Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/nskondratev/telegram-mcpWrote 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.
[](https://agentmods.dev/mcp/nskondratev/telegram-mcp/telegram-allowlist-mcp)<a href="https://agentmods.dev/mcp/nskondratev/telegram-mcp/telegram-allowlist-mcp"><img src="https://agentmods.dev/badge/mcp/nskondratev/telegram-mcp/telegram-allowlist-mcp/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.
<a href="https://agentmods.dev/mcp/nskondratev/telegram-mcp/telegram-allowlist-mcp"><img src="https://agentmods.dev/badge/mcp/nskondratev/telegram-mcp/telegram-allowlist-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
telegram-allowlist-mcp 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 9d 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.
What it actually says
{ "telegram-allowlist-mcp": { "command": "uvx", "args": [ "telegram-allowlist-mcp" ] } }
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.
- 9d ago First seen · 8 lines scan A 7b47de30e7d2
telegram-allowlist-mcp is an MCP server published in the GitHub repository nskondratev/telegram-mcp (0 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.
Other mcp servers, from other repositories
telegram-mcp
MCP server "telegram-mcp" as configured in VovaVindar/telegram-mcp. Launched with .venv/bin/fastmcp run telegram_mcp_server.py.
tdl-mcp
MCP server "tdl-mcp" as configured in rixile9999/tdl-mcp. Runs locally from the tdl-mcp npm package. Needs 2 environment variables to run.
whatsapp-mcp-local
MCP server: visão e escrita no WhatsApp (macOS app nativo + web cross-platform via Chrome). Lê o histórico local com segurança e envia com gate de confirmação. Runs locally from the whatsapp-mcp-local npm package.
tgread
MCP server "tgread" as configured in demian-overflow/tgread. Runs locally from the tgread Python package.
hoton-mcp
MCP server that lets AI agents buy Telegram Stars, Premium and TON top-ups on hoton.tg. Runs locally from the hoton-mcp npm package.
mssql-mcp
Security-first, read-only MCP (Model Context Protocol) server for Microsoft SQL Server. Verifies the database user is read-only at startup and applies query-level defense in depth. Runs locally from the @esasiyun17/mssql-mcp npm package.