agent-fleet-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
agent-fleet runs other AI agents for you. Usual flow: fleet_status -> spawn_agent(role='manager', backend=..., task=...) -> wait_for_agents (repeat until done) -> get_agent / get_transcript -> fetch_files. Managers can create their own child agents. No call blocks for more than about 55 seconds, so keep polling wait_for_agents for long tasks.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fleet_statusC | Who you are (lead, manager or child), which agent backends work on this PC, and the agents you can see. |
| 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. |
| send_messageA | Send the agent its next instruction. Returns at once unless wait_seconds > 0 (max ~55). |
| 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. |
| get_agentC | Status, folders, children and latest output of one agent. |
| get_transcriptB | The agent's conversation log: your messages, its replies, tool activity and errors. Page with after_event_id. |
| interrupt_agentA | Cancel what the agent is doing right now; it stays available for new messages. |
| stop_agentA | Stop an agent for good (and its children). |
| 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. |
| 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. |
| list_filesB | List files in an agent's outbox, inbox or workdir. |
| 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. |
| read_app_conversationB | Lead only. Read one saved conversation from codex, claude-code or antigravity. |
| 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
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.
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.
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.
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.