Enables interaction with Telegram bots via the MTProto protocol, providing tools to send messages, wait for bot replies, and retrieve message history.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@telegram-mcp ask @BotFather to list my bots"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A minimal MCP server for Telegram bot interaction via MTProto — intentionally simple, easy to read, and easy to extend.
Looking for a full-featured Telegram MCP server? Check out chigwell/telegram-mcp — 60+ tools covering messaging, groups, contacts, media, admin, and more.
This project takes a different approach: two tools, ~150 lines of server code, zero complexity. It's a clean starting point for anyone who wants to understand how MCP servers work with Telegram, or who only needs basic bot messaging without the overhead of a full client.
Learning reference — Read the entire server in 5 minutes
Fork-friendly — Add exactly the tools you need, nothing you don't
Minimal dependencies — Just Telethon, MCP SDK, and python-dotenv
Related MCP server: telegram-mcp
Tool | Description |
| Send a message to a Telegram bot and wait for its reply |
| Get message history with a Telegram bot |
Log in with your phone number
Create a new application (any name/description)
Copy the API ID and API Hash
# Install
pip install git+https://github.com/tensakulabs/telegram-mcp.git
# Set your credentials
export TELEGRAM_API_ID=12345678
export TELEGRAM_API_HASH=abcdef1234567890abcdef1234567890
export TELEGRAM_PHONE=+15551234567
# Run one-time authentication (sends a code to your Telegram app)
telegram-mcp-authAdd to ~/.claude/settings.json:
{
"mcpServers": {
"telegram": {
"command": "uvx",
"args": ["--from", "git+https://github.com/tensakulabs/telegram-mcp.git", "telegram-mcp"],
"env": {
"TELEGRAM_API_ID": "your-api-id",
"TELEGRAM_API_HASH": "your-api-hash",
"TELEGRAM_SESSION_DIR": "/path/to/session/dir"
}
}
}
}Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"telegram": {
"command": "uvx",
"args": ["--from", "git+https://github.com/tensakulabs/telegram-mcp.git", "telegram-mcp"],
"env": {
"TELEGRAM_API_ID": "your-api-id",
"TELEGRAM_API_HASH": "your-api-hash",
"TELEGRAM_SESSION_DIR": "/path/to/session/dir"
}
}
}
}If you've cloned the repo:
{
"mcpServers": {
"telegram": {
"command": "uv",
"args": ["--directory", "/path/to/telegram-mcp", "run", "telegram-mcp"],
"env": {
"TELEGRAM_API_ID": "your-api-id",
"TELEGRAM_API_HASH": "your-api-hash"
}
}
}
}Environment variable | Required | Default | Description |
| Yes | — | Your Telegram API ID |
| Yes | — | Your Telegram API hash |
| Auth only | — | Phone number for authentication |
| No | Auto-detect | Path to .env file |
| No | Working directory | Directory for session file |
This server uses the Model Context Protocol to expose Telegram interaction as tools that any MCP-compatible AI client can use. Under the hood, it:
Connects to Telegram via MTProto using your pre-authenticated session
Sends messages to bots as your user account
Polls for replies and returns structured JSON responses
Disconnects cleanly after each operation
Your session file (telegram_user.session) contains auth tokens — never commit it
The .gitignore excludes session files by default
API credentials should be passed via environment variables, not hardcoded
This tool acts as YOUR Telegram account — treat it accordingly
git clone https://github.com/tensakulabs/telegram-mcp.git
cd telegram-mcp
uv sync
uv run telegram-mcpPython 3.10+
uv (recommended) or pip
MIT
Get message history with a Telegram bot.
Args:
bot: Bot username (e.g. '@BotFather' or 'BotFather')
limit: Number of messages to retrieve (default 20)
| Name | Required | Description | Default |
|---|---|---|---|
| bot | Yes | ||
| limit | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. The description only states 'Get message history' but does not mention read-only nature, authentication requirements, rate limits, or behavior with large limits. Given the lack of annotations, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—four short lines—and well-structured with clear 'Args:' listing. Every sentence adds value with no wasted words. It is appropriately sized for a simple tool with two parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (2 parameters), the presence of an output schema (so return values need not be explained), and the minimal sibling context, the description is fairly complete. It could optionally mention that it retrieves messages from a bot conversation, but the current description is sufficient for basic use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning beyond the input schema by providing examples for the 'bot' parameter ('e.g. '@BotFather' or 'BotFather'') and clarifying the default for 'limit' (20). With 0% schema description coverage, the description compensates well, though it could elaborate on the format or constraints of 'limit'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb and resource: 'Get message history with a Telegram bot.' This distinguishes it from the sibling tool 'send_message', which sends messages. The purpose is specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly indicates when to use this tool (retrieve history) versus the sibling 'send_message' (send messages). However, it does not explicitly state when not to use it or provide alternatives beyond the sibling context. This is adequate for a simple list retrieval tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send a message to a Telegram bot and wait for its reply.
Args:
bot: Bot username (e.g. '@BotFather' or 'BotFather')
message: The message text to send
timeout: Seconds to wait for a reply (default 30)
| Name | Required | Description | Default |
|---|---|---|---|
| bot | Yes | ||
| message | Yes | ||
| timeout | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It mentions waiting for a reply and the timeout parameter, but lacks details on error handling, authentication needs, or destructive behavior. Transparency is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, front-loaded with the purpose, and uses a structured docstring format (Args section). Every sentence adds value, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 3 parameters, no schema descriptions, and an existing output schema (not shown), the description covers the main inputs adequately. It does not describe the return value, but that is mitigated by the output schema. Missing details on prerequisites or edge cases are minor gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, so the description adds critical meaning: bot as Bot username, message as text, timeout as seconds. This compensates well, though bot format (with/without @) could be clearer.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Send a message to a Telegram bot and wait for its reply,' specifying the verb (send), resource (message to a Telegram bot), and behavior (wait for reply). It is distinct from the sibling tool get_history.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage (send and wait for reply) but does not provide explicit guidance on when to use this tool versus alternatives, nor does it state exclusions or prerequisites. The context of a single sibling reduces the need, but no explicit guidelines are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have clearly distinct purposes: one retrieves message history, the other sends a message and waits for a reply. No overlap or ambiguity.
Both tools follow a consistent verb_noun pattern in snake_case (get_history, send_message), making them predictable and easy to understand.
With only 2 tools for a Telegram bot server, the surface is too thin. Typical Telegram interactions require more operations (e.g., listing bots, deleting messages), making this feel incomplete.
Obvious gaps exist: no tool to list available bots, delete messages, get updates, or handle multiple bots. The set covers only basic send and retrieve operations.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol (MCP) server for Selise Blocks Cloud integration
Telegram bridge for your MCP-compatible agent. Bidirectional, no LLM in our stack.
Multi-tenant Telegram gateway for AI agents — HTTP+stdio, 8 tools, MTProto User API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tensakulabs/telegram-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
