pulsemcp verified Safe content atomic mcp-remote

This MCP server provides Telegram channel and group scraping capabilities through both web scraping and official API integration, enabling AI assistants to extract posts, channel information, and perform searches from public Telegram content. Built by DLHellMe using TypeScript with Puppeteer for browser automation and the official Telegram client library, it offers 15 specialized tools including authenticated and unauthenticated scraping modes, full channel history extraction with automatic file saving, date range filtering, manual browser-guided scraping, and fast API-based operations for users with Telegram API credentials. The implementation features robust authentication management with cookie persistence, comprehensive content parsing that handles restricted posts and media detection, automatic markdown formatting with reaction data, and flexible deployment options supporting both headless and interactive browser modes, making it valuable for content analysis workflows, social media monitoring, research applications, and building AI assistants that need programmatic access to Telegram's vast public content ecosystem.

Cognium trust score

71%

Tier

Verified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.

Scan details: Circle-IR · 2026-09-28 · Appeal

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: devops-ci
Source: PulseMCP
Repository: github.com/dlhellme/telegram-mcp-server
Author type: human
Last scanned: 2026-09-28
Updated: 2026-09-28

View source Find related skills

MCP

Resolve Telegram from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"