What are the requirements for Caboose MCP?

Caboose MCP requires the following environment variables: AWS_SECRETS_MANAGER (required). You'll also need a compatible MCP client like Claude Desktop or Claude Code.

Is Caboose MCP free to use?

Yes, Caboose MCP is open source and free to use. You can find the source code on GitHub.

What MCP clients support Caboose MCP?

Caboose MCP works with any MCP-compatible client including Claude Desktop (Anthropic's official desktop app), Claude Code (CLI tool), Cursor, and other editors with MCP support.

How do I configure Caboose MCP?

Configure Caboose MCP by adding it to your MCP client's config file. The setup block at the top of this page generates a ready-to-paste config for Claude Code, Cursor, Codex, Windsurf, and Claude Desktop.

MCP server/ai-tools

Caboose MCP Server

Q: What tools does Caboose MCP provide?

repo_create_tool: Creates a new tool definition in the repository.. repo_test_tool: Tests a specific tool with provided input.. repo_approve_tool: Approves a tool for deployment..

Q: How do I install Caboose MCP?

Install Caboose MCP by running: claude mcp add --transport http MCP_CABOOSE https://mcp.chrismarasco.io/mcp

Personal AI toolserver with 129 MCP tools for Claude and VS Code

caboose-mcp/fafb ↗by caboose-mcpupdated Mar 22, 2026

Manual setup required. We don't have a verified install command for this server. Follow the maintainer README and use the raw config below as a starting point.

Prepare the server locally

Run this once before adding it to Claude Code.

git clone https://github.com/caboose-mcp/fafb
cd fafb

Then follow the repository README for any remaining dependency or build steps.

Add it to Claude Code

Paste the maintainer's config below, then edit any placeholder values.

~/.claude.json

{
  "servers": {
    "fafb": {
      "type": "http",
      "url": "https://mcp.chrismarasco.io/mcp"
    }
  }
}

See the fafb README for full setup instructions.

Required:AWS_SECRETS_MANAGER

Make your agent remember this setup

caboose-mcp's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.

npx conare@latest

Free · one command · indexes the sessions already on disk. Set up in the browser instead →

What it does

Exposes 129 MCP tools across hosted, local, and common tiers
Includes Discord OAuth2 PKCE flow for secure authentication
Supports admin approval workflows for new tool creation
Automatic tool synchronization and deployment via GitHub PRs
Integrated with Slack and Discord for bot-based agent loops

Tools 3

repo_create_toolCreates a new tool definition in the repository.

repo_test_toolTests a specific tool with provided input.

repo_approve_toolApproves a tool for deployment.

Environment Variables

AWS_SECRETS_MANAGERrequiredUsed for storing fafb environment variables

Try it

→Create a new tool for my personal dashboard called 'weather_check' that fetches local weather data.

→Test the 'repo_create_tool' functionality with a dummy tool definition.

→Approve the pending 'github_issue_tracker' tool for deployment.

→List all available hosted tools currently managed by the ecosystem manager.

Original README from caboose-mcp/fafb

fafb

Personal AI toolserver — 129 MCP tools exposed to Claude, VS Code, and chat bots via a Go server hosted on AWS ECS, with Discord OAuth, admin approval workflows, and automatic tool synchronization.

Something selfishly for me but hopefully useful for others.

⚡ NEW: Ecosystem Manager (Phases 1-6) — Discord OAuth, auto-deployment, tool creation UI, admin approval workflows, and 129 tools extracted and synchronized.

Live endpoint: https://mcp.chrismarasco.io/mcp · Web UI: https://mcp.chrismarasco.io/ui/

[!WARNING] Experimental software — use at your own risk. This project is under active development and has not been fully tested. Tools may behave unexpectedly, modify data, or fail without warning. See the Disclaimer for full terms.

