pycycle-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pycycle-mcpRun parametric sweep on turbofan cycle with BPR range 5-7."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pycycle-mcp
pycycle-mcp is a lightweight Model Context Protocol server for pyCycle/OpenMDAO
engine-cycle workflows. The repository includes deterministic examples/tests so
local development and CI can validate tooling contracts without requiring a full
runtime installation of pyCycle/OpenMDAO assets.
Overview
The project currently provides:
A FastMCP-powered server with stdio and HTTP-compatible transports.
Tooling for cycle lifecycle, variable inspection/updates, execution, sweeps, and total-derivative evaluation.
Pydantic-backed validation with structured MCP-style error payloads.
Deterministic examples for repository scaffolding checks and smoke tests.
Related MCP server: MCP-PIF Server
Quickstart
Requires Python 3.12+.
python3 -m venv .venv
source .venv/bin/activate
make dev
make test
make ciStart the server over stdio:
pycycle-mcp --transport stdioInspect the non-blocking HTTP transport configuration example:
PYTHONPATH=src python3 examples/server/http_launch_config.pyExamples
The examples are deterministic and aligned with the current repository contracts.
Examples index:
examples/README.mdTool discovery:
examples/client/tool_discovery.pySession lifecycle:
examples/cpacs/session_lifecycle.pyExport snapshot:
examples/cpacs/export_snapshot.py
Docs
Docs source:
docs/index.rstPublished docs (placeholder): https://cmudrc.github.io/pycycle-mcp/
Build the docs locally with:
make docsPython API Rename
The package import root is now:
pycycle_mcp(new)
Legacy pre-rename import paths and CLI aliases are intentionally removed.
Shared-CPACS Integration
This MCP includes a CPACS adapter (src/pycycle_mcp/cpacs_adapter.py) that
bridges pyCycle to the shared-CPACS aircraft analysis pipeline.
What it does
The adapter reads engine parameters and aerodynamic drag from CPACS, runs a real
OpenMDAO/pyCycle turbofan cycle analysis, and writes performance results — net
thrust, TSFC, OPR, BPR, fuel flow — into //mcpResults.
Direction | XPath |
Reads |
|
Writes |
|
Running as part of the pipeline
python pipeline/shared_cpacs_orchestrator.py D150_v30.xml --mcps tigl su2 pycycle missionSee cmudrc/aircraft-analysis for full pipeline documentation, versioning details, and installation instructions.
Related MCP servers
MCP | Repository |
TiGL (geometry) | |
SU2 (CFD aerodynamics) | |
Mission (trajectory/fuel) |
Contributing
Contribution guidelines live in CONTRIBUTING.md.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cmudrc/pycycle-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server