Predictive intelligence for drug discovery — Claude Code MCP server
The Predictive intelligence for drug discovery MCP server for Claude Code queries negative biomedical findings across seven modalities to check failed molecules and abandoned targets before lab testing.
no license 1,147 installs updated 2026-05-25
claude mcp add --transport http drug-discovery https://drug-discovery.run.toolsWhat Predictive intelligence for drug discovery does
This server connects an agent to failed experiment datasets across drug research. The index indexes 7 modalities, featuring 84.5M small molecules, 37.6M CRISPR screens, and 104K terminated clinical studies. Records come from ChEMBL, PubChem BioAssay, DepMap, ClinicalTrials.gov, and 10 other registries.
Every entry includes source provenance with DOI, PMID, and license details. Built-in tools like search_inactive_compounds and search_target_history report inactive candidate pairs, ADMET defects, or selectivity failures. You can also evaluate target fatigue with get_target_landscape using a gene identifier such as EGFR.
The integration relies entirely on a remote HTTP endpoint at https://drug-discovery.run.tools. No local datasets are required. Queries fail without an active internet connection to this host.
What it helps with
- Look up inactive small-molecule compound-target pairs
- Check target attrition and past failures by gene symbol
- Track terminated clinical trials and CRISPR screen dropouts
- Review ADMET defects and drug interaction risks across modalities
Example prompts for the agent
- Run
search_target_historyfor EGFR to inspect failed attempts across all modalities - Check inactive small-molecule candidates using
search_inactive_compounds - Inspect provenance and negative assay history for a compound with
get_compound
How to install Predictive intelligence for drug discovery
Platform CLI: remote server
claude mcp add --transport http drug-discovery https://drug-discovery.run.toolsPlatform CLI: remote server
codex mcp add predictive-intelligence-for-drug-discovery --url https://drug-discovery.run.toolsConfig file
{
"mcpServers": {
"predictive-intelligence-for-drug-discovery": {
"url": "https://drug-discovery.run.tools"
}
}
}Config file
{
"servers": {
"predictive-intelligence-for-drug-discovery": {
"type": "http",
"url": "https://drug-discovery.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http predictive-intelligence-for-drug-discovery https://drug-discovery.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Predictive intelligence for drug discovery
How to install Predictive intelligence for drug discovery in Claude Code?
Run claude mcp add --transport http predictive-intelligence-for-drug-discovery https://drug-discovery.run.tools. Alternatively, configure it under a shorter alias via claude mcp add --transport http drug-discovery https://drug-discovery.run.tools.
What does this MCP server do?
It lets agents search millions of negative findings, including inactive molecules, ineffective CRISPR guides, and halted clinical trials. Every finding comes with provenance data like DOI and PMID.
What databases are indexed by this server?
It indexes records from ChEMBL, PubChem BioAssay, DepMap, ClinicalTrials.gov, Retraction Watch, and 10 other scientific sources.