"How to connect and execute queries on a private SQL database" matching MCP servers:

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

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 clean-room SHARP-on-MCP compliant FHIR R4 MCP server that enables AI agents to interact with any FHIR R4 endpoint using SHARP context headers, without server-side OAuth. It provides clinical tools, lab results, imaging, and interactive MCP-UI dashboards.

MCP server for the STRING protein–protein interaction database, hosted by STRING at mcp.string-db.org. Adapted for LLM grounding: responses are size-limited and include metadata and notes on interpretation and next steps. Tools cover identifier resolution, interaction networks and evidence, functional and PPI enrichment, and sequence similarity search.

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

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.

Public read-only MCP server providing structured access to Atlarium habitat data and advisory functions for aquariums, terrariums, and related systems.

MyChart MCP Server

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).

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.

MCP server for interacting with Galaxy bioinformatics platform, enabling AI assistants to connect to Galaxy instances, search and execute tools, manage workflows, and access other features.

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 natural language exploration of OMOP CDM databases for concept discovery, patient count queries, and cohort SQL generation with support for multiple database backends.

Enables an AI agent to query a patient-records SQLite database with tools for schema inspection, safe SQL queries, patient risk assessment, and readmission risk analysis.

Enables natural language querying of healthcare claims data by exposing a SQLite database with read-only SQL tools, allowing users to ask questions in plain English and get answers backed by real database queries.

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 searching the NIAID Data Ecosystem for biomedical research resources including datasets, clinical studies, and publications using Elasticsearch queries.

Enables natural language queries about Swiss mandatory health insurance coverage for medications and medical devices using official BAG lists.

Enables language models to search biomedical literature, fetch sequences, and follow links across Entrez databases through eleven read-only tools wrapping the nine NCBI Entrez E-utilities. It handles URL building, pacing, redirects, response caps, and API-key redaction so queries can be answered without a browser or scraping.

Explains why two scientific papers disagree. A contradiction explorer for bench scientists that compares two studies' designs and grounds every claim in a verbatim quote from the source text.

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.

Enables querying and monitoring Brazilian Federal Council of Medicine resolutions on AI, telemedicine, and electronic medical records, with a local searchable copy and official document links.

MCP server enabling AI agents to search and retrieve evidence reviews from evipedia.ai on health and longevity interventions, and to suggest new interventions for review.

MCP server that reads glucose data from a FreeStyle sensor via the LibreLinkUp API, providing current glucose and history with explicit coverage and gaps.

Monitors PubMed and medRxiv for configurable research topics, summarizes papers using a local LLM, and stores deduplicated results in a local database.

Works out a health plan from your own record: which screening is due and evidence-based suggestions with citations. Reads and writes one health-roadmap.json file on your machine; nothing is sent to a server.

Enables searching fictional lab tests, comparing prices, quoting and booking sample collections, and escalating to a human agent via natural language.

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.

Enables AI agents to retrieve cited pharmacogenomic and gene-variant information, including drug–gene guidance from CPIC/DPWG and rsID lookups, so responses can quote curated sources instead of relying on memory. A local package also lets users read raw DNA files on their own computer without sending the file data to the remote service.