FleetQ

v1.0.0Coding Agentsstable

AI Agent Mission Control — 200+ MCP tools across 31 domains. Manage agents, experiments, workflows, crews, skills, tools, credentials, approvals, signals, budgets, marketplace, knowledge bases, chatbots, and more. Self-hosted, open-source (AGPL-3.0).

agent-orchestrationagentic-aiai-agentsai-automationautonomous-agents
Share:
30
Stars
0
Downloads
0
Weekly
0/5

What is FleetQ?

FleetQ is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai agent mission control — 200+ mcp tools across 31 domains. manage agents, experiments, workflows, crews, skills, tools, credentials, approvals, signals, budgets, marketplace, knowledge bases, chatbo...

AI Agent Mission Control — 200+ MCP tools across 31 domains. Manage agents, experiments, workflows, crews, skills, tools, credentials, approvals, signals, budgets, marketplace, knowledge bases, chatbots, and more. Self-hosted, open-source (AGPL-3.0).

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • AI Agent Mission Control — 200+ MCP tools across 31 domains.

Use Cases

Manage 200+ MCP tools
Agent orchestration
Workflow automation
escapeboy

Maintainer

LicenseAGPL 3.0
Languagephp
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx fleetq

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use FleetQ

FleetQ (Agent Fleet) is a self-hosted, open-source AI agent orchestration platform exposing over 675 MCP tools across 62 tool groups, covering agent management, workflow DAG orchestration, budget controls, approval inboxes, signal ingestion, SSH command execution, artifact tracking, and multi-channel notifications. It serves as a mission control layer for autonomous AI agent pipelines, supporting human-in-the-loop approvals, pessimistic budget locking, and comprehensive audit trails for production deployments. Built with Laravel and Livewire, it requires PostgreSQL, Redis, and at least one LLM provider API key.

Prerequisites

  • Docker and Docker Compose installed (recommended deployment path)
  • PostgreSQL database (Docker Compose sets this up automatically)
  • Redis instance (Docker Compose sets this up automatically)
  • At least one LLM provider API key: ANTHROPIC_API_KEY, OPENAI_API_KEY, or GOOGLE_AI_API_KEY
  • An MCP-compatible client such as Claude Desktop or Cursor
1

Clone the repository

Clone the FleetQ repository from GitHub.

git clone https://github.com/escapeboy/agent-fleet-o.git
cd agent-fleet-o
2

Run the automated installer

Use the make install command, which copies the env file, builds Docker services, and launches an interactive setup wizard to configure your database, admin credentials, and LLM providers.

make install
3

Configure LLM provider API keys

Edit the .env file to add your LLM provider credentials. At least one provider is required for agents to execute tasks.

# In .env:
ANTHROPIC_API_KEY=your-anthropic-key
OPENAI_API_KEY=your-openai-key
GOOGLE_AI_API_KEY=your-google-key
4

Access the FleetQ web interface

Once the installer completes, open the web interface to finish setup and locate your MCP server connection URL.

# Visit in browser:
http://localhost:8000
5

Configure your MCP client

Add the FleetQ MCP server to your Claude Desktop config. The server URL is available in the FleetQ web interface under the MCP integration settings.

{
  "mcpServers": {
    "fleetq": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "http://localhost:8000/mcp"]
    }
  }
}

FleetQ Examples

Client configuration

Claude Desktop configuration connecting to a self-hosted FleetQ instance via mcp-remote.

{
  "mcpServers": {
    "fleetq": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "http://localhost:8000/mcp"]
    }
  }
}

Prompts to try

Agent orchestration and workflow management tasks available through FleetQ's MCP tools.

- "List all active agents and their current status"
- "Create a new workflow that drafts a blog post, runs an SEO check, and then publishes it"
- "Show me pending approval requests in the approval inbox"
- "What is the current budget usage for the content-automation agent crew?"
- "Run the web-scraper agent on https://example.com and save the results as an artifact"
- "Send a Slack notification to the #deployments channel when the pipeline completes"

Troubleshooting FleetQ

make install fails with Docker or database errors

Ensure Docker Desktop is running and docker compose (v2) is available. Run 'docker compose ps' to check container status. If PostgreSQL fails to start, check that port 5432 is not already in use by another local Postgres instance and adjust DB_PORT in the .env file if needed.

Agents fail to execute tasks with LLM provider errors

Verify that at least one LLM provider API key is correctly set in .env and that the key has sufficient quota. Run 'docker compose exec app php artisan tinker' and test the API connection. Check the Laravel Horizon queue dashboard at http://localhost:8000/horizon for job failure details.

MCP client cannot reach the FleetQ server at localhost:8000

Confirm the FleetQ containers are running with 'docker compose ps'. If using Claude Desktop on macOS with Docker in a VM, replace localhost with host.docker.internal or your machine's LAN IP. Check that port 8000 is not blocked by a local firewall.

Frequently Asked Questions about FleetQ

What is FleetQ?

FleetQ is a Model Context Protocol (MCP) server that ai agent mission control — 200+ mcp tools across 31 domains. manage agents, experiments, workflows, crews, skills, tools, credentials, approvals, signals, budgets, marketplace, knowledge bases, chatbots, and more. self-hosted, open-source (agpl-3.0). It connects AI assistants to external tools and data sources through a standardized interface.

How do I install FleetQ?

Follow the installation instructions on the FleetQ GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with FleetQ?

FleetQ works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is FleetQ free to use?

Yes, FleetQ is open source and available under the AGPL 3.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "fleetq": { "command": "npx", "args": ["-y", "fleetq"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use FleetQ?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides