ansys-fluent-mcp

ansys-fluent-mcp is an MCP server development skill for AI agents, published by Cai-aa in the CAE-Agent-Hub repository on GitHub. Skillspace rates ansys-fluent-mcp D (57/100) and it passed the safety scan; the rating is based on static analysis only.

Drive an ANSYS Fluent solver session through the standalone `ansys-fluent-mcp` MCP server. USE WHEN the user asks to load a case/mesh, inspect physics, change settings, run iterations, or query results — and the chat client is connected directly to the MCP (VS Code Copilot, Cursor, Claude Desktop). EXPOSES a 22-tool surface: `session_status`, `connect`, `disconnect`, `find_api`, `get_help`, `get_state`, `get_targeted_context`, `list_named_objects`, `find_named_object`, `select_named_objects`, `summarize_setup`, `simulation_report`, `solver_status`, `run_code`, `validate_code`, `screenshot`, `mesh_quality`, `list_fields`, `compare_files`. This is a STATELESS leaf: there is no plan/journal/rollback and no `propose_step` / `finalize` planning machinery — `run_code` mutates the live solver immediately. DO NOT USE FOR generic Python / CFD-theory questions unrelated to Fluent.

Grade
D
Quality
57 / 100
Safety
Passed
GitHub stars
889

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubCai-aa/CAE-Agent-Hub

Our review

Architecture
80 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in MCP server development

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.