Skip to main content
Glama

agent-fleet-mcp (beta)

An MCP server that lets a lead agent (you in Claude Desktop, ChatGPT, Antigravity, Claude Code, VS Code, ...) run manager agents, and lets managers run their own child agents — across:

Backend

How it is driven

Needs

codex — ChatGPT desktop (Codex mode) / Codex CLI

OpenAI's official codex app-server JSON-RPC

npm i -g @openai/codex, signed in

antigravity — Google Antigravity

official agy -p --output-format stream-json

Antigravity CLI (agy), signed in

claude-code — Claude Code

claude -p --output-format stream-json

Claude Code CLI, signed in

ollama, lmstudio, vllm, any OpenAI-compatible server

/v1/chat/completions

server running locally

Agents created through Codex show up in the ChatGPT desktop app's Codex history, and Antigravity agents in Antigravity's history.

Install

Needs Python 3.11+ and uv (or pip).

uv tool install git+https://github.com/s0wingseason/agent-fleet-mcp
agent-fleet install      # adds agent-fleet to every supported app it finds
agent-fleet doctor       # shows which apps and backends were found

Then fully quit and reopen each app (Claude Desktop and ChatGPT keep running in the tray).

agent-fleet install --hosts claude-desktop,codex limits it to some apps; --dry-run shows what would change. agent-fleet uninstall removes it again. Every edited config file gets a one-time *.agent-fleet.bak backup.

Apps it configures: Claude Desktop (including the Microsoft Store build), Claude Code, ChatGPT desktop / Codex CLI (~/.codex/config.toml), Google Antigravity (~/.gemini/.../mcp_config.json), Gemini CLI, VS Code, Cursor, Windsurf, LM Studio, Hermes Agent.

Not MCP hosts, so nothing is installed into them: Ollama, vLLM (use them as agent backends). Bionic and Open WebUI need manual setup (not covered yet).

Related MCP server: agentmux

Tools

Tool

Who

fleet_status

everyone

spawn_agent, send_message, wait_for_agents, get_agent, get_transcript, interrupt_agent, stop_agent

lead: any agent; manager: its own children

send_files, fetch_files, list_files

same; files go through each agent's inbox / outbox

list_app_conversations, read_app_conversation, adopt_conversation

lead only — reads Codex, Claude Code and Antigravity history saved on this PC, or takes over one of those conversations

Typical lead prompt: "Use agent-fleet: spawn a codex manager to refactor X, an antigravity manager to write tests, wait for both, then fetch their files."

Calls never block more than ~55 s (MCP hosts time out around 60 s); poll wait_for_agents for long jobs.

How it works

  • Every app launches its own agent-fleet serve process. Agents run inside the process that created them; all processes share one SQLite database in ~/.agent-fleet, so every app sees every agent, its status and transcript. An agent can only be messaged from the app that runs it — unless that app has closed, in which case the next app to message it takes it over and resumes the same conversation.

  • Managers get the agent-fleet tools injected (Codex via -c mcp_servers..., Claude Code via --mcp-config) with their own identity; children run without them.

  • Folders: ~/.agent-fleet/agents/<id>/{work,inbox,outbox}, shared drop folder ~/.agent-fleet/exchange. Config: ~/.agent-fleet/config.toml (models, sandbox modes, limits, allowed folders).

Known limits of this beta

  • Not yet tested end to end on Windows with all backends together; please file issues.

  • No Windows .exe installer yet (planned), and no desktop/UI automation.

  • Regular ChatGPT chats (not Codex) live in OpenAI's cloud and aren't readable here. Automating the ChatGPT window to scrape replies conflicts with OpenAI's Terms of Use; this project only uses OpenAI's own codex app-server interface.

  • Antigravity history reading is best-effort (undocumented storage format).

  • Local-model agents are chat-only (no file tools yet).

  • If codex on your PATH is a different program (e.g. the PyPI "codex" comic server), agent-fleet ignores it and looks for OpenAI's CLI under npm's global folder; agent-fleet doctor reports this.

Safety

Agents run with your user account. Codex agents default to workspace-write sandbox; Claude Code agents to acceptEdits; Antigravity agents to --sandbox. File tools refuse paths outside allowed folders and anything that looks like keys or credentials. Review ~/.agent-fleet/config.toml before giving agents broader access.

MIT licensed.

Available Tools

14 tools
adopt_conversationB

Lead only. Turn an existing codex, claude-code or antigravity conversation into a fleet agent so you can keep directing it with send_message.

Inputs: app (required), name (required), conversation_id (required), role.

fetch_filesA

Copy the agent's deliverables (its outbox, or specific paths) to dest. Default dest is the fleet exchange folder for the lead, or your own inbox for a manager.

