telegram-mcp
Enables interaction with Telegram Bot API for sending messages, photos, editing messages, answering callbacks, and fetching updates.
README
telegram-mcp
Dedalus MCP server for Telegram Bot API workflows. It exposes bot identity, message sending, photo sending, update polling, callback answers, and message editing.
Tools
get_me- Get bot identity.send_message- Send a text message to a chat.send_photo- Send a photo by URL or file ID.get_updates- Fetch bot updates.answer_callback_query- Respond to an inline keyboard callback query.edit_message_text- Edit a bot message.
Safety Notes
send_message, send_photo, answer_callback_query, and edit_message_text are user-visible. They can contact real Telegram users or groups and may trigger notifications. Confirm chat_id, message_id, callback IDs, and message contents before calling write tools.
Telegram bot tokens grant control of the bot. Do not commit tokens or chat exports.
Important DAuth Limitation
Telegram's official Bot API requires the token in the request URL:
https://api.telegram.org/bot<TOKEN>/<method>
dedalus_mcp 0.7.0 Connection supports secret injection into HTTP headers, not URL path templating. This repository still declares a DAuth connection named telegram-mcp with secret key TELEGRAM_BOT_TOKEN, but the implemented HTTP calls use a server-side TELEGRAM_BOT_TOKEN environment variable until path-secret support is available.
This means the current code is best deployed as a Type 2/3 server with a server or required credential environment value, not as a fully isolated path-templated DAuth server. Revisit this once Dedalus supports path credential templating for Telegram.
Environment
TELEGRAM_BOT_TOKEN=123456:ABC-DEF...
DEDALUS_AS_URL=https://as.dedaluslabs.ai
For _client.py:
DEDALUS_API_KEY=dsk-live-...
DEDALUS_API_URL=https://api.dedaluslabs.ai
DEDALUS_MCP_SERVER=dedalus-labs/telegram-mcp
TELEGRAM_TEST_CHAT_ID=...
TELEGRAM_TEST_MESSAGE_ID=...
TELEGRAM_TEST_CALLBACK_QUERY_ID=...
Run Locally
uv run python src/main.py
In another terminal:
MCP_SERVER_URL=http://127.0.0.1:8080/mcp uv run python src/_client.py
The client calls every tool. It intentionally includes write calls, so use a safe test chat.
Deploy
Publish as dedalus-labs/telegram-mcp, configure TELEGRAM_BOT_TOKEN securely, deploy, then run:
DEDALUS_MCP_SERVER_ONLY=1 DEDALUS_MCP_SERVER=dedalus-labs/telegram-mcp uv run python src/_client.py
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.