# ai.nullary/nullary

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

- name: ai.nullary/nullary
- version: 1.0.1
- connection class: R0 (autonomous)
- trust: 86/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.nullary%2Fnullary
- tools: https://api.protogrid.dev/v1/servers/ai.nullary%2Fnullary/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 100
- freshness: 65
- provenance: 75
- drivers: +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.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 35 of 35 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 7,995 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 35, about 7,995 tokens to load them all
- tool set hash: 66f6f95c00f00e14142891e290cd996b
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.nullary/nullary.svg)](https://protogrid.dev/servers/ai.nullary/nullary)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp.nullary.ai/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (35)

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