mcp-telegram

Provides an MCP server/CLI that connects LLM agents to Telegram via Telethon (MTProto), enabling sending/editing/deleting messages, searching dialogs, managing drafts, and downloading media through MCP tools.

Evaluated Mar 30, 2026 (22d ago)
Homepage ↗ Repo ↗ Communication mcp model-context-protocol telegram telethon mtproto messaging python ai-agents tooling cli
⚙ Agent Friendliness
46
/ 100
Can an agent use this?
🔒 Security
50
/ 100
Is it safe for agents?
⚡ Reliability
32
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
62
Documentation
72
Error Messages
0
Auth Simplicity
55
Rate Limits
20

🔒 Security

TLS Enforcement
70
Auth Strength
50
Scope Granularity
20
Dep. Hygiene
60
Secret Handling
55

Uses Telegram MTProto via Telethon; transport security is expected over HTTPS/TCP, but the README does not explicitly state TLS requirements. Auth is based on Telegram API credentials plus a stored session file; no OAuth/scopes are documented, so access control is coarse. README warns to keep API credentials private and mentions stored session data. Multiple-instance use of the same session file may cause SQLite locking issues (reliability/security-adjacent operational concern). No security hardening (encryption of session file, audit logging, explicit redaction behavior) is documented in the provided text.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
40
Error Recovery
35
AF Security Reliability

Best When

You need local/on-prem style Telegram access for an MCP-enabled agent and can run the CLI/MCP server securely with a dedicated session.

Avoid When

You need OAuth-style app authorization, fine-grained per-tenant permissions, or a documented, standardized error contract for programmatic retries.

Use Cases

  • Letting an AI assistant send messages to Telegram users/chats
  • AI-assisted moderation workflows (e.g., delete/edit messages) with human review
  • Retrieving and summarizing Telegram message history via search/history tools
  • Media retrieval workflows (download photos/videos/documents) for downstream analysis

Not For

  • Automated bulk spam or abusive messaging
  • Use without understanding Telegram Terms of Service and user/device consent
  • Use where strong enterprise compliance/audit controls are required without additional hardening

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Interactive login using Telegram API ID/hash + phone number + verification code (+ optional 2FA) Session-file based authentication
OAuth: No Scopes: No

Authentication is session-based (Telethon SQLite session). No OAuth or explicit scopes are documented; access is effectively governed by possession of the session/credential storage configured via env/session files.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; it appears to be an open-source CLI package.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Use of multiple concurrent mcp-telegram instances with the same session file can trigger Telethon SQLite 'database is locked' errors.
  • Authentication is interactive (login prompts) and relies on a locally stored session; agents will need pre-authenticated setup or scripted environment provisioning.
  • The README does not document tool parameter schemas or structured error codes, so robust agent-side handling may require inspection of runtime behavior.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-telegram.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered