MCP directory
Find the right research tool.
Search trusted Model Context Protocol servers for bioinformatics, data access, and computational research.
7 MCPs
Showing 7 results on this page
breadcrumbsMCP
A Model Context Protocol (MCP) server that discovers and interacts with bioinformatics services through embedded "breadcrumb" metadata in HTML pages.
UCSCCBmcp
A Model Context Protocol (MCP) server that provides access to UCSC Cell Browser datasets by parsing the dataset.json file from https://cells.ucsc.edu/dataset.json.
STRING-MCP
A comprehensive Python package for interacting with the STRING database API through a Model Context Protocol (MCP) bridge.
Gene Expression Omnibus (GEO) MCP
A Model Context Protocol (MCP) server for accessing GEO (Gene Expression Omnibus) data through NCBI E-Utils API. The tool will enable you to search for GEO datasets, series, samples, platforms, and profiles for your LLM. Tested with Claude Desktop, chatGPT has no out of the box support for this tool yet. Claude will automatically use the tools if it fits the context.
PLSDBmcp
PLSDB MCP Server Model Context Protocol server for interacting with the PLSDB (Plasmid Database) API. This server provides tools to search, filter, and retrieve plasmid data from PLSDB.
Folklore Clinical Variant Interpretation MCP
Official public, read-only MCP from Helena Bioinformatics for clinical germline variant interpretation. It resolves supported GRCh38 SNVs and simple indels, returns source-backed evidence, provenance, automated ACMG/AMP variant-level decision support, and related PubMed literature. It accepts no patient or case context and does not provide a diagnosis or treatment recommendation; qualified genetics professional review is required.
FlowProof
FlowProof is the execution and provenance layer for MCP-enabled bioinformatics. Where data-access servers (e.g. GEOmcp, STRINGmcp) let an assistant look things up, FlowProof lets it actually run a pipeline and prove the result. Each run emits a Workflow Run RO-Crate recording the pipeline, exact tool versions, parameters, and SHA-256 checksums of every input and output, so an AI-produced result is reproducible byte-for-byte. It runs locally over stdio (your data stays on your machine) or as a hosted HTTP endpoint, and exposes six MCP tools: list, describe, run, status, results, provenance. Seed pipelines: ont-read-stats (Oxford Nanopore read QC, runs on a built-in sample with no input), variant-call-short, rnaseq, fetchngs, viralrecon. Install with: uvx flowproof-mcp