CircusMCP - AI Agent DevServer Management Made Simple
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
- 01List managed processes
- 02Inspect process state and PID
- 03Start, stop, and restart processes
- 04Add processes dynamically
- 05Structured MCP tool responses
Use cases
- 01Check development process status
- 02Restart a process while debugging
- 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 READMECircus MCP
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 Commands | Circus MCP | Reduction | |
|---|---|---|---|
| Tool calls per investigation | 8-12 | 3-5 | 60-70% |
| Tokens per investigation | 2,900-9,400 | 935-1,535 | ~75% |
| With retries (typical) | ~10,000+ | ~2,000 | ~80% |
| Retry cost scaling | Exponential | Linear | — |
Process Management via MCP
Circus MCP exposes process lifecycle operations as MCP tools. AI agents call structured tools instead of parsing shell output.
| Tool | Parameters | Description |
|---|---|---|
list_processes | — | List all managed processes |
get_process_status | name | Process state and PID |
start_process | name | Start a process |
stop_process | name | Stop a process |
restart_process | name | Restart a process |
add_process | name, 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 MCP | Supervisord MCP | |
|---|---|---|
| Dynamic process addition | Via API | Not supported (requires config file edit + reload) |
| Log retrieval | stdout + stderr in one call | Separate calls |
| System stats (CPU/memory) | Available | Not available |
| Idempotent operations | ensure_started / ensure_stopped | Throws error if already running |
| Transport | ZeroMQ (async) | HTTP XML-RPC (sync) |
| Best for | AI agent workflows | Existing Supervisord environments |
Documentation
- AI Token Reduction Solution — Token cost analysis, team-scale projections, research references
- AI & MCP Technical Background — Architecture, MCP hosting, tenant isolation
- Installation & CLI Reference — Setup, configuration, full command reference
License
Comments
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.