This server provides a single, focused capability: sending direct Telegram messages via your personal Telegram account using the send_telegram_message tool.
Specify the recipient's Telegram username (without @) and the message content to send them a direct message.
Designed as a "pager" for notifications or alerts (e.g., notifying yourself when a build finishes).
What you cannot do:
Read chat history
Delete messages
View contacts
Perform any other Telegram account actions
Allows sending direct messages via a personal Telegram account.
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 Pager MCP Server Send a message to 'john_doe' saying 'Task completed successfully'"
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 specialized Model Context Protocol (MCP) server that allows AI coding assistants (like Cursor, Cline, or Claude Desktop) to send direct messages via your personal Telegram account.
Security First: This server exposes exactly one tool (send_telegram_message). It is intentionally designed as a "Telegram Pager", meaning the AI cannot read your chat history, delete messages, or view your contacts.
Do NOT use this tool for spam. If you configure an AI agent to send unsolicited messages, bulk broadcasts, or promotional content using this server, Telegram's automated systems will quickly flag your activity. Your personal Telegram account will be permanently banned and your phone number blocked. Use this exclusively for personal notifications or messaging your own contacts responsibly.
To use this, you need a Telegram API ID and Hash.
Log in to my.telegram.org/apps.
Create an application (if you haven't already).
Copy your App api_id and App api_hash.
Related MCP server: Telegram MCP Server
Install the package:
pipx install mcp-server-telegram-pagerGenerate your Session String: Because Telegram requires 2FA (a login code sent to your app), you must generate an authentication session string locally first.
mcp-server-telegram-pager-authFollow the prompts to enter your API ID, Hash, and Login Code. Copy the long session string it outputs!
Add the following to your IDE's MCP configuration file (e.g., in Cursor or Claude Desktop):
{
"mcpServers": {
"telegram-pager": {
"command": "mcp-server-telegram-pager",
"env": {
"TELEGRAM_API_ID": "YOUR_API_ID_HERE",
"TELEGRAM_API_HASH": "YOUR_API_HASH_HERE",
"TELEGRAM_SESSION": "YOUR_LONG_SESSION_STRING_HERE"
}
}
}
}Once configured, you can ask your AI assistant:
"Send a Telegram message to username 'coolperson123' saying 'The build finished successfully!'"
(Note: Do not include the @ symbol in the username).
Send a direct message to a Telegram user. Do not use the @ symbol in the username (e.g. use 'jakethesnake', not '@jakethesnake').
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | ||
| username | Yes |
| 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. It only states the basic action without any details about side effects, rate limits, error handling, or return values. The agent gains little insight into what happens beyond the call.
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 two sentences long, with the first sentence stating the purpose and the second adding a critical usage note. No unnecessary words, and the most important information is front-loaded.
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?
The tool is simple with only two parameters, and there are no siblings to compare against. However, the description omits any mention of return values or behavior (even though an output schema exists but is not shown). It is adequate for a basic action but lacks completeness for an agent to predict outcomes.
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, meaning no parameter descriptions exist. The tool description adds value for the 'username' parameter by specifying the format (no '@'), but does not explain 'message' or provide any other semantic details. This is minimal compensation for the schema gap.
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 action ('Send a direct message') and the target ('a Telegram user'). The verb and resource are specific, and there are no sibling tools to differentiate, so it's adequately clear for the given context.
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 provides a practical guideline about not using the '@' symbol in the username, which helps avoid common errors. However, it does not offer guidance on when to use this tool versus other potential alternatives (none listed) or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0send_telegram_messageScored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools.
The single tool uses a clear verb_noun pattern (send_telegram_message), which is consistent and predictable.
One tool is borderline for the 'Telegram Pager' purpose; while it could be sufficient for a narrowly scoped paging server, it feels thin compared to typical server sizes.
The server only supports sending messages, lacking any other operations like checking delivery status or managing contacts, which are significant gaps for a Telegram integration.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
An MCP server that integrates with Discord to provide AI-powered features.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
