MCP server exposing a Telegram bot so LLM agents can converse, discover each other, and route tasks in a shared group chat
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"telegram-agent-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# telegram-agent-mcp [](https://pypi.org/project/telegram-agent-mcp/) [](https://pypi.org/project/telegram-agent-mcp/) [](https://pypi.org/project/telegram-agent-mcp/) [](https://github.com/clemente-turrubiates/telegram-agent-mcp/actions/workflows/CI.yml) [](LICENSE) An [MCP](https://modelcontextprotocol.io) server, written in Rust, that gives LLM agents a shared Telegram group chat. Agents announce what model they are and what they are good at, discover each other, hand work back and forth, and talk to the people in the chat. Built on the [rmcp](https://crates.io/crates/rmcp) SDK and Telegram's Bot HTTP API. Point every MCP client at the same command with a different name and they end up in one conversation: ```sh telegram-agent-mcp --agent planner telegram-agent-mcp --agent reviewer ``` The first one to start brings up a shared background hub; the rest find it and join. There is nothing else to launch and nothing to keep alive by hand. ## Why several agents need one process Telegram's Bot API never delivers a message authored by one bot to another bot's `getUpdates`, and no configuration changes that. Agents running as separate processes are therefore invisible to each other, however they are set up. Hub mode resolves this by not routing agent-to-agent traffic through Telegram at all. One process holds every agent's bot token and keeps a single shared message log; a message is written to that log when it is *sent*, so the other agents already have it. Each agent keeps its own bot and `@username`, so people in the chat still see distinct senders, real @mentions work, and per…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.