tggroupMCP
Enables interaction with Telegram groups via MTProto, including message retrieval, sending, and semantic search with RAG support.
README
tggroupMCP
TypeScript MCP stdio server for a Telegram group through MTProto/GramJS.
The default chat is Парилка228 (-1003179772905), but all chat IDs live in env config so the server can be reused for other groups.
Setup
cd /root/telegram-parilka-mcp
npm install
cp .env.example .env
npm run generate-session
npm run build
Put the generated TELEGRAM_SESSION into .env.
Run
npm run print-config
npm run start
Cache warmer
Run this as a long-lived process to keep SQLite warm. It fetches recent messages first, then an older backfill chunk, using cursors stored in SQLite:
npm run sync-daemon
One-shot mode, useful for cron/systemd timers:
npm run sync-once
Vector RAG
Set OPENAI_API_KEY or TELEGRAM_EMBEDDINGS_API_KEY, then index cached messages into local SQLite vector chunks:
npm run embed-once -- --limit-chunks 1000
The regular sync daemon also indexes new chunks when embeddings are configured. search_messages returns keyword, vector, and hybrid candidates; semantic_search_messages returns only cosine-ranked chunks.
MCP config example:
[mcp_servers.telegram-parilka]
command = "/root/telegram-parilka-mcp/bin/telegram-parilka-mcp"
Sending is live by default. Set TELEGRAM_SEND_ENABLED=false or pass dry_run: true to preview without posting.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.