
Mosaic Pre-Clinical Intelligence
io.github.sourabhnkPublished by GitHub account sourabhnkv2.2.1Updated Oct 25, 2026
Pre-clinical drug-target intelligence: 60 curated targets, 1,969 counted partner genes, 11 tools
The publisher's own server: [PREPROD] Clinical.ly Research Suite
Overview
A local MCP server that answers pre-clinical drug-target questions from your own PostgreSQL Mosaic database, with 5 free and 6 Pro tools.
- What you can do
- Look up target dossiers, compounds with measured activity, papers and AlphaFold structures, each with a coverage state so missing data is not shown as zero. Check a coverage grid for any human gene symbol, resolving identity and structure live. With Pro enabled, review clinical trials, assay validation precedent, pathway context and the target's 1-hop network. Assess synthetic-lethal whitespace and candidate resistance-bypass targets. Free calls return up to 10 compounds or papers; Pro up to 50.
- When to use it
- Use it when you already hold a PostgreSQL instance with the Mosaic schema and want an assistant to query drug-target intelligence locally over stdio. It is not a source of Mosaic's curated data; for that, the README points to a separate hosted server.
- Requirements
- A local Python runtime (pip, uvx or python -m) and a PostgreSQL or Neon connection string in DATABASE_URL ending in /mosaic_db, holding the Mosaic schema. Optional MOSAIC_TIER and MOSAIC_API_KEY. Stdio only; remote transport is not implemented in this package.
Installation
In SourceWeft
- Open Mosaic Pre-Clinical Intelligence in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
mosaic-mcp
Pre-clinical drug-target intelligence as an MCP server: target profiles, compounds, literature, structure, clinical pipeline, validation precedent and whitespace analysis — 11 tools, 5 free and 6 Pro. Every count carries a coverage state, so "we did not look" never renders as zero.
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, with the Mosaic schema, and it serves the tools over it. There is no public read-only credential for Mosaic's knowledge graph.
If you want Mosaic's curated knowledge graph — 60 oncology targets, ~128K compounds linked to them, 57,896 papers and 9,062 clinical trials (counted 2026-10-07), refreshed monthly — use the hosted server. It needs no database and no local install:
- Claude.ai connector (OAuth, Streamable HTTP):
https://mcp.getmosaic.dev/mcp - Remote MCP with an API key (SSE):
https://mcp.getmosaic.dev/sse - Sign in, API keys and on-demand dossiers for any human gene: https://getmosaic.dev
Quick start (self-hosted)
With Claude Desktop
Add to your claude_desktop_config.json:
With Claude Code
Standalone
uvx mosaic-mcp and python -m mosaic_mcp.server work too. This package is
stdio-only: --transport sse exits with NotImplementedError, because
remote transport is the hosted server above.
Tools
Free (5)
Free calls return up to 10 compounds or papers; Pro up to 50.
Pro (6)
mosaic_request_dossier and mosaic_get_dossier (on-demand dossiers) run only
on the hosted server; they need its fetch and synthesis pipeline.
Configuration
Changelog
Full history in CHANGELOG.md. Latest: 2.1.1 — the
mosaic-mcp command starts again (it had failed with ImportError since
1.7.0). 2.1.0 capped mcp below 2, without which a fresh install died on
import, and carried the fixes from a live audit of the hosted server.
License
Apache 2.0 for the MCP server tools. The hosted knowledge graph data requires a subscription for Pro-tier access.
Source: README.md at commit 49b7ac1
Tools
0Version history
6- v2.2.1LatestOct 17, 2026
- v2.2.0Oct 16, 2026
- v2.1.3Oct 14, 2026
- v2.1.1Oct 7, 2026
- v2.0.0Sep 22, 2026
- v1.7.2Sep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Clinical integrations
[PREPROD] Clinical.ly Research Suite
ly.clinical.api-preprodOfficial publisher
[PREPROD] Clinical.ly Research Suite's hosted MCP server, published by api-preprod.clinical.ly; credential required; Streamable HTTP.

Zovo Trial Finder
Published by GitHub account theluckystrike
A remote MCP server that lets an assistant find recruiting clinical trials for a condition, optionally near a city, and pull details of a specific study.

HealthStylz Clinical Nutrition & Circadian Environment MCP
Published by GitHub account harrybuild
Remote MCP server giving assistants HealthStylz dietitian articles, NIH/PubMed supplement evidence, AG1 cost math, and curtain and herb guides.

US Healthcare NPI Leads, FDA Recalls & ClinicalTrials
Published by GitHub account jesleytassili-glitch
US Healthcare NPI Leads, FDA Recalls & ClinicalTrials's hosted MCP server; credential required; Streamable HTTP.

Clinical Codes Mcp
Published by GitHub account mrfentmen
Local MCP server that lets an assistant look up LOINC lab codes, ICD-10-CM diagnoses and condition names from the NIH Clinical Tables API.