Teamwork.com
Run Teamwork projects, help desk, spaces and chat from an AI agent.

618 MCP servers with 12,363+ tools, ready to connect to Claude, ChatGPT, Cursor and Agentman agents over the Model Context Protocol.
234 of 618 connectors in ProductivityShow all
Run Teamwork projects, help desk, spaces and chat from an AI agent.
Edit, organise and export Tella screen recordings.
Search US home service pros, refine by clarifying questions, read reviews.
Read, create, complete and delete TickTick tasks, lists, habits and focus records.
Query your Tiller finance spreadsheet and let an agent write categories and notes back.
Draw diagrams, flowcharts and wireframes on a live tldraw canvas in the chat, and edit them by hand as the agent…
Search Google Meet, Zoom and Teams transcripts and notes.
Triage your inbox, plan your week, create projects and complete tasks.
Search The L Suite's peer-ranked directory of outside counsel.
Search U.S. state trial court dockets, rulings, verdicts and judge analytics.
Read, search and update Trello boards, cards, checklists, Inbox and Planner.
Search, view and compare hotels on Tripadvisor.
Search accommodation on trivago from an AI assistant.
Benchmark software pricing, search contracts and pull negotiation playbooks.
Give a coding agent your organization's component library, design tokens and engineering standards.
Search bookable Turkish Airlines flights, check status, look up a PNR, track baggage and price an upgrade.
Get real-time Uber fare and ETA estimates between two US locations.
Search restaurants and menus on Uber Eats.
Search your organisation's Udemy Business catalogue and build learning paths and AI Role Play scenarios.
Parse PDFs, scans, spreadsheets and email into structured AI-ready data.
Search support conversations, monitor SLAs and read analytics.
Find jobs or talent, post jobs and manage proposals and contracts from an AI agent.
Read, create and edit Valuecase digital sales rooms.
Search Lithuanian and EU legislation, case law and regulator guidance with citations.
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.