"Connecting to a vector knowledge base" matching MCP servers:

MCP server for connecting Claude Desktop to a local medical knowledge base with real-time file watching, enabling natural language interaction with medical documents.

Search Vascue's public healthcare-operations documentation: AI front desk for clinics, provider-side insurance claims automation, Cliniko integration, security. Public content only.

Builds and manages a cardiology-focused knowledge graph in Neo4j by extracting medical entities and relationships from documents using LLMs. It enables users to ingest PDFs, refine extracted data, and perform natural language queries to gain clinical insights.

Enables searching and retrieving detailed medical knowledge on diseases, vaccines, medical examinations, and treatments, supporting health-related queries and medical concept understanding.

Enables natural-language querying of a mock legacy healthcare database and returns validated FHIR resources (Patient, Observation, Condition).

Enables AI assistants to read COVID-19 lateral flow test results from photographs by calling a deployed computer-vision pipeline, returning verdicts like positive or negative with confidence.

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 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).

Enables variant annotation and effect prediction using the Ensembl VEP API, with support for batch and single queries.

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.

Enables AI agents to rank US healthcare organizations for clinical trial site feasibility, predicting patient accrual for a Graves' disease protocol using claims and registry data.

A structure-aware MCP server for querying the SPOKE biomedical knowledge graph, enabling entity resolution, schema introspection, path finding, and safe Cypher queries for biomedical knowledge inference.

MyChart MCP Server

Enables scoring the WHO-5 Well-Being Index from five answers, returning a 0–100 score and a low, reduced, or normal band without providing a diagnosis.

An MCP server for longevity and metabolic medicine that provides a medication catalog, dosing protocols, contraindication screening, drug interaction checks, lab recommendations, and patient intake pathways across 35 compounds.

Provides direct SQL access to a locally hosted Reactome database, enabling schema discovery, guarded read-only queries, and ergonomic helpers over the full relational schema.

Enables a dental office's AI agent to verify benefits for a batch of up to 25 patients in a single MCP call, returning coverage percentages, frequency limits, waiting periods and deductible/annual-maximum remaining, each tied to a plan-clause citation. Exceptions such as identity mismatches or ambiguous cases are routed to a human review queue rather than guessed, with every call audit-logged.

Enables agents to interact with a clinic booking API, including listing specialties, doctors, and a patient's appointments, and booking or cancelling appointments when the active profile permits, while preserving the caller's authority and screening tool descriptions for safety.

Exposes a clinic's knowledge base and structured records to Claude Desktop as callable tools, with read tools grounded with citations and write tools gated behind approval.

Enables querying a synthetic patient dataset with tools to look up patients by ID, age, disease, name, and get statistics, connecting Claude Desktop to local data.

Enables LLM agents to search biomedical literature, retrieve article details, find related papers, manage caching, and download open-access full texts through MCP with structured, agent-friendly responses.

Provides safe read-only access to synthetic healthcare data via FHIR R4, enabling AI assistants to search patients, retrieve vitals, and summarize conditions using a public sandbox.

Enables editing and querying of Gene Ontology Causal Activity Models (GO-CAMs) through the Barista API. Supports model creation, individual and fact management, evidence addition, and causal pathway construction for biological knowledge representation.

An MCP server that exposes a DICOMweb-compliant DICOM archive to AI assistants. It lets any MCP-capable client search studies, series and instances, inspect metadata, read Structured and Encapsulated PDF Reports, and render image frames — all through natural language.

A Model Context Protocol (MCP) server for searching the National Provider Identifier (NPI) registry. This server provides tools to search and retrieve information about healthcare providers and organizations in the United States.

Enables read-only FHIR access to Practice Fusion EHR to search patients, appointments, conditions, medications, and lab results.

Enables conversational access to 400,000+ clinical trials on ClinicalTrials.gov, allowing users to search, compare, and retrieve trial details using plain English through MCP-compatible clients like Cursor and Claude Desktop.

Enables AI coding agents to search and retrieve official CryoSPARC documentation with version awareness, using a local prebuilt index for safe and fast access.

Enables MCP clients to query educational dermatology knowledge, access optional MoleCare mole-tracking and analysis tools, and explore MLOps and infrastructure operations with safe mock data when no credentials are configured.

Enables MCP clients to calculate a 28-point hemodialysis patient stability score and retrieve its thresholds and decision ranges, returning parameter scores, trends, red-flag overrides, and contextual clinical messages without storing data or requiring network access.