Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

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

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

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nullary": {
      "type": "remote",
      "url": "https://mcp.nullary.ai/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "nullary": {
      "type": "http",
      "url": "https://mcp.nullary.ai/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=nullary&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLm51bGxhcnkuYWkvbWNwIn0%3D"
}

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

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

extensions:
  "nullary":
    enabled: true
    name: "nullary"
    type: streamable_http
    uri: "https://mcp.nullary.ai/mcp"
    timeout: 300

Quality 91 / 100strong

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations35 of 35 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 7,995 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

35 tools, about 7,995 tokens to load them all · tool set 66f6f95c00f0 · checked 2026-10-20 15:26 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 86 / 100

provenance75

liveness100

freshness65

hygiene100

+repository +dns-namespace +reachable +uptime-100% ~updated-149d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://mcp.nullary.ai/mcp` streamable-http	none	yes	100%	287 ms	2025-11-25	2026-10-20

Tools (35)

`get_compound`read-only	A compound (structure, name, max clinical phase) + its full negative profile across modalities/sources.
`get_coverage`read-only	Per-modality and per-source coverage stats (honest Phase-1 numbers).
`get_finding_provenance`read-only	Full provenance + detail for a single finding by id.
`get_model_card`read-only	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`read-only	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`read-only	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`read-only	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`read-only	ADC failures attributed to linker chemistry.
`search_admet_failures`read-only	Small-molecule ADMET failures.
`search_admet_failures_all_modalities`read-only	ADMET failures across ALL modalities.
`search_ancestry_specific_failures`read-only	Ancestry-specific CRISPR failures.
`search_bispecific_format_failures`read-only	Bispecific format/engineering failures.
`search_developability_failures`read-only	Antibody developability failures.
`search_drug_drug_interaction_failures`read-only	Drug-drug interaction failures.
`search_failed_adcs`read-only	ADCs that failed at any stage.
`search_failed_bispecifics`read-only	Bispecifics that failed at any stage.
`search_failed_clinical_antibodies`read-only	Discontinued/terminated clinical antibodies.
`search_failed_essentiality_screens`read-only	Non-dependency / failed essentiality screens.
`search_failed_guides`read-only	Failed/ineffective CRISPR guides.
`search_failed_oligonucleotides`read-only	ASOs/siRNAs that failed engagement/developability.
`search_failed_peptide_therapeutics`read-only	Failed peptide therapeutics.
`search_failed_protacs`read-only	PROTACs that failed degradation/ternary/permeability.
`search_failed_replications`read-only	Findings that failed to replicate.
`search_failed_selectivity`read-only	Small molecules that failed selectivity.
`search_failed_vaccines`read-only	Failed/terminated vaccines (by pathogen/indication).
`search_inactive_compounds`read-only	Inactive small-molecule compound-target pairs.
`search_indication_history`read-only	ALL failed approaches for an indication across every modality.
`search_mechanism_failures`read-only	Approaches that failed for a mechanism (by target).
`search_oligo_delivery_failures`read-only	Oligonucleotide delivery failures.
`search_pathogen_history`read-only	Vaccine + antimicrobial + antibody failures for a pathogen.
`search_peptide_stability_issues`read-only	Peptide stability/half-life failures.
`search_protac_e3_issues`read-only	PROTAC E3-ligase recruitment / ternary failures.
`search_safety_failures`read-only	Clinical/preclinical safety failures across modalities.
`search_target_history`read-only	ALL failed approaches against a target across every modality.
`search_vaccine_immunogenicity_failures`read-only	Failed vaccine immunogen designs.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.nullary/nullary",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-16/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.nullary.ai/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.1",
  "repository": {
    "url": "https://github.com/nullary-ai/nullary",
    "source": "github"
  },
  "description": "Negative results intelligence for drug discovery — query measured failures via MCP."
}