What can you do with this server?

The vCFD MCP server lets an AI/voice agent manage OpenFOAM CFD cases end-to-end — from template-based case creation through meshing, async solving, job monitoring, result analysis, and ParaView export. * Discover templates & cases: list_templates, list_cases (with mesh/time status), describe_case * Case lifecycle: create_case (from a template like hagen_poiseuille), delete_case, clean_case (both require confirm=true) * Pipe setup: set_pipe_parameters for geometry (radius, length), fluid properties (density, viscosity), and mesh resolution (n_axial, n_radial), plus bulk velocity * Meshing: generate_mesh (blockMesh, optionally async) and check_mesh for quality summaries * Solving (async jobs): start_solver (returns job_id immediately), get_job_status, get_logs (residual-friendly tail), stop_job (SIGTERM or forced SIGKILL) * Results: summarize_results for spoken-friendly summaries and compare_to_analytical against the Hagen–Poiseuille solution * Visualization export: export_for_paraview via foamToVTK, with optional zip packaging

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@vCFD Create a Hagen-Poiseuille pipe case and run the simulation." 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.

vCFD

by gpu7

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

vCFD

Voice-driven CFD: Grok Voice + MCP + OpenFOAM + ParaView.

Speak natural language commands; a Grok voice agent calls vCFD MCP tools that set up and run OpenFOAM cases, then summarize results and export data for ParaView on your Mac.

JARVIS for CFD (pragmatic edition): full-duplex speech → tool calls → async solvers → spoken engineering summaries. Not movie magic—solid async job handling and careful tool design.

Architecture

Human (speech)
    ↕ Speech-to-Speech
Grok Voice / Voice Agent Builder
    ↓ Remote MCP (HTTP/SSE + auth)
vCFD MCP Server (Python / FastMCP)
    ↓ subprocess or Docker
OpenFOAM cases & solvers
    ↓ foamToVTK / case zip
ParaView (Mac)

vCFD does not modify OpenFOAM. It launches OpenFOAM executables and edits case dictionaries. OpenFOAM remains a separate GPLv3 runtime (see NOTICE).

Related MCP server: Foam-Agent

Quick start (Mac Silicon)

Requirements

Python 3.12+ and uv
Optional: Docker (for real OpenFOAM; mock mode works offline)
Optional: ParaView (visualization)
Grok Build for agentic development / local MCP

Install

git clone https://github.com/gpu7/vCFD.git
cd vCFD
uv sync

Run tests (mock OpenFOAM)

uv run pytest -q

Run MCP server (stdio)

export VCFD_OPENFOAM_MODE=mock   # or docker | native
./scripts/dev_stdio.sh

Attach to Grok Build

grok mcp add vcfd -- uv run --directory /path/to/vCFD vcfd-mcp

Or configure in ~/.grok/config.toml:

[mcp_servers.vcfd]
command = "uv"
args = ["run", "--directory", "/path/to/vCFD", "vcfd-mcp"]
env = { VCFD_OPENFOAM_MODE = "mock" }
enabled = true

First case: Hagen–Poiseuille pipe

Through MCP tools (or voice):

create_case(name="pipe1", template="hagen_poiseuille")
set_pipe_parameters(case_name="pipe1", radius=0.05, bulk_velocity=0.1)
generate_mesh(case_name="pipe1") → check