Home / MCP registry index / ai.nullary/nullary

ai.nullary/nullary

ai.nullary/nullary in the official MCP registry. Endpoint https://mcp.nullary.ai/mcp. Source: github.com/nullary-ai/nullary.

The registry describes it as: Negative results intelligence for drug discovery — query measured failures via MCP.

We read its 35 tools on 2026-10-22. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.

A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.

Tools it advertises

search_inactive_compounds search_failed_selectivity search_admet_failures search_failed_guides search_failed_essentiality_screens search_ancestry_specific_failures search_developability_failures search_failed_clinical_antibodies search_failed_peptide_therapeutics search_peptide_stability_issues search_failed_protacs search_protac_e3_issues search_failed_oligonucleotides search_oligo_delivery_failures search_failed_vaccines search_vaccine_immunogenicity_failures search_failed_adcs search_adc_linker_failures search_failed_bispecifics search_bispecific_format_failures search_admet_failures_all_modalities search_drug_drug_interaction_failures search_mechanism_failures search_failed_replications search_safety_failures search_target_history search_indication_history search_pathogen_history get_compound get_finding_provenance get_target_landscape list_top_targets list_models get_model_card get_coverage

Run this server? Show the check in your README

The badge reflects the latest weekly read: MCP tool check badge

Markdown
[![MCP tool check](https://lazaretto.dev/mcp-registry/ai-nullary-nullary/badge.svg)](https://lazaretto.dev/mcp-registry/ai-nullary-nullary)

How this was checked

Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.

To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.