"A GitHub repository for agent guardrails" matching MCP servers:

An open source biomedical research agent that provides LLMs with 28 tools for drug discovery, protein analysis, literature search, medical imaging, omics, and sandbox execution, all running locally via Ollama and MedGemma.

AI-powered HEOR (Health Economics and Outcomes Research) MCP server with 7 tools for literature search across 41 medical data sources, cost-effectiveness modeling (Markov/PartSA/PSA), and HTA dossier preparation for NICE, EMA, FDA, IQWiG, HAS, and EU JCA submissions.

Upload your raw DNA file from 23andMe, AncestryDNA, MyHeritage, FamilyTreeDNA, or any VCF -- and watch a team of AI agents fan out across 16+ public genomics databases, share discoveries with each other in real time, and produce a comprehensive health report. Everything runs on your machine. Nothing is uploaded anywhere.

Enables compiling typed decision queries into the smallest decision-sufficient evidence context with machine-checkable Context Certificates, providing auditable executable-biology inference through local MCP tools.

A local-first MCP server for querying multi-omic personal health data (genome, labs, wearables) with an honesty contract and progressive disclosure skills.

Provides medical symptom extraction, differential diagnosis generation, PubMed literature search, and abstract summarization tools for LLM agents.

Enables medical care management by retrieving and synthesizing PubMed literature, drafting provider emails for user review, and supporting human-in-the-loop approvals.

Enables MCP-capable AI agents to query OneAquaHealth FHIR R4 water, air and population-health data through a single standard interface, receiving a deterministic OK/CAUTION/DO_NOT_USE trust verdict, reasons and a citable FHIR reference for every value. It also exposes official OAH code definitions and supports citizen reports drafted into IG-conformant Observations, written back only after explicit human approval.

Enables prediction of blood-brain barrier permeability for drug molecules via machine learning, with molecule name lookup, plain-language explanations, similar drug search, and applicability domain checks. Exposes these as MCP tools and orchestrates them via a LangGraph agent.

This server enables interacting with the National Digital Health Mission's Health Information User (HIU) API, allowing agents to access and manage health information through the Multi-Agent Conversation Protocol.

Enables analysis of clinical trial protocols using MCP tools for document listing, entity extraction, adverse event clustering, and summarization.

Provides a six-tool research-assistance workflow for CRC-LNM cases using precomputed CT, pathology features, and clinical values. Enables multimodal analysis and research queries on deidentified cases.

MCP server for headless care coordination, providing tools for case-aware provider search powered by ai-carematch.

Enables scenario-based clinical communication practice through MCP tools for discovering scenarios, starting sessions, sending practitioner turns, and receiving evidence-linked evaluation feedback.

Enables LLM agents to query de-identified FHIR-shaped hospital data through audited, read-only tools for patients, encounters, conditions, observations, medications, and interaction checks, while any medication write stays a draft that a clinician must confirm out-of-band.

Enables secure natural language querying of a clinical SQL Server database using a local Ollama model, with strict SQL validation to protect sensitive data.

Enables LLMs to interact with OpenEHR electronic health record systems by retrieving clinical archetypes, generating AQL queries from natural language, and executing queries against on-premise EHR databases. Supports OpenEHR Clinical Knowledge Manager integration and custom IIS-hosted EHR APIs for comprehensive medical data access.

Enables AI agents to search and analyze clinical trial data from ClinicalTrials.gov using both structured SQL queries for filtering trials by status, phase, and conditions, and semantic vector search for exploring detailed protocol information like exclusion criteria.

Enables genomic sequence analysis through the Evo 2 model, supporting DNA sequence scoring, embedding, generation, and variant effect prediction with multiple model checkpoints (7B, 40B, 1B parameters).

Exposes four CMS public datasets as callable tools in Claude conversations, enabling natural-language real-world evidence analytics without SQL expertise.