NPI Registry
Look up and search US provider records from the CMS NPPES NPI Registry.
MCP connectors
618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
35 of 618 connectors in HealthcareShow all
Healthcare connectors
Owkin
Query TCGA histopathology slides — cell-type quantification, tumour-microenvironment features, cohort survival.
PopHIVE
Query Yale's harmonized US public-health surveillance data — flu, COVID, RSV, measles, overdose, chronic disease…
PubMed
Search 41 million biomedical citations and retrieve PMC full text.
Scholar Gateway
Search over 8 million peer-reviewed Wiley journal articles with DOI-linked citations.
Scite
Search papers, patents, trials, grants and FDA records, with Smart Citations showing if later work supported or…
SNOMED CT Terminology
Look up, validate and expand SNOMED CT clinical concepts from your AI agent.
Strava
Query your own Strava training history from an AI agent.
Synapse.org
Search Synapse research datasets and read entity metadata, annotations and provenance.
Synthesize Bio
Generate synthetic human gene expression data from a plain-language experiment description and run differential…
Turquoise
Query US negotiated healthcare rates — hospital, lab, drug, device — plus a payer/provider graph.
Product names and logos belong to their owners. Each connector is built by its own developer, and Agentman is not affiliated with them. The ones Agentman builds and runs are marked “Built and run by Agentman”.
FAQ
Common questions about MCP servers
What is an MCP server?
A server that exposes a tool’s capabilities over the Model Context Protocol, so an AI agent can call them directly. It is the standard way to let an assistant act in a system rather than just describe it.
How do I connect one of these to Claude or ChatGPT?
Each server page carries its connection URL, which works in any MCP-compatible client. In Agentman Studio connecting is one click and there is no config file to edit.
Are these servers built by Agentman?
Most are not. Each is built by its own developer, and each page names them and links to their documentation. The few Agentman builds and runs are marked “Built and run by Agentman”. Every page lists what the server exposes and cites the sources its factual claims come from.
How do I know what a server can actually do to my data?
Each page lists the tools the server exposes. Where we could read the server directly, every tool carries the safety label its vendor gave it: read-only, acts, or destructive. Each page also has a Limits section; read both before connecting anything to a production system.
Use them in an agent
Put these connectors to work.
Connect any of these once and your agents call their tools on their own: on a schedule, in a workflow, with nobody at the keyboard.