Agent Messenger

What is Agent Messenger?

Give your AI agent the power to read and send messages across Slack, Discord, Teams and more

Agent Messenger is a unified, agent-friendly CLI for messaging platforms. It automatically extracts credentials from your desktop apps—no OAuth flows, no API keys, no admin approval needed.

Why Agent Messenger?

For AI Agents

AI agents need to communicate with humans through messaging platforms. But integrating with Slack, Discord, or Teams traditionally requires:

  • OAuth setup - Creating apps, getting admin approval, managing tokens
  • API keys - Storing secrets, handling rotation, security concerns
  • Platform-specific code - Learning different APIs for each platform

Agent Messenger eliminates all of this. Your agent can start sending messages in seconds.

For Developers

Building AI-powered workflows that interact with messaging platforms shouldn't require a week of OAuth debugging. Agent Messenger provides:

  • Zero configuration - Extract tokens from your existing desktop apps
  • Unified interface - Same commands work across all platforms
  • JSON output - Perfect for piping into other tools or LLMs

How It Works

Agent Messenger reads authentication tokens directly from your installed desktop apps (Slack, Discord, Teams). These apps store session tokens locally, and Agent Messenger safely extracts them.

# Extract credentials from Slack desktop app
agent-slack auth extract

# That's it! Now you can send messages
agent-slack message send general "Hello from my AI agent!"

No app creation. No admin approval. No waiting.

Key Features

FeatureDescription
Auto-extractionPulls tokens from desktop apps automatically
Multi-platformSlack, Discord, and Microsoft Teams
Multi-workspaceSwitch between workspaces/servers easily
JSON outputMachine-readable by default, --pretty for humans
ComprehensiveMessages, channels, users, reactions, files

Why Not MCP?

The Model Context Protocol (MCP) is a popular way to give AI agents access to external tools. But it has a fundamental problem: context bloat.

MCP servers expose all their tools at once. When you connect an MCP server with 50 tools, your AI agent's context window fills up with 50 tool descriptions—even if it only needs one.

Agent Skills + CLI is better:

MCP ApproachAgent Skills Approach
All tools loaded at onceLoad only what you need
Bloated context windowMinimal token usage
Agent confused by optionsFocused, relevant tools
Static tool definitionsDynamic skill loading

With Agent Messenger, your AI agent loads the skill it needs, uses the CLI, and moves on. No wasted tokens.

Why Not OAuth?

Traditional Slack/Discord/Teams integrations require OAuth:

  1. Create an app in the platform's developer portal
  2. Configure OAuth scopes and redirect URLs
  3. Submit for workspace admin approval
  4. Wait days (or weeks) for approval
  5. Handle token refresh, storage, and rotation

Agent Messenger skips all of this.

Your desktop apps already have valid session tokens. Agent Messenger extracts them directly, so you can start sending messages immediately.

When OAuth Makes Sense

OAuth is better when you need:

  • Server-side bots - Running 24/7 without your desktop app
  • Multi-user applications - Many users authenticating separately
  • Granular permissions - Fine-tuned access control

Bot support is on our roadmap for these use cases.

Design Principles

Zero Configuration

The best setup is no setup. Agent Messenger should work the moment you install it.

AI-First, Human-Friendly

Default output is JSON for machines. Add --pretty for humans. Both are first-class citizens.

Unified Interface

Learn once, use everywhere. The same commands work across Slack, Discord, and Teams.

Fail Fast, Fail Clear

When something goes wrong, tell the user exactly what and how to fix it. No cryptic error codes.

Respect Privacy

Tokens stay on your machine. Nothing is sent to external servers. Your credentials are yours.

Next Steps

  • Quick Start - Get running in 30 seconds
  • Slack - Full Slack command reference
  • Discord - Full Discord command reference
  • Teams - Full Teams command reference

Inspiration

Agent Messenger is inspired by agent-browser from Vercel Labs, which takes a similar approach to browser automation for AI agents.

On this page