Connect
Optimize
Secure
Telegram MCP Server
for AI Agents
Production-ready Telegram MCP server with 38 extensible actions — plus built-in authentication, security, and optimized execution.
Telegram MCP Server
Built by 
StackOne
StackOne 
Coverage
38 Agent Actions
Create, read, update, and delete across Telegram — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Telegram MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Telegram tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Telegram call.
Tools Discovery →What is the Telegram MCP Server?
A Telegram MCP server lets AI agents read and write Telegram data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Telegram MCP server ships with 38 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Telegram MCP Tools and Actions
Every action from Telegram's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Webhooks
- Set Webhook
Set a webhook URL to receive updates
- Delete Webhook
Remove the webhook and switch to polling
Chat Invite Links
- Create Chat Invite Link
Create an additional invite link for a group or channel
- Export Chat Invite Link
Get or regenerate the primary invite link for a group or channel
Messages
- Send Message
Send a text message to a chat
- Copy Message
Copy a message to another chat without a forwarding link
- Copy Messages
Copy multiple messages to another chat without the original source attribution
- Delete Message
Delete a message from a chat
- Delete Messages
Delete multiple messages in a chat
Forward Messages
- Forward Message
Forward a message to another chat
- Forward Messages
Forward multiple messages to another chat
Other (27)
- Send Photo
Send a photo to a chat
- Send Document
Send a document or file to a chat
- Send Audio
Send an audio file to a chat
- Send Video
Send a video file to a chat
- Send Animation
Send an animation (GIF or H.264/MPEG-4 AVC video without sound) to a chat
- Send Voice
Send a voice message to a chat
- Send Location
Send a geographic location to a chat
- Send Contact
Send a phone contact to a chat
- Send Poll
Send a native poll to a chat
- Send Dice
Send an animated emoji that displays a random value
- Send Chat Action
Send a chat action indicator to show the bot is processing
- Get Bot Info
Get information about the bot
- Get Updates
Get incoming updates for the bot
- Get Webhook Info
Get current webhook status
- Get Chat
Get information about a chat
- Get Chat Administrators
Get a list of administrators in a group or channel
- Get Chat Member Count
Get the number of members in a chat
- Get Chat Member
Get information about a member of a chat
- Get File
Get basic information about a file and prepare it for downloading
- Get User Profile Photos
Get a list of profile pictures for a user
- Answer Callback Query
Send a response to a callback query from an inline keyboard button
- Ban Chat Member
Ban a user from a chat
- Unban Chat Member
Unban a previously banned user from a chat
- Leave Chat
Make the bot leave a group, supergroup, or channel
- Edit Message Text
Edit the text of a previously sent message
- Pin Message
Pin a message in a chat
- Unpin Message
Unpin a specific message in a chat
Set Up Your Telegram MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Telegram in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Telegram MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Telegram MCP Server FAQ
Telegram MCP server vs direct API integration — what's the difference?
A Telegram MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Telegram. A Telegram MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Telegram at runtime. StackOne provides both.
How does Telegram authentication work for AI agents?
Telegram authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Telegram account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Telegram MCP tools vulnerable to prompt injection?
Yes — Telegram MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Telegram agent and how do I avoid it?
Context bloat happens when Telegram tool schemas and API responses eat your Telegram agent's memory, preventing it from reasoning effectively. A single Telegram query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Telegram agent can access?
Yes — you can limit which actions your Telegram agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Telegram MCP server?
Yes — you can create custom agent actions for your Telegram MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Telegram's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Telegram MCP server?
Skip a Telegram MCP server if your integration is purely software-to-software — direct Telegram API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Telegram actions at runtime.
What AI frameworks and AI clients does the StackOne Telegram MCP server support?
The StackOne Telegram MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.