TelegramSAFE
MCP Server for Telegram
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Enable LLMs to control your Telegram
Connect Large Language Models to Telegram via the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction).
Built with Telethon, this server allows AI agents to interact with Telegram, enabling features like sending/editing/deleting messages, searching chats, managing drafts, downloading media, and more using the MTProto.
Table of Contents
- 🚀 Getting Started
- Prerequisites
- Installation
- ⚙️ Usage
- Login
- Connect to the MCP server
- 🧰 Available Tools
- 📨 Messaging Tools
- 🔍 Search & Navigation
- 📝 Draft Management
- 📂 Media Handling
- 🛠️ Troubleshooting
- 🤝 Contributing
- 📝 License
🚀 Getting Started
Prerequisites
- Python 3.10 or higher
- `uv` Install via the official uv guide.
Installation
Install the mcp-telegram CLI tool:
uv tool install mcp-telegram
⚙️ Usage
[!IMPOR
a7b2c632bf57OBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-telegram -- uvx mcp-telegram
{
"mcpServers": {
"mcp-telegram": {
"command": "uvx",
"args": [
"mcp-telegram"
]
}
}
}Exposed tools (9)
5 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
delete_message | destructive | Delete messages from a specific entity. |
edit_message | write | Edit a message from a specific entity. |
get_draft | read | Get the draft message for a specific entity. |
get_messages | read | Get messages from a specific entity. |
media_download | read | Download media from a specific message to a unique local file. |
message_from_link | read | Get a message from a link. |
search_dialogs | read | Search for users, groups, and channels. |
send_message | write | Send a message to a Telegram user, group, or channel. |
set_draft | write | Set a draft message for a specific entity. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
delete_message
.pre-commit-config.yaml
curl -LsSf https://astral.sh/uv/install.sh | sh
logo.png
Gates applied: no_behavioural_pass.
a7b2c632bf57full audit observations/trust-audit/mcp-server/dryeab__telegram-6.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | a7b2c632bf57 | SAFE | B | 89 | first audit |
Questions
What is the Telegram MCP server?
MCP Server for Telegram
What tools does Telegram expose?
9 in total: 5 read-only, 3 that write, and 1 that can delete or overwrite (delete_message). Every one is listed on this page with its risk.
Is Telegram safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Telegram need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (a7b2c632bf57), read on 2026-10-06. The repository is watched and re-audited when it changes.