mcpField
C
CircusMCP - AI Agent DevServer Management Made Simple

CircusMCP - AI Agent DevServer Management Made Simple

github.com/aether-platformOther2Updated 34w ago

About CircusMCP - AI Agent DevServer Management Made Simple

Circus MCP exposes Circus process management to AI coding agents through structured tools, reducing the need to parse shell output during development troubleshooting. It supports process lifecycle operations and dynamic process addition.

Key features

  1. 01List managed processes
  2. 02Inspect process state and PID
  3. 03Start, stop, and restart processes
  4. 04Add processes dynamically
  5. 05Structured MCP tool responses

Use cases

  1. 01Check development process status
  2. 02Restart a process while debugging
  3. 03Add a process to a development setup

MCP support

Circus MCP exposes process lifecycle operations as MCP tools, including listing, status checks, start, stop, restart, and dynamic addition. Agents can use structured responses instead of raw shell command output.

Details

From the project README

Circus MCP

PyPI version Python 3.10+ License: MIT

Cut 75-80% of AI agent debugging tokens in development cycle. Process management via MCP — structured tools replace shell commands.

75-80% Token Reduction for AI Agent Debugging in Development Cycle

AI agents debugging processes via raw shell commands (supervisorctl, ps, journalctl) burn most of their tokens on unstructured output parsing, repeated commands, and inter-step reasoning. Circus MCP replaces this with structured, bounded MCP tool responses.

Raw CommandsCircus MCPReduction
Tool calls per investigation8-123-560-70%
Tokens per investigation2,900-9,400935-1,535~75%
With retries (typical)~10,000+~2,000~80%
Retry cost scalingExponentialLinear—

Process Management via MCP

Circus MCP exposes process lifecycle operations as MCP tools. AI agents call structured tools instead of parsing shell output.

ToolParametersDescription
list_processes—List all managed processes
get_process_statusnameProcess state and PID
start_processnameStart a process
stop_processnameStop a process
restart_processnameRestart a process
add_processname, command, numprocesses?, working_dir?Add a new process dynamically
Claude Code
claude mcp add circus-mcp -- uv run circus-mcp mcp
VS Code / Cursor

.vscode/mcp.json:

{
  "servers": {
    "circus-mcp": {
      "command": "uv",
      "args": ["run", "circus-mcp", "mcp"]
    }
  }
}

Circus MCP vs Supervisord MCP

Circus MCPSupervisord MCP
Dynamic process additionVia APINot supported (requires config file edit + reload)
Log retrievalstdout + stderr in one callSeparate calls
System stats (CPU/memory)AvailableNot available
Idempotent operationsensure_started / ensure_stoppedThrows error if already running
TransportZeroMQ (async)HTTP XML-RPC (sync)
Best forAI agent workflowsExisting Supervisord environments

Documentation

License

MIT — see LICENSE. Built on Circus.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.