Inputs: agent_id (required), dest, paths.

fleet_statusC

Who you are (lead, manager or child), which agent backends work on this PC, and the agents you can see.

Inputs: no named parameters.

get_agentC

Status, folders, children and latest output of one agent.

Inputs: agent_id (required).

get_transcriptB

The agent's conversation log: your messages, its replies, tool activity and errors. Page with after_event_id.

Inputs: agent_id (required), limit, after_event_id.

interrupt_agentA

Cancel what the agent is doing right now; it stays available for new messages.

Inputs: agent_id (required).

list_app_conversationsB

Lead only. List conversations saved on this PC by app: codex (ChatGPT desktop Codex mode and Codex CLI), claude-code, or antigravity.

Inputs: app (required), limit, search.

list_filesB

List files in an agent's outbox, inbox or workdir.

Inputs: agent_id (required), where.

read_app_conversationB

Lead only. Read one saved conversation from codex, claude-code or antigravity.

Inputs: app (required), conversation_id (required), max_chars.

send_filesB

Copy files or folders into the agent's inbox. The lead may send from Desktop, Documents, Downloads (configurable) and fleet folders; managers from their own folders.

Inputs: paths (required), agent_id (required), subfolder.

send_messageA

Send the agent its next instruction. Returns at once unless wait_seconds > 0 (max ~55).

Inputs: text (required), agent_id (required), wait_seconds.

spawn_agentB

Create an agent. backend: codex (ChatGPT/Codex), antigravity, claude-code, ollama, lmstudio, vllm, or another name from fleet_status. role: 'manager' (can create its own child agents) or 'child'. Managers can only create children. If task is given it is sent as the first message. workdir (lead only) points the agent at an existing folder, e.g. a code repo.

Inputs: name (required), backend (required), role, task, +4 more.

stop_agentA

Stop an agent for good (and its children).

Inputs: agent_id (required).

wait_for_agentsA

Wait (max ~55s) until the agents finish their current work. mode 'all' or 'any'. Returns each agent's status and latest output; call again if done is false.

Inputs: agent_ids (required), mode, timeout_seconds.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 14 tools

    Disambiguation4/5

    Most tools target clearly distinct operations: lifecycle (spawn/stop/interrupt), communication (send_message/wait_for_agents), inspection (get_agent/get_transcript), and file transfer (send/fetch/list_files). The retrieval cluster is slightly fuzzy — fleet_status vs get_agent vs get_transcript, and wait_for_agents vs get_agent — but descriptions clarify the polling/blocking distinction well enough that misselection is unlikely.

    Naming Consistency4/5

    Nearly all names follow a snake_case verb_noun pattern (spawn_agent, send_message, stop_agent, list_files). The main deviations are fleet_status (noun-first, no verb) and inconsistent retrieval verbs (get vs fetch vs list vs read), but the overall convention is readable and predictable.

    Tool Count5/5

    Fourteen tools is well within a healthy range for a multi-agent orchestration server that spans agent lifecycle, messaging, file exchange, and conversation import. Each tool maps to a distinct operation with no padding or redundancy.

    Completeness4/5

    The surface covers the full agent lifecycle (spawn, message, wait, inspect, interrupt, stop) plus file transfer and conversation adoption, which is strong coverage. Minor gaps exist: no way to remove/clean up a stopped agent from the fleet, no batch/multi-agent messaging or broadcast, and no way to update an agent's configuration after spawn.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables users to delegate text and code tasks across multiple AI models with automatic failover, maintain shared mission memory and checkpoints across MCP harnesses, and coordinate parallel role-based subagents. It also supports model discovery, provider inventory, health checks, and stdio/HTTP tool access while leaving patches and tests to the harness.
      24
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables any MCP host to delegate work to multiple coding-agent CLIs such as Codex, Claude Code, and Antigravity as subagents, preserving native sessions and supporting team-based supervision and agent-to-agent messaging.
      17
      11 npm
      Apache 2.0
    • A
      license
      B
      quality
      B
      maintenance
      Enables MCP-compatible clients to delegate complex multi-step programming and research goals to coordinated teams of specialized subagents, with cross-session messaging, swarm and pipeline workflows, sandboxed workspace tools, persistent SQLite state, and a live dashboard.
      22
      74 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Provides a provider-agnostic MCP server that coordinates structured multi-agent workflows, owning task claims, action logs, handoffs, and server-side health gates for coding agents. It enables tracked specs, tasks, reviews, and verified completion across Claude Code, Codex CLI, Cursor, Grok Build, and OpenCode.
      29 npm
      MIT