PostHog
Run HogQL, build dashboards, ship feature flags and triage errors.

618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
618 connectors
Run HogQL, build dashboards, ship feature flags and triage errors.
Manage Postman collections, specs, environments and mocks, and run a collection against live APIs.
Create, query and delete Prisma Postgres databases from an AI agent.
Issue virtual payment cards, set spend limits, pause or permanently close them, and read the full card number.
Start workflow runs, complete tasks, update form fields and query data sets.
Build, brand, publish and analyse AI assessments and lead magnets.
Query Profound AI-search visibility, citation and bot-traffic analytics, and build or run Profound Agents.
Search 41 million biomedical citations and retrieve PMC full text.
Search and update Pylon support issues, accounts and contacts.
Read a European business bank account and act on invoicing, cards and approvals.
Query earnings call transcripts, filings, slide decks and financials for 15,000+ public companies.
Create endpoints, set rate limits, manage security rules and read billing across 80+ chains.
Read texts and call transcripts from a Quo business phone number and send SMS.
Deploy, redeploy and debug apps on Railway's usage-billed cloud.
Search your participant panel, build studies from templates, schedule interviews and act on incentives.
Query corporate card spend from your AI assistant: tools stage Ramp data, execute_query runs SQL.
Ramp Rate software benchmarks and the Ramp AI Index, as aggregated market data.
Compare published Canadian mortgage rates from your AI assistant.
Query Razorpay payments, orders, refunds and payouts from your AI assistant.
Read Read AI meeting transcripts, summaries and action items.
Search every highlight you have saved and triage your Reader inbox.
Let an AI agent reschedule, cancel and create real Calendar and Outlook events.
Design, build and analyse Remesh research conversations.
Query global employment, payroll, time off and org structure.
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.