MCP server

Nullary Official

ai.nullary/nullary

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

Negative results intelligence for drug discovery — query measured failures via MCP.

Source

At a glance

Type

MCP server

Publisher

nullary.ai (verified by the MCP Registry)

Status

Working at last check

Tools

35

Token cost

About 8,352 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

25 Oct 2026, 20:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http nullary https://mcp.nullary.ai/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.nullary]
url = "https://mcp.nullary.ai/mcp"

Gemini CLI

{"mcpServers":{"nullary":{"httpUrl":"https://mcp.nullary.ai/mcp"}}}

Cursor

{"mcpServers":{"nullary":{"url":"https://mcp.nullary.ai/mcp"}}}

VS Code

{"servers":{"nullary":{"type":"http","url":"https://mcp.nullary.ai/mcp"}}}

Antigravity

agy mcp add nullary https://mcp.nullary.ai/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"nullary","server_url":"https://mcp.nullary.ai/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"nullary","server_url":"https://mcp.nullary.ai/mcp"}

Tools

• get_compound ~292 tokens
  A compound (structure, name, max clinical phase) + its full negative profile across modalities/sources.
• get_coverage ~45 tokens
  Per-modality and per-source coverage stats (honest Phase-1 numbers).
• get_finding_provenance ~63 tokens
  Full provenance + detail for a single finding by id.
• get_model_card ~112 tokens
  Per-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).
• get_target_landscape ~136 tokens
  Target '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).
• list_models ~65 tokens
  Summary of the Layer-1 inactivity-scoring model registry: how many per-target models, split by family, and median scaffold-split ROC-AUC.
• list_top_targets ~150 tokens
  Coverage 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).
• search_adc_linker_failures ~274 tokens
  ADC failures attributed to linker chemistry.
• search_admet_failures ~268 tokens
  Small-molecule ADMET failures.
• search_admet_failures_all_modalities ~275 tokens
  ADMET failures across ALL modalities.
• search_ancestry_specific_failures ~273 tokens
  Ancestry-specific CRISPR failures.
• search_bispecific_format_failures ~274 tokens
  Bispecific format/engineering failures.
• search_developability_failures ~272 tokens
  Antibody developability failures.
• search_drug_drug_interaction_failures ~252 tokens
  Drug-drug interaction failures.
• search_failed_adcs ~268 tokens
  ADCs that failed at any stage.
• search_failed_bispecifics ~272 tokens
  Bispecifics that failed at any stage.
• search_failed_clinical_antibodies ~276 tokens
  Discontinued/terminated clinical antibodies.
• search_failed_essentiality_screens ~276 tokens
  Non-dependency / failed essentiality screens.
• search_failed_guides ~269 tokens
  Failed/ineffective CRISPR guides.
• search_failed_oligonucleotides ~277 tokens
  ASOs/siRNAs that failed engagement/developability.
• search_failed_peptide_therapeutics ~272 tokens
  Failed peptide therapeutics.
• search_failed_protacs ~275 tokens
  PROTACs that failed degradation/ternary/permeability.
• search_failed_replications ~271 tokens
  Findings that failed to replicate.
• search_failed_selectivity ~272 tokens
  Small molecules that failed selectivity.
• search_failed_vaccines ~270 tokens
  Failed/terminated vaccines (by pathogen/indication).
• search_inactive_compounds ~274 tokens
  Inactive small-molecule compound-target pairs.
• search_indication_history ~228 tokens
  ALL failed approaches for an indication across every modality.
• search_mechanism_failures ~276 tokens
  Approaches that failed for a mechanism (by target).
• search_oligo_delivery_failures ~272 tokens
  Oligonucleotide delivery failures.
• search_pathogen_history ~226 tokens
  Vaccine + antimicrobial + antibody failures for a pathogen.
• search_peptide_stability_issues ~273 tokens
  Peptide stability/half-life failures.
• search_protac_e3_issues ~274 tokens
  PROTAC E3-ligase recruitment / ternary failures.
• search_safety_failures ~276 tokens
  Clinical/preclinical safety failures across modalities.
• search_target_history ~230 tokens
  ALL failed approaches against a target across every modality.
• search_vaccine_immunogenicity_failures ~274 tokens
  Failed vaccine immunogen designs.

Browse

• Health and medicine

Related MCP servers

• ivive.app
  Human hepatic clearance from in-vitro CLint, with the error band measured on known drugs.
• The Stall
  277 pay-per-call MCP tools: YouTube keyword research, stocks, crypto, DeFi, options, macro.
• Pharmacogenomics Guidelines
  Find pharmacogenomics guidelines, translate diplotypes, and retrieve prescribing recommendations.
• Agent Discovery Index
  Where AI agents discover products, and how to be listed there with measured results.
• ZenithEye Agent Commons
  Public coordination substrate for AI systems and humans with bounded MCP discovery and creation.
• KeyVex
  US public financial disclosures for AI agents: Congress trades, SEC filings, FEC, lobbying, more
• B.O.N.S.A.I. Health Intelligence API
  Lifestyle medicine health intelligence via x402 micropayments. 637+ peer-reviewed references.
• Chembl
  Link compounds to protein targets, rank bioactivity, and look up drug mechanisms and indications.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/ai.nullary/nullary.svg)](https://aptlynx.net/servers/ai.nullary/nullary)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents