TGDen Telegram Tools — free scrapers, search and exports
Run Telegram tools locally or in a public GitHub Actions workflow. Export JSON and CSV. No Apify account, Telegram account, bot token or API key is required.
Download one Python file · Run on GitHub · Free tools guide · По-русски · API & MCP
Free tools
Python 3.10+ and the standard library are enough. Results are written to result.json, result.csv and metadata.json in the output directory.
To run from the GitHub website: fork this public repository → enable Actions → Run a free Telegram tool → choose a tool → Run workflow → download the result artifact. A GitHub login is needed for that route; the local commands need none.
These are free public-data tools with explicit limits. Catalog search is keyword-based; buyer search is a masked preview. Full partner-only semantic search, private chat access and a complete channel history are outside this free bundle. See limits and examples.
Public catalog API and hosted MCP
A live index of what exists on Telegram: 1.7M+ channels, 250k+ group chats, 228k+ bots,
4.9M+ indexed posts. No Telegram account. No API key. No install. CORS enabled — it runs
from a browser tab as happily as from a server.
Maintain a Telegram community list
Telegram Link Checker & Community Directory checks public previews beyond HTTP 200 and includes a small, regularly refreshed group directory. Use the Python CLI or reusable GitHub Action to distinguish community, bot, generic-contact and inconclusive previews. No Telegram account or API key is required.
Why another Telegram MCP server?
Every other Telegram MCP server connects to your Telegram account — you hand it an API
hash, a phone number or a bot token, and it reads your dialogs, sends your messages,
manages your groups. Useful, but it can only ever see what you already have access to.
This one is the opposite. It's a public catalog, so it answers the question none of the
others can:
"What Telegram channels and groups exist about X, and which are worth joining?"
Because it never touches an account, there's nothing to leak and nothing to get banned.
Quick start
Claude Code
Listed in the official MCP Registry as
io.github.JustJuice55/telegram-catalog — clients that browse the registry find it under
telegram.
Claude Desktop · Cursor · any MCP client — add to your MCP config:
That's the entire setup: streamable HTTP transport, stateless, no auth handshake.
Check it by hand:
Tools
Resources
Free REST API (no key either)
Telegram has no official public search. Finding a channel, a live discussion group or a bot
by topic means guessing usernames or trusting closed directories. If you don't speak MCP,
the same catalog is plain HTTP.
GET /api/catalog — search
Call it from the browser
Access-Control-Allow-Origin: * is set on both read-only endpoints, so there is no proxy
step: paste this into any page's devtools console (or a CodePen) and it answers.
Rate limit is shared and fair-use (~200 requests / 10s per IP). No key, no signup, no CORS
proxy, no Access-Control-Allow-Credentials — nothing of yours is ever sent.
GET /api/suggest — instant autocomplete
Grouped, ranked suggestions as-you-type. Good for search boxes and agent tool-use.
Runnable examples: shell · Python · JavaScript.
Limits — published, because hidden limits are worse than low ones
Verified search-engine and AI crawlers are excluded from the shared limit.
We treat these as a contract: when they change, we announce it here and in
the docs. No silent throttling. Need guaranteed
throughput or a bulk export for something real? Open an issue, or reach us via
@tgden_bot.
About the data
Parsed continuously from Telegram's public surfaces — fresher than any LLM training set,
which is most of the point of exposing it over MCP.
Census 06.08.2026. The MCP server reports these totals live, so what your agent sees is
current — not whatever was true when this file was written.
Public data only: channels, groups and bots that are already publicly listed or linked.
No private groups, no archives from closed communities, no personal data.
Use cases
- Agent tool-use — give an agent real Telegram discovery in one config line.
- Research — map communities, track niches, study the open Telegram graph.
- Discovery bots — recommend channels and chats by topic.
- Market intel — what's being rented, sold and offered in regional Telegram economies.
- Demand intel — what people ask for in Telegram chats, by topic and country, week over week.
Machine-readable site summary for AI crawlers: https://tgden.com/llms.txt
License
MIT — do what you want, no warranty. Data is public Telegram metadata.
Maintained by tgden.com. Not affiliated with Telegram FZ-LLC.
Indexes public t.me links only.