Eight biomedical intelligence tools, callable from Claude Desktop, Cursor, ChatGPT, or any MCP-compatible agent. No auth required. Evidence-verified outputs.
Add GaiaLab to any MCP client. No API key, no sign-up. Discovery doc at /.well-known/mcp.json.
claude_desktop_config.json){
"mcpServers": {
"gaialab": {
"url": "https://www.gailabai.com/mcp",
"transport": "streamable-http"
}
}
}
.cursor/mcp.json){
"servers": {
"gaialab": {
"url": "https://www.gailabai.com/mcp"
}
}
}
curl -X POST https://www.gailabai.com/mcp \ -H "Content-Type: application/json" \ -d '{ "method": "tools/call", "params": { "name": "gaialab_get_target_brief", "arguments": { "gene": "KRAS", "diseaseContext": "pancreatic cancer" } } }'
curl https://www.gailabai.com/.well-known/mcp.json
Returns tool list, endpoint, and capability declaration in one JSON object. MCP clients use this for auto-configuration.
All tools return JSON. Evidence-verified outputs include grounded ratio, cite-F1, and PMID hallucination rate where applicable.
A typical translational researcher workflow using GaiaLab as a reasoning backend.
// Tool: gaialab_get_target_brief { "gene": "PARP1", "diseaseContext": "BRCA1-mutant ovarian cancer" } // Returns: protein function, AlphaFold pLDDT=92, druggabilityScore=95, // top drugs: Olaparib (Tier I, score 84), Niraparib (Tier I, score 79), // top pathways: DNA damage response (q=2.1e-8), homologous recombination (q=4.3e-7)
// Tool: gaialab_verify_claim { "claim": "PARP1 inhibition causes synthetic lethality in BRCA1-deficient cells", "pmids": ["18469177", "18455974"], "geneContext": ["PARP1", "BRCA1"] } // Returns: evidenceStatus="grounded", pmidsChecked=true, hallucinated=0, // citeF1=0.82, summary="All cited PMIDs verified as real."
// Tool: gaialab_generate_validation_plan { "hypothesis": "PARP1 inhibition causes synthetic lethality in BRCA1-deficient cells", "geneContext": ["PARP1", "BRCA1"], "diseaseContext": "BRCA1-mutant ovarian cancer" } // Returns: 4-stage plan: cell-line viability assay → clonogenic survival → // xenograft model → Phase II basket trial design, each with // controls, timeline, and go/no-go criteria
Every tool call fetches live data. No stale knowledge cutoffs.
Free tier: 50 analyses/day. Keys are optional — unauthenticated requests share a rate-limited pool.
# Check quota and usage stats curl -H "X-API-Key: gl_..." https://www.gailabai.com/api/keys/usage
<!-- Drop-in embed --> <div id="gaialab-widget" data-genes="BRCA1,TP53,PTEN" data-disease="triple-negative breast cancer"></div> <script src="https://www.gailabai.com/widget.js" async></script> // Programmatic: GaiaLab.render({ target: '#my-container', genes: ['KRAS', 'STK11'], disease: 'KRAS-mutant NSCLC', apiKey: 'gl_...', onReady: (info) => console.log('Snapshot:', info.snapshotId) });
Every analysis runs a 3-stage evidence integrity pipeline before returning results.
All AI-generated PMIDs batch-queried against NCBI E-utilities esummary. Hallucinated citations stripped before display. Rate reported on every result.
Claims verified against abstract text using cross-encoder/nli-deberta-v3-large. Entailment threshold 0.5. 2,500-char passage window.
Citation precision, recall, and F1 computed per ALCE benchmark methodology. cite-F1 ≥ 0.6 = well-grounded. Reported on every trust snapshot.
See full methodology · live trust dashboard · benchmark scores