MCP server for hybrid medical consultation integrating Western and Traditional Chinese Medicine, enabling symptom analysis, diagnosis, and treatment suggestions through two specialized models.
An MCP server implementing the ROBINS-I V2 framework for risk-of-bias assessment in non-randomized studies, with deterministic algorithms and full provenance. It enables users to parse study documents, specify target trial results, answer signalling questions with evidence-bound quotes, and compute or override domain judgements.
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.
Monitors PubMed and medRxiv for configurable research topics, summarizes papers using a local LLM, and stores deduplicated results in a local database.
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 coding agents to interact with the Reactome pathway database, including search, lookup, hierarchy traversal, SBML/SBGN export, and gene-set enrichment analysis.
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 AI assistants and local LLMs to interact with BirdNET-Go bioacoustic observatories, providing tools to query recent and historical bird detections, monitor station health, and retrieve audio clips.
Enables natural language querying of EFSA's OpenFoodTox database containing 8,006 chemical substances with toxicity data, safety assessments, risk limits, and genotoxicity studies for food additives, pesticides, and contaminants.
Enables searching biomedical images (X-rays, CT/MRI, clinical photos, etc.) from the Open-i database using natural language queries, returning image results as Markdown links.
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.
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.
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.
Enables AI agents and applications to search, retrieve, and analyze chemical compounds, substances, and bioassays from PubChem's vast chemical information database through comprehensive tools for chemical research and discovery.
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.
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.
Integrates Diabetes:M data with Claude Desktop to access glucose readings, insulin data, food diary, and health metrics through natural language conversations.
MCP server that provides tools for querying the Human Phenotype Ontology (HPO) including term lookup, hierarchy exploration, cross-ontology mappings, and gene-phenotype-disease associations, all grounded in a local SQLite database for fast offline lookups.
Enables AI assistants to check the live FDA drug shortage database by generic name, brand name, active ingredient or NDC, returning current status, availability, shortage reasons and package-level details. Also supports browsing recently updated listings and counting shortages by status, therapeutic category or distinct product.
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.
A local-first MCP server that provides fast access to OpenEMR wiki pages, users guide, and selected API documentation through tools like search, page retrieval, and category listing.
Enables biopharma catalyst research by aggregating signals from ClinicalTrials.gov, PubMed, SEC EDGAR, openFDA, and Yahoo Finance, with a single tool to audit a ticker/drug combination and return a forensic verdict.
Enables AI assistants to securely read a user's own sundhed.dk health record data, including medications, lab results, vaccinations, and referrals, after MitID login via a local browser session.
Enables querying the openFDA drug adverse event database for pharmacovigilance work-ups: case searches, counts and demographic/outcome breakdowns, disproportionality measures (ROR/PRR with Mantel-Haenszel adjustment), and empirical Bayes (MGPS/EBGM) signal scores, including bulk screening and stratification by sex, age, or year alongside confounder-adjusted analyses.
Enables graph-based fraud propagation scoring for clinical diagnostics, diffusing risk across entities with a deterministic fallback when the ML model is unavailable.
Enables searching and retrieving molecular hydrogen medical literature from H2 Papers database, with per-paper safety notes always included in results.
Enables users to store and query their own medical data—labs, medications, diagnoses, wearables, and food logs—in a local Postgres database and interact with it through any MCP client, with deterministic safety checks.
Enables querying the WormBase database for C. elegans and nematode genomics data, including gene information, protein sequences, phenotypes, interactions, and expression patterns through natural language.
Enables AI assistants to query the eggNOG 7 database in natural language for protein lookups, orthologous groups, pairwise orthologs, protein families, taxonomy, and database statistics. Also delivers structured functional annotations such as KEGG KO and GO terms with confidence scores, plus an index of bulk-downloadable data files.
Enables AI assistants to search and retrieve bacterial strain details, taxonomy, culture media, 16S rRNA sequences, and genome information from the BacDive database through MCP tools.
An MCP server that provides access to PubMed and NCBI's biomedical literature database for searching articles, retrieving metadata, and tracking citations. It enables users to explore related research, browse MeSH vocabulary, and find free full-text links.
Enables healthcare AI interactions via MCP protocol with built-in EU AI Act compliance. Provides quick installation, well-documented API, and enterprise support.
Enables LLM-powered applications to look up bacterial and archaeal taxonomy, search genomes, browse and navigate the taxonomic tree, and compare genomes or find phylogenetic paths between taxa. It works out of the box with a built-in reference dataset covering major phyla and can be pointed at full Genome Taxonomy Database TSV files for comprehensive queries.
Lets Claude answer plain-language questions about Canadian drug shortages by combining Health Product Shortages Canada reports with Drug Product Database details, so users can check whether a drug is short, batch-check a watchlist of DINs, list Tier 3 shortages, find same-ingredient alternatives, and scan for stale or duplicate reports. Every report is returned with a freshness label and check-with-supplier flag, and the server can also build the dashboard locally from live data.
MCP server for connecting Claude Desktop to a local medical knowledge base with real-time file watching, enabling natural language interaction with medical documents.
Provides a Model Context Protocol server for accessing and querying biomedical data from BioThings services, including gene, variant, chemical, and taxon annotations.
This MCP server generates individualized meal plans for children with chronic kidney disease (CKD) based on KDIGO 2024/PRNT 2020/KRCP 2025 guidelines, incorporating patient age, CKD stage, allergies, dietary culture, and diet diary analysis. It provides deterministic nutrient computations and tools for meal plan generation, food database lookup, and risk analysis.
Enables publishing of medical content (articles, procedures, clinics) to a Korean skincare platform via a publishing API, requiring API URL and API key for authentication.
Enables interaction with the CEDAR (Center for Expanded Data Annotation and Retrieval) metadata repository to fetch templates and retrieve template instances. Supports querying structured metadata and biomedical data annotations through the CEDAR platform.
Converts messy metabolite names into standard database identifiers (KEGG, HMDB, ChEBI, PubChem, InChIKey) and performs crosswalking to Mouse-GEM for metabolic model input, with deterministic tools and an LLM reasoning layer for identity disambiguation.
Read-only access to a curated, evidence-labelled corpus of mTOR research: studies, entities, signed pathway relations with supporting and conflicting evidence, and open questions.