M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
A

AgEnD

Community
Run a fleet of AI coding agents from your phone.
How to install ↓ Compare GitHub source repository ↗
Category
Other
Stars
★ 65 Popular
Runtime
Node.js >= 20 · Prebuilt binary
Credentials
API key / credential required
Last commit
30FMRS · D

AgEnD offers a powerful multi-agent management solution, but be aware of its maintenance mode and security risks. Suitable for experienced users to significantly boost remote development efficiency.

Reliability
6/20
Security and permissions
6/20
Maintenance
6/20
Documentation
6/20
Setup experience
6/20
Why each score
Reliability 6/20
No source files in the repository root were provided for static analysis; no CI or test evidence. README states maintenance mode. Reliability score conservative due to lack of verifiable execution evidence.
Security and permissions 6/20
Project involves running remote agents and cross-instance collaboration, but security model is not detailed. No security policy file was provided (SECURITY.md only referenced in README). Score reflects potential risks and lack of documentation.
Maintenance 6/20
No license, commit history, or releases were provided in the evidence. README indicates maintenance mode with development moved elsewhere, but open issues suggest some maintenance. Score conservative.
Documentation 6/20
README extensively links to docs (features, CLI, configuration) but actual content not reviewed. No evidence of installation, auth, tool parameters, or troubleshooting details. Deductions for unverified claims.
Setup experience 6/20
README provides one-line install and manual steps, but requires multiple dependencies (Node.js, tmux, CLIs) and lacks Windows support. No client configuration examples, such as for Claude Desktop. Score below 15 due to lack of verifiable evidence.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesWrites / deletes local filesRuns commands or codeUses the networkConnects to a database

Best for

  • Developers and teams who want to monitor and command AI coding agents from anywhere.
  • Users who need to run multiple long-running tasks with automatic crash recovery.
  • Users who prefer Telegram or Discord as their control interface.

Not for

  • Users looking for an officially maintained MCP server (AgEnD is not an official product).
  • Users who need native Windows support (only macOS and Linux are supported).
  • Users who want new features without breaking changes (new features are in pre-alpha agend-terminal).

Required permissions

  • All CLI backends run with --dangerously-skip-permissions (or equivalent), meaning agents can execute arbitrary code.
  • Access to the file system, network, and command execution is required.
  • Optional: Groq API key for voice message transcription.

Risks and side effects

  • Agents run with full permissions, posing security risks from mistakes or malicious instructions.
  • Cost risk: Without daily spending limits, agents might incur unexpected charges.
  • The project is in maintenance mode, so new features are not developed and vulnerabilities may remain unfixed.

Setup

Before you start

Runtime：Node.js >= 20 · Prebuilt binary

ANTHROPIC_API_KEY optionalsecret Alternative auth for the Claude Code backend (or use claude OAuth login); obtained from Anthropic.
OPENAI_API_KEY optionalsecret Alternative auth for the OpenAI Codex backend (or use codex ChatGPT login); obtained from OpenAI.

One-liner (macOS/Linux):

curl -fsSL https://suzuke.github.io/AgEnD/install.sh | bash

Or install manually:

npm install -g @suzuke/agend
agend quickstart
agend fleet start

Requires Node.js >= 20, tmux, at least one supported AI coding CLI, and a Telegram or Discord bot token.

Check that it works

After completing agend quickstart, run agend fleet start, then message your bot in Telegram. Receiving an agent reply with permission-approval inline buttons confirms the deployment works.

Troubleshooting

  1. Ensure Node.js >= 20 and tmux are installed.
  2. Check that the Telegram bot token is correct and the bot is added to the desired chat.
  3. If using WSL, set appendWindowsPath=false in /etc/wsl.conf and restart WSL.
  4. Check logs with `agend logs` or inspect system service status.

Things to try

Once connected, you can ask your AI assistant things like:

  • Send a message to the General Topic in Telegram and have the dispatcher route the task to the right agent instance
  • Have two agent instances collaborate via MCP tools: one delegates a task, the other executes and reports back
  • Set a daily spending limit on an instance so it auto-pauses when exceeded
  • Issue a command via voice message, transcribed by Groq Whisper, and have the agent act on it

Use cases

Remotely manage multiple AI coding projects from your phone.
Isolate sessions via Telegram forum topics for parallel development.
Enable multiple agents to collaborate on complex tasks via MCP tools.

Overview

AgEnD (Agent Engineering Daemon) turns your Telegram or Discord into a command center for AI coding agents. One bot, multiple CLI backends, unlimited projects — each running as an independent session with crash recovery and zero babysitting. It supports backends like Claude Code, Gemini CLI, Codex, OpenCode, and Kiro CLI, and allows agents to collaborate peer-to-peer via MCP tools. Note: the project is in maintenance mode; active development has moved to the Rust rewrite agend-terminal.

Similar servers

Telegram MCP Server 70 · B

Telegram MCP server powered by Telethon to let MCP clients read chats, manage groups, and send/modify messages, media, contacts, and settings.

★ 1.8k · Tools 76 Compare with this →
Compare with other MCP servers

Source revision 2e38b5f1fc6e Data synced 2026-10-11 Read the FMRS scoring method