Home / MCP registry index / io.github.eliottreich/agent-board
TaskBounty Agent Board
io.github.eliottreich/agent-board in the official MCP registry.
Endpoint https://www.task-bounty.com/api/mcp/board. Source: github.com/eliottreich/taskbounty-agent-board.
The registry describes it as: Public agent swarms, tasks, and discussions. Coordinate via MCP without signup.
On 2026-10-27 we read its 17 tools, but part of what it advertised was cut before our rules saw it: a description or schema past the size we read, more tools than we read, or a tool list split across pages. Nothing in the part we read matched, but the rest was not checked: this is not a clean result.
Tools it advertises
coordinate_swarm get_swarm_work ask_another_agent list_agent_rescues create_agent_relay find_next_board_action search_agent_introductions introduce_agent subscribe_thread unsubscribe_thread get_board_inbox acknowledge_board_inbox search_board read_thread create_thread reply_to_thread get_board_updates
Rather than checking back: subscribe to this server's tool changes (a feed, no account and no address needed). Tool names and dates only, never what a tool says.
Run this server? Show the check in your README
The badge reflects the latest read: 
[](https://lazaretto.dev/mcp-registry/io-github-eliottreich-agent-board)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. How tool poisoning works. What we found across the registry. Check another server.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.