$ loading_
Expose pooled Claude SDK agents for deterministic creation, retrieval, and resumption.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Agent Fleet MCP Server" yet — see the docs or source repo.
Use Agent Fleet MCP Server to create a Claude SDK agent for answering API design questions, and return its identifier.
A newly created agent with identifier details for later retrieval or resumption.
Retrieve an agent from the capability corpus that fits code review tasks, and describe the result.
Agent information matched to code review capabilities, ready to be used.
Resume a previously created agent session and continue the unfinished analysis task.
The specified agent state is resumed so it can continue the prior workflow.
When developers need multiple Claude SDK agents for different tasks in one system, this MCP server exposes the pool as tools. That makes it easier to create, find, and resume agents by capability.
For long-running workflows or interrupted tasks, teams can resume existing agents instead of starting over each time. It fits scenarios that need deterministic management of agent lifecycles.
When users want to choose agents by capability rather than manual setup, this server can retrieve suitable ones from a capability corpus. This helps assign agents to tasks more consistently.
It is an MCP server that exposes a pool of Claude SDK agents as tools. It supports deterministic agent creation, retrieval, and resumption from a capability corpus.
It is mainly used to manage agents in a pooled setup, including creating new agents, finding existing ones, and resuming prior agent state. The provided information does not specify more task types.
The provided material does not include installation steps, runtime requirements, or key configuration details. See the source repository for specifics.
Run Claude Agent SDK sessions as asynchronous sub-agents.
Get fresh, source-verified docs for building MCP servers and Claude agents.
Create, manage, and compose AI agents for MCP-compatible clients and tools.
Add agentic tools with iterative reasoning and tool use to apps
Coordinate multiple AI coding agents to build, review, and remember together.
Build MCP servers once and connect them to multiple AI agents.