Skip to content
InfratoApp
InfratoApp / Resources / MCP servers / agent-fleet-o

agent-fleet-o

agent-fleet-o is an MCP server, listed under model apis. It reaches anthropic, google, openai and typesafe. It needs ANTHROPIC_API_KEY, DB_PASSWORD, GOOGLE_AI_API_KEY, OPENAI_API_KEY, OP_SERVICE_ACCOUNT_TOKEN and TYPESAFE_API_KEY to authenticate. Its repository has 76 GitHub stars and is licensed under AGPL-3.0; we last read it on 2026-10-22.

Agent-fleet-o is an open-source platform for self-hosted orchestration of autonomous multi-agent systems, offering visual DAG workflows and integration with 670+ MCP tools. It supports human-in-the-loop approvals and connects with AI agents like Claude, GPT-4o, Gemini, Ollama, and Codex.

Install

MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. agent-fleet-o’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.

What it reaches, and what it needs

Reaches
anthropic, google, openai, typesafe
Credential
ANTHROPIC_API_KEY, DB_PASSWORD, GOOGLE_AI_API_KEY, OPENAI_API_KEY, OP_SERVICE_ACCOUNT_TOKEN, TYPESAFE_API_KEY

What it connects to

Wraps

Unverified means a mention in the server’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.

Maintenance

Stars
76
State
listed
Licence
AGPL-3.0
From the repository

Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 670+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.

agent-fleet-o compared with similar servers

agent-fleet-o compared with the closest alternatives, by services reached, credentials, stars, last update and licence
ServerReachesNeedsStarsLast updateLicence
agent-fleet-o (this page)anthropic, google, openai, typesafeANTHROPIC_API_KEY, DB_PASSWORD, GOOGLE_AI_API_KEY, OPENAI_API_KEY, OP_SERVICE_ACCOUNT_TOKEN, TYPESAFE_API_KEY762026-10-20AGPL-3.0
Promptheusanthropic, google, openai(3 shared)ANTHROPIC_API_KEY, GOOGLE_API_KEY, OPENAI_API_KEY172026-10-13MIT
paperbananaatlascloud, google, openai(2 shared)ATLASCLOUD_API_KEY, GOOGLE_API_KEY, OPENAI_API_KEY2,4122026-09-17MIT
just-promptanthropic, deepseek, gemini, groq, openai(2 shared)ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, OPENAI_API_KEY7392025-08-10—
flamaanthropic, openai(2 shared)None listed3042026-10-13Apache-2.0
schemagateanthropic, entra, gemini, mysql, openai, postgres, schemagate(2 shared)ANTHROPIC_API_KEY, ENTRA_CLIENT_SECRET, GEMINI_API_KEY, OPENAI_API_KEY, SCHEMAGATE_AUDIT_SIGNING_KEY1052026-10-22Apache-2.0

Ranked by services in common with agent-fleet-o, then by stars. Figures are from each repository when we last read it.

Common questions about agent-fleet-o

What does agent-fleet-o do?
Agent-fleet-o is an open-source platform for self-hosted orchestration of autonomous multi-agent systems, offering visual DAG workflows and integration with 670+ MCP tools. It supports human-in-the-loop approvals and connects with AI agents like Claude, GPT-4o, Gemini, Ollama, and Codex.
How do I install agent-fleet-o?
Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/escapeboy/agent-fleet-o
What does agent-fleet-o connect to, and what does it need?
It reaches anthropic, google, openai and typesafe. The credentials we found in its source are ANTHROPIC_API_KEY, DB_PASSWORD, GOOGLE_AI_API_KEY, OPENAI_API_KEY, OP_SERVICE_ACCOUNT_TOKEN and TYPESAFE_API_KEY.
Is agent-fleet-o official and is it maintained?
We found nothing naming it as a vendor’s official server. Its repository has 76 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-20.
What licence does agent-fleet-o use?
The repository declares the AGPL-3.0 licence.

More MCP servers for model apis

All model apis entries →

Learn this on Infrato