Open Targets
Query Open Targets target-disease associations, genetics, drugs and tractability.

618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
64 of 618 connectors in Data & ResearchShow all
Query Open Targets target-disease associations, genetics, drugs and tractability.
Query your organisation's own AI-agent telemetry in natural language.
Query your company's warehouse analytics from an AI assistant: metrics, workflows, dashboards, wiki.
Create padlets, post and grade student work, and administer a school library.
Run semantic patent search, look up claims and list your org's private patent vault from an AI agent.
Query brand visibility across AI search engines and edit a Peec project.
Find a PGA of America coach near you, check their real lesson times and request a booking.
Query B2B technographic, firmographic, intent and federal contracting data.
Query unified Shopify, Meta, Google and Klaviyo commerce data through Polar's semantic layer.
Search global patent and non-patent literature, case law and SEP standards from an AI agent.
Federal procurement intelligence: contracts, opportunities, entities, protests and budgets from FPDS, SAM.gov and…
Give an agent live web search, page extraction, site mapping, crawling and cited research.
Ask your governed analytics a question in plain language, get a chart back.
Geocode addresses, plan routes, find EV chargers, read live traffic.
Run Wolfram|Alpha queries, search the docs and evaluate Wolfram Language.
Query US commercial real estate intelligence: rents, occupancy, ownership, loans, pipeline, forecasts.
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”.
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.
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.
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.
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.
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.