DOCS BLOG ABOUT TRY THE GATEWAY

// MCP TOOL REFERENCE

NULLARY TOOLS

35 tools from the Nullary MCP Server, categorised by risk level.

View the Nullary policy → Token cost: 7,055 tokens →

// ALL 35 NULLARY TOOLS

READ 35 tools

Read get_compound A compound (structure, name, max clinical phase) + its full negative profile across modalities/sources. Read get_coverage Per-modality and per-source coverage stats (honest Phase-1 numbers). Read get_finding_provenance Full provenance + detail for a single finding by id. Read get_model_card Per-target Layer-1 model card: training counts and held-out scaffold-split metrics (ROC-AUC, PR-AUC, Brier,... Read get_target_landscape Target 'graveyard' / exhaustion index: how many distinct compounds/agents have been tried against a target ... Read list_models Summary of the Layer-1 inactivity-scoring model registry: how many per-target models, split by family, and ... Read list_top_targets Coverage browse: the most heavily-pursued ('graveyard') targets, ranked by recorded negative findings. Opti... Read search_adc_linker_failures ADC failures attributed to linker chemistry. Read search_admet_failures Small-molecule ADMET failures. Read search_admet_failures_all_modalities ADMET failures across ALL modalities. Read search_ancestry_specific_failures Ancestry-specific CRISPR failures. Read search_bispecific_format_failures Bispecific format/engineering failures. Read search_developability_failures Antibody developability failures. Read search_drug_drug_interaction_failures Drug-drug interaction failures. Read search_failed_adcs ADCs that failed at any stage. Read search_failed_bispecifics Bispecifics that failed at any stage. Read search_failed_clinical_antibodies Discontinued/terminated clinical antibodies. Read search_failed_essentiality_screens Non-dependency / failed essentiality screens. Read search_failed_guides Failed/ineffective CRISPR guides. Read search_failed_oligonucleotides ASOs/siRNAs that failed engagement/developability. Read search_failed_peptide_therapeutics Failed peptide therapeutics. Read search_failed_protacs PROTACs that failed degradation/ternary/permeability. Read search_failed_replications Findings that failed to replicate. Read search_failed_selectivity Small molecules that failed selectivity. Read search_failed_vaccines Failed/terminated vaccines (by pathogen/indication). Read search_inactive_compounds Inactive small-molecule compound-target pairs. Read search_indication_history ALL failed approaches for an indication across every modality. Read search_mechanism_failures Approaches that failed for a mechanism (by target). Read search_oligo_delivery_failures Oligonucleotide delivery failures. Read search_pathogen_history Vaccine + antimicrobial + antibody failures for a pathogen. Read search_peptide_stability_issues Peptide stability/half-life failures. Read search_protac_e3_issues PROTAC E3-ligase recruitment / ternary failures. Read search_safety_failures Clinical/preclinical safety failures across modalities. Read search_target_history ALL failed approaches against a target across every modality. Read search_vaccine_immunogenicity_failures Failed vaccine immunogen designs.

// FAQ

How many tools does the Nullary MCP server have? +

The Nullary MCP server exposes 35 tools across 1 categories: Read.

How do I enforce policies on Nullary tools? +

Route the Nullary server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Nullary tools fall into? +

Nullary tools are categorised as Read (35). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.