Ansys CFX-MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| session_statusA | Report whether the cfx leaf has an active backend. Safe to call before |
| connectA | Connect the cfx leaf to a backend. Available backend kinds: ['pycfx']. Pass |
| disconnectA | Disconnect the cfx leaf's active backend. |
| run_codeA | Execute Python code against the active PyCFX session namespace. The code runs with |
| validate_codeA | Dry-run / validate CFX Python without applying side effects. Returns parse / type / semantic feedback. |
| cfx_workflowA | Run one focused CFX lifecycle or artifact action. Actions: start_pre, import_mesh, write_def, start_solver, wait_solver, get_results_file, open_post, status. Use the external agent layer for custom PyCFX code generation. |
| cfx_model_contextA | Return a targeted, compact CFX model context slice. Actions: summary, list_named_objects, find_named_object, select_named_objects, state, api_help, find_api, allowed_values, targeted_context. Use max_items to keep responses small. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| toolsets_definition | Toolset definitions for PyAnsysMCPService discovery. |
TDQS
Scored across 7 tools
Most tools have clearly distinct roles: connection lifecycle (connect/disconnect/session_status), code execution/validation (run_code/validate_code), workflow actions, and model context queries. The main potential confusion is between run_code and cfx_workflow, since cfx_workflow actions could also be performed via custom Python, but the descriptions provide enough routing guidance to separate them.
Tool names mostly follow a clean snake_case pattern with imperative verbs (connect, disconnect, run_code, validate_code). session_status and cfx_workflow/cfx_model_context are more noun-like, but overall the naming is consistent enough and predictable across the set.
Seven tools is a well-scoped size for this server's purpose. Each tool covers a distinct functional layer: backend connection, live code execution, validation, high-level workflow control, and model introspection, without redundancy or bloat.
The tool surface covers the main CFX interaction lifecycle: connect, run custom code, validate, drive workflows, and inspect model context. run_code provides an escape hatch for arbitrary PyCFX operations, though a few high-level conveniences like explicit solver output retrieval or session list/close operations are absent, which is a minor gap.