Architecture

graph TD
    Claude["Claude Code (stdio)"] -->|all 118 tools| Binary["fafb (Pi)"]
    VSCode["VS Code / Bruno"] -->|HTTPS| ALB["ALB · mcp.chrismarasco.io"]
    ALB --> Serve["ECS · --serve-hosted
68 hosted tools"]
    Slack["Slack"] --> Bots["ECS · --bots
Slack + Discord gateway"]
    Discord["Discord"] --> Bots
    Bots -->|Claude Haiku| Agent["Bot agent loop"]
    Binary -->|LAN MQTT| Bambu["Bambu A1 Printer"]
    Binary -->|socket| DockerD["Docker daemon"]
    Serve & Bots --> SM["AWS Secrets Manager
fafb/env"]

Tool Tiers

Tools are split so the cloud server only exposes what's safe remotely.

Tier	Flag	Count	What's included
Hosted	`--serve-hosted`	68	Calendar, Slack, Discord, GitHub, Notes, Focus, Learning, Sources, CloudSync, Audit, Auth, Health, Secrets, DB, Env, Mermaid, Greptile, Sandbox, Persona, Jokes, Setup, Claude Files, Self-Improve, Repo Management (create, test, approve, deploy), Gamma (presentations)
Local	`--serve-local`	25	Docker, execute_command, Bambu, Blender, Chezmoi, Toolsmith, Agency
Common	(any mode)	3	Jokes, Claude Files, Setup
Combined	`--serve` / stdio	129	Everything (common + hosted + local + new tools)

Full reference: docs/tools.md · ECOSYSTEM.md

⚡ Ecosystem Manager (NEW)

Phases 1-6 Complete: Secure, integrated toolkit for managing 129 MCP tools with Discord OAuth, admin approval workflows, and automatic tool synchronization.

Key Features

✅ Phase 1: Discord OAuth2 PKCE flow for user authentication ✅ Phase 2: Auto-extract 129 tools + auto-sync UI on push to main ✅ Phase 3: Tool creation, testing, and admin approval workflow ✅ Phase 4: Auto-generate Gamma presentation decks ✅ Phase 5: GitHub PR-based tool submission with CI tests ✅ Phase 6: Admin UI forms + parameter validation

Create a Tool

Via Web UI:

1. Go to https://ui.mcp.chrismarasco.io/admin/create-tool
2. Fill in tool details (name, description, parameters)
3. Click "Create Tool" → saved to ~/.claude/pending-tools/
4. Test via /admin/pending-tools
5. Admin approves → commits to main → auto-deploys

Via MCP:

fafb repo_create_tool --name "my_tool" --description "Does X" --tier "hosted"
fafb repo_test_tool --tool_name "my_tool" --test_input_json '{}'
fafb repo_approve_tool --tool_name "my_tool"

See ECOSYSTEM.md for complete workflow and API reference.

Quick Start

Connect to the live server

Claude Code CLI:

# HTTP — works in any project
claude mcp add --transport http MCP_CABOOSE https://mcp.chrismarasco.io/mcp

# User scope — available across all projects
claude mcp add --transport http --scope user MCP_CABOOSE https://mcp.chrismarasco.io/mcp

VS Code — add to .vscode/mcp.json:

{
  "servers": {
    "fafb": {
      "type": "http",
      "url": "https://mcp.chrismarasco.io/mcp"
    }
  }
}

Bruno — open the bruno/ folder as a collection.

Run locally (Claude Code on Pi)

cd packages/server && go build -o fafb .

# Interactive setup wizard — writes .env
./fafb --se

Frequently Asked Questions

What are the key features of Caboose MCP?

Exposes 129 MCP tools across hosted, local, and common tiers. Includes Discord OAuth2 PKCE flow for secure authentication. Supports admin approval workflows for new tool creation. Automatic tool synchronization and deployment via GitHub PRs. Integrated with Slack and Discord for bot-based agent loops.

What can I use Caboose MCP for?

Managing personal productivity workflows across calendar, notes, and Slack. Automating infrastructure and bot deployment via GitHub actions. Developing and testing custom MCP tools with an admin approval workflow. Controlling local hardware like Bambu printers and Docker containers via Claude.

How do I install Caboose MCP?

Install Caboose MCP by running: claude mcp add --transport http MCP_CABOOSE https://mcp.chrismarasco.io/mcp

What MCP clients work with Caboose MCP?

Caboose MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Conare · memory for coding agents

Turn this server into reusable context

Keep Caboose MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Set up free$npx conare@latest