"JSON Web Tokens" matching MCP servers:

Privacy layer for healthcare AI agents. Pseudonymises patient identifiers (NHS numbers, names, dates of birth, addresses; UK and US) into labelled tokens locally before text reaches an agent, then restores the originals afterwards, keeping the token map out of agent context.

Condition-aware ingredient & product safety intelligence for AI agents. Every answer carries a claim-level evidence attestation, verdict, an evidence tier, and a citation – curated against authoritative sources (LactMed, InfantRisk, PubMed, DSLD, DermNet, EU CosIng) by Health AI. Hosted MCP server – no install, no key. Endpoint: https://mcp.healthai.com (Streamable HTTP, JSON-RPC 2

Enables LLM clients and agents to produce realistic synthetic medical referral letter PDFs — a German Überweisungsbrief/Arztbrief or the same letter in another language — either from structured JSON with deterministic, seeded rendering or from a free-text description written by a configured LLM. Each call returns the finished PDF as an embedded resource plus the completed letter content and its seed as structured data.

Enables AI assistants to upload clinical documents and medical device images for health data extraction, normalization, and retrieval of structured coded results in formats such as JSON, FHIR, HL7, CSV, and Parquet.

Exposes configured SiLA 2 servers as MCP tools so clients can discover their features, read properties, and invoke commands (including observable ones) without writing a client script per instrument. Server features are discovered dynamically, and results are returned as JSON with SiLA error details on failure.

A TypeScript MCP server for interacting with CDISC Define-XML 2.0 and 2.1 files, enabling users to load, search, and retrieve clinical data metadata including datasets, variables, and codelists. It supports local file processing with document caching and provides responses in both JSON and Markdown formats.

Enables MCP agents to read messy lab and instrument spreadsheet exports by detecting headers, cleaning table bounds, parsing decimal commas, preserving LOD/LOQ qualifiers, and returning JSON rows with column metadata.

MCP server for OpenBCI hardware via BrainFlow, enabling board connection, streaming, signal processing, and export with a web dashboard.

Reads raw lab-instrument files (microscopy, mass spectrometry, chromatography, flow cytometry, NMR, electrophysiology, spectroscopy, plate readers, qPCR) without vendor software, returning metadata, images, spectra and traces as JSON. It also checks files for damage, runs common analyses, and exports to open formats such as OME-TIFF, OME-Zarr, mzML, Parquet and NWB.

Enables LLM agents to programmatically inspect hardware resources, run in-memory inference benchmarks, list supported fMRI studies, and retrieve cortical and subcortical atlas region indices via JSON-RPC 2.0.

Enables comprehensive interaction with DHIS2 health information systems through 40+ tools covering complete Web API functionality. Supports data management, tracker programs, analytics, and bulk operations for DHIS2 development and administration.

Enables querying of per-residue missense tolerance, Pfam domain annotations, and variant counts for human transcripts by wrapping the MetaDome web service. Provides MCP tools for resolving transcripts, requesting tolerance landscapes, and identifying constrained regions.

Exposes MCP tools that compute longevity and metabolic metrics (autophagy index, GKI, MAGE), cardio-renal biomarkers (BUN/creatinine ratio, cardiac output and TPR, nocturnal BP dipping), chronobiology estimates (DLMO, melanopic lux, caffeine clearance), plus neuro-recovery and biomechanics scores. Runs as a zero-dependency Python JSON-RPC 2.0 stdio server so any MCP-compatible client can query these physiological domain calculators.

Enables agents to generate fully synthetic U.S. medical-billing specimen PDFs and benefit notices, each paired with ground-truth JSON describing the injected billing errors, written only into a caller-supplied workspace folder for testing document extraction and bill-review tools.

Enables an agent to log doses, observations, and tasks on a per-person shift-change board, run a deterministic readiness check that cites public drug-label sources, seal a hash-chained handover brief, and replay the audit chain through nine MCP JSON-RPC tools with idempotent mutations.

Exposes standardized MCP tools over SSE and JSON-RPC that let an Alexa+ agent retrieve patient vitals and medication adherence, control Ring doorbells and smart deadbolts, dispatch emergency escalations with SBAR triage notes, and log immutable care events to a cloud ledger. This enables proactive, autonomous health monitoring and emergency response on an Echo Show for elderly people living alone.

Enables MCP clients to discover and invoke domain-specialized tools for humanitarian emergency response, public health, research synthesis, grant proposals, human rights monitoring, maternal health, and SOP synthesis. It supports JSON-RPC 2.0 over Streamable HTTP for structured, privacy-conscious field outputs and voice-friendly summaries.

An MCP server providing public plant bioinformatics APIs including UniProt, NCBI, InterProScan, PDB, AlphaFold, Ensembl Plants, and web-based resources like Sol Genomics and BAR, without local data. It supports gene lookups, protein summaries, structure retrieval, and functional annotations through natural language.

An MCP server for managing a home medicine box, enabling AI assistants to query medicines, recognize images, compute expiry dates, and get medication advice via stdio JSON-RPC.

MCP server that connects AI assistants to a live Ketcher window, the open-source web-based chemical structure editor. Draw, edit, and organize structures directly in the canvas you have open.