nullary
ai.nullary/nullaryVersion 1.0.1Negative results intelligence for drug discovery — query measured failures via MCP.
Status
Responds222 msAnswered our handshake without sign-in.- Last checked
- Nov 14, 2026, 13:31 UTC
- Latency
- 222 ms
- Remotes responding
- 1 of 1
- Sign-in
- No sign-in
- Hosting
- Hosted outside the EU (detected)
- Registry data as of
- Nov 14, 2026, 21:12 UTC
Data from the official MCP Registry, checked by run.zero. How we check
Connect
Streamable HTTP
https://mcp.nullary.ai/mcpResponds222 msNo sign-in
Claude Code
claude mcp add --transport http nullary https://mcp.nullary.ai/mcpClaude Desktop and claude.ai
Settings > Connectors > Add custom connector
Name: nullary
Remote MCP server URL: https://mcp.nullary.ai/mcpCursor
{
"mcpServers": {
"nullary": {
"url": "https://mcp.nullary.ai/mcp"
}
}
}VS Code
code --add-mcp '{"name":"nullary","type":"http","url":"https://mcp.nullary.ai/mcp"}'Built your own server? run.zero hosts MCP servers on European infrastructure.
Tools
35 tools
Read-only | Idempotent | Open world | ||
|---|---|---|---|---|
get_compoundA compound (structure, name, max clinical phase) + its full negative profile across modalities/sources. | No | Yes | Yes | Yes |
get_coveragePer-modality and per-source coverage stats (honest Phase-1 numbers). | No | Yes | Yes | Yes |
get_finding_provenanceFull provenance + detail for a single finding by id. | No | Yes | Yes | Yes |
get_model_cardPer-target Layer-1 model card: training counts and held-out scaffold-split metrics (ROC-AUC, PR-AUC, Brier, calibration). Accepts a gene symbol (e.g. EGFR) or UniProt accession (e.g. P00533). | No | Yes | Yes | Yes |
get_target_landscapeTarget 'graveyard' / exhaustion index: how many distinct compounds/agents have been tried against a target and failed, broken down by modality and outcome. Answers 'how picked-over is this target?'. Accepts a gene symbol (e.g. EGFR) or a UniProt accession (e.g. P00533). | No | Yes | Yes | Yes |
list_modelsSummary of the Layer-1 inactivity-scoring model registry: how many per-target models, split by family, and median scaffold-split ROC-AUC. | No | Yes | Yes | Yes |
list_top_targetsCoverage browse: the most heavily-pursued ('graveyard') targets, ranked by recorded negative findings. Optional family filter (kinase, gpcr, protease, nuclear_receptor, ion_channel, transporter, phosphatase, other). | No | Yes | Yes | Yes |
search_adc_linker_failuresADC failures attributed to linker chemistry. | No | Yes | Yes | Yes |
search_admet_failuresSmall-molecule ADMET failures. | No | Yes | Yes | Yes |
search_admet_failures_all_modalitiesADMET failures across ALL modalities. | No | Yes | Yes | Yes |
search_ancestry_specific_failuresAncestry-specific CRISPR failures. | No | Yes | Yes | Yes |
search_bispecific_format_failuresBispecific format/engineering failures. | No | Yes | Yes | Yes |
search_developability_failuresAntibody developability failures. | No | Yes | Yes | Yes |
search_drug_drug_interaction_failuresDrug-drug interaction failures. | No | Yes | Yes | Yes |
search_failed_adcsADCs that failed at any stage. | No | Yes | Yes | Yes |
search_failed_bispecificsBispecifics that failed at any stage. | No | Yes | Yes | Yes |
search_failed_clinical_antibodiesDiscontinued/terminated clinical antibodies. | No | Yes | Yes | Yes |
search_failed_essentiality_screensNon-dependency / failed essentiality screens. | No | Yes | Yes | Yes |
search_failed_guidesFailed/ineffective CRISPR guides. | No | Yes | Yes | Yes |
search_failed_oligonucleotidesASOs/siRNAs that failed engagement/developability. | No | Yes | Yes | Yes |
search_failed_peptide_therapeuticsFailed peptide therapeutics. | No | Yes | Yes | Yes |
search_failed_protacsPROTACs that failed degradation/ternary/permeability. | No | Yes | Yes | Yes |
search_failed_replicationsFindings that failed to replicate. | No | Yes | Yes | Yes |
search_failed_selectivitySmall molecules that failed selectivity. | No | Yes | Yes | Yes |
search_failed_vaccinesFailed/terminated vaccines (by pathogen/indication). | No | Yes | Yes | Yes |
search_inactive_compoundsInactive small-molecule compound-target pairs. | No | Yes | Yes | Yes |
search_indication_historyALL failed approaches for an indication across every modality. | No | Yes | Yes | Yes |
search_mechanism_failuresApproaches that failed for a mechanism (by target). | No | Yes | Yes | Yes |
search_oligo_delivery_failuresOligonucleotide delivery failures. | No | Yes | Yes | Yes |
search_pathogen_historyVaccine + antimicrobial + antibody failures for a pathogen. | No | Yes | Yes | Yes |
search_peptide_stability_issuesPeptide stability/half-life failures. | No | Yes | Yes | Yes |
search_protac_e3_issuesPROTAC E3-ligase recruitment / ternary failures. | No | Yes | Yes | Yes |
search_safety_failuresClinical/preclinical safety failures across modalities. | No | Yes | Yes | Yes |
search_target_historyALL failed approaches against a target across every modality. | No | Yes | Yes | Yes |
search_vaccine_immunogenicity_failuresFailed vaccine immunogen designs. | No | Yes | Yes | Yes |
Details
- Registry status
- Active
- Published
- May 25, 2026
- Updated
- May 25, 2026
- Website
- Not given
- Categories
- Uncategorized
- GDPR
- Not declared