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 Python 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 |
|
Design-thrust override (engine sizing)
run_adapter(..., design_thrust_lbf=<float>) is an additive option that drives
the cycle to an explicit design net thrust Fn_DES instead of deriving it from
CPACS aero drag. This is the entry point used by the agent's engine-resizing and
cruise-match skills to iterate on engine size (the achieved Fn_DES_lbf is
echoed back in the results). The classic drag-derived path is unchanged when the
argument is omitted.
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.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityFmaintenanceA Model Context Protocol (MCP) server that provides JSON-RPC functionality through OpenRPC.24243Apache 2.0
- Flicense-qualityDmaintenanceA Python-based implementation of the Model Context Protocol that enables communication between a model context management server and client through a request-response architecture.
- Flicense-qualityDmaintenanceA server implementation of the Model Context Protocol (MCP) that provides REST API endpoints for managing and interacting with MCP resources.
- AlicenseBqualityDmaintenanceA Model Context Protocol (MCP) server based on OpenRPC, providing JSON-RPC function invocation and method discovery services.21Apache 2.0
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
MCP server exposing the Backtest360 engine API as tools for AI agents.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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