How we expose a full project tracker over MCP (so agents can file and close issues)

Taskfolk has launched a public MCP server that lets AI agents create, assign, comment on, and close issues in a real project tracker, with the same permissions and workflow as human users. The company treats agents as named members with their own API keys, never billing them as seats, and supports both Bearer and OAuth authentication. Early adopters importing from Jira, Trello, and Linear found that mapping states and members before letting agents write is critical.

Most "AI project tools" wrap a chatbot around a board. We needed the opposite: a real issue tracker that agents can drive over MCP, with the same permissions and workflow humans use. This is the writeup of how Taskfolk does that, what we ship today, and what broke when we imported Jira, Trello, and Linear into an agent-writable workspace. If an agent cannot create, assign, comment, and close the same issues a human sees, it is not on the team. It is a sidecar. We treat agents as named members. Each one has its own API key. They are never billed as seats. Public MCP Streamable HTTP : https://taskfolk.ai/api/mcp/v1 https://taskfolk.ai/api/mcp/v1 Registry id: ai.taskfolk/mcp Docs and connect notes Claude, Cursor, VS Code : https://github.com/taskfolk/mcp https://github.com/taskfolk/mcp Auth is Bearer or OAuth. The server card is at https://taskfolk.ai/.well-known/mcp/server-card.json https://taskfolk.ai/.well-known/mcp/server-card.json REST is at https://taskfolk.ai/api/v1 https://taskfolk.ai/api/v1 if you want the same workspace without MCP. Once connected, a coding agent in Cursor or Claude can: The board does not change shape for the agent. Same projects, same members, same permissions. Three things showed up fast: If you import, map states and members before you let an agent write. Site: https://taskfolk.ai https://taskfolk.ai Free: unlimited members, 5 projects, 25 AI credits. Viewers are free. Agents are never billed as seats. Pro is $3/editor. Business is $6/editor. If you already run MCP clients, start at the GitHub README rather than the marketing page.