TG CLI
TG Telegram Parser refreshes a saved channel export, adding new posts and revisiting a configured number of earlier discussions.
- 241 ★ on the repository
- Last commit
Extended access
Why this level
- The CLI reads Telegram history available to the account and stores messages, user information and media; optional analysis sends data to a model.
Install
- Services
Manual install
docker compose up --buildFirst launch from the local repository. Docker creates an env template; the owner supplies actual access separately.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The CLI reads Telegram history available to the account and stores messages, user information and media; optional analysis sends data to a model.
This is third-party code. Review the repository files before installing.
What it does
TG Telegram Parser is a CLI/MCP tool that exports Telegram channel posts, discussion comments and reactions to JSON, CSV, Parquet or PostgreSQL, with optional media downloads. A local dashboard displays posts, comment trees and dataset metrics. Incremental runs add new posts and revisit selected older ones. Separate commands compare periods or analyze exports using a configured language model. CLI and MCP support automation beyond the dashboard.
Who it is for. Telegram channel editors analyzing discussions and comparing audience response through saved exports.
Good fit when
- An editor collects posts and comments from owned channels for analysis.
- After the initial export, an operator adds posts and refreshes recent discussions.
- A report compares comments, participants and reactions across two periods.
- Saved JSON is opened locally without reconnecting to Telegram.
Not a fit when
- The account lacks access to the channel or discussions.
- An export containing user names would be published without review.
- Incremental mode must continuously refresh the entire history regardless of lookback limits.
Example request
Export my channel’s posts and comments for the agreed period, anonymize user fields and keep the data local without LLM analysis.Limitations
Export needs API_ID, API_HASH and a Telegram account session; keep the session file separate from public material. Incremental export revisits new posts and a configured number of older ones, leaving comments beyond that window unchanged. Anonymization replaces selected user fields, but message text still needs review before sharing. External LLM analysis sends export content to the configured provider and requires separate setup.
How to disable. Stop Docker services, scheduling and watch mode. Review session files, exports and media before deleting or sharing them.
FAQ
How do I open the dashboard?
After `docker compose up --build`, open `http://localhost:9595` and configure Telegram in Export.
Can I try it without Telegram?
Yes. Use the repository’s demo JSON in the local dashboard first.
How do I validate configuration?
Run `docker compose run --rm cli config-check` before exporting.
What does incremental refresh?
New posts and the number of older posts set by `INCREMENTAL_LOOKBACK_POSTS` are revisited. Their comments, reactions and counters refresh; discussions outside that window can remain unchanged.
Is an LLM required?
No. Export and local viewing are separate from analysis; enable a model only for an agreed task.
Discussion
No questions or reviews yet.
Related
All Telegram toolsTGStat MCP
tgstat-mcp
TGStat MCP server: Telegram channel and post search, subscriber and reach trends, ERR and mentions
Telegram API MCP
telegram-api-mcp
MCP server for the Telegram Bot API: messages, channels, forums, payments and long posts from a bot, with Telegram rate limits built in
Telegram MCP by chaindead
Telegram MCP
A Go MCP server for your Telegram account: the agent reads dialogs and unread messages, marks them read, leaves replies as drafts
MCP Telegram with write access: the agent sends, edits and deletes messages, searches chats, keeps drafts and downloads media in your account over MTProto
A Telethon MCP server: the agent reads and sends messages and manages chats, contacts and folders in your Telegram account
VK to Telegram bridge MCP
vk-tg-bridge
A 4-tool MCP server that pulls VK wall posts, filters them by rules and publishes them to Telegram via the Bot API
README in short
Watch mode keeps the Telegram session open and refreshes active discussions. It runs separately from the scheduler used for timed exports.