watchlist ownership requires an owner_key in the form anon:<token>. A caller should generate and retain a random token, then reuse it for subsequent operations. Bare user IDs and email addresses are rejected. Reads and writes are owner-scoped in SQL, and watchlists are excluded from the response cache.

The repository's listed counts are dated and can change. Use mosaic_kg_stats for current figures in the connected database. The hosted knowledge graph's Pro access requires a subscription. The MCP server tools are licensed under Apache 2.0, while hosted data access has separate subscription requirements.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Mosaic Pre Clinical Intelligence

Mosaic Pre-Clinical Intelligence is an MCP server that connects to a PostgreSQL database and exposes tools for drug target search, target profiles, compounds, patents, papers, structures, indications, scores, and watchlists. The package supplies the query layer, while the operator provides the database and optional API key for Pro tools.

Install it with `pip install mosaic-mcp`, set `DATABASE_URL` to your PostgreSQL connection string, and run `mosaic-mcp`. Claude Desktop can launch it from an MCP configuration, while Claude Code can add it with `claude mcp add mosaic -- mosaic-mcp`.

No, the package does not include the curated knowledge graph or a public read-only credential. It is a bring-your-own-database query layer. Use the hosted endpoint at `https://mcp.getmosaic.dev/sse` for Mosaic's curated data without a local database.

Set `MOSAIC_API_KEY` before starting the server to enable Pro tool access. Pro tools cover competitive landscapes, whitespace analysis, target validation, clinical pipelines, compound analysis, and other advanced research functions.

No, the package supports stdio only. Passing `--transport sse` raises `NotImplementedError`; use Mosaic's hosted remote endpoint for SSE access instead.

Related MCP servers

All in Biology & Bioinformatics All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMosaic Pre Clinical Intelligence AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mosaic-pre-clinical-intelligence-2?style=directory)](https://allmcps.com/mcp/mosaic-pre-clinical-intelligence-2)
HTML Embed
<a href="https://allmcps.com/mcp/mosaic-pre-clinical-intelligence-2"><img src="https://allmcps.com/api/badge/mosaic-pre-clinical-intelligence-2?style=directory" alt="Mosaic Pre Clinical Intelligence on AllMCPs" /></a>