What is telegram-user-mcp CLAUDE.md?

Instructions for a read-only MCP server that connects to Telegram as a real user account. Telegram is a messaging platform; the server can read and search messages, list chats, inspect groups, find pinned messages, and download media, including from private chats the account can access.

Use it to search messages, review chats and folders, inspect group details, retrieve pinned content, and download media.

It lets an agent work with the user's Telegram data while limiting the documented tools to reading and downloading information.

How 22syn/telegram-user-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 22syn/telegram-user-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/22syn/telegram-user-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/22syn/telegram-user-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/22syn/telegram-user-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/22syn/telegram-user-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/22syn/telegram-user-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/22syn/telegram-user-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/22syn/telegram-user-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/22syn/telegram-user-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 648 This file is loaded in full into every session.

When invoked 648 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00648	$0.00648
Opus 5.5	$0.00259	$0.00259
Sonnet 5.5	$0.00130	$0.00130
Haiku 4.5	$0.00065	$0.00065

Measured 2mo ago against content hash d505aeaefa39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

telegram-user-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 33 lines

What it actually says

CLAUDE.md — telegram-mcp

📋 Active plan (2026-07-23): docs/plans/2026-07-23-graph-audit-followup.md — graph-audit follow-up; review before structural changes. 📋 Improvement plan (2026-07-23): docs/plans/2026-07-23-improvement-plan.md — the PRD's own prompt-injection safeguard was never implemented, add before any write capability.

Purpose An MCP (Model Context Protocol) server that connects to Telegram as a real user account (MTProto via GramJS), exposing read-only tools to MCP clients (Claude Desktop, Cursor, etc.): read & search messages, list chats/folders, inspect group info, get pinned messages, and download media. Because it authenticates as the user, it can see everything the account can — private channels, groups, and DMs a bot cannot.

Stack

Node.js ≥18, CommonJS (plain JS, no build step)
@modelcontextprotocol/sdk — MCP server framework
telegram (GramJS) — MTProto client
input — interactive CLI prompts during setup

Structure

server.js — the MCP server; implements all tools (main entry, main field)
setup.js — one-time interactive login (api_id, api_hash, phone, 2FA)
cli.js — bin entry (telegram-user-mcp), dispatches setup vs. server
docs/ — additional documentation
LICENSE (MIT), README.md

Run / dev

npm run setup (or npx telegram-user-mcp setup) — one-time login
npm start — run the MCP server (node server.js)
Register in an MCP client via command: npx, args: ["-y", "telegram-user-mcp"]

Conventions / notes

All tools are read-only (reading, search, discovery, media info/download). No sending/posting.
groupUrl args accept a https://t.me/... link, @username, or numeric id (from list_dialogs).
Config in ~/.telegram-mcp-config.json (apiId, apiHash, phoneNumber, optional downloadDir, maxDownloadMB). Login session in ~/.telegram-mcp-session — grants full account access; treat as a password, never commit/share. Media downloads land in ~/.telegram-mcp-downloads/.
download_media refuses files over maxDownloadMB (default 200) unless maxMB overrides; use get_thumbnail to preview heavy videos cheaply.
Get api_id / api_hash from https://my.telegram.org → API development tools.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 33 lines · 648 tokens per session scan A d505aeaefa39

Subscribe to this mod's changes

telegram-user-mcp CLAUDE.md is an instructions file published in the GitHub repository 22syn/telegram-user-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 648 tokens to every session, about $0.0026 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

telegram-user-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
telegram-user-mcp CLAUDE.md22syn/telegram-user-mcp	Instructions file	0	10d ago	MIT	A	648	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

telegram-user-mcp: Instructions file for Claude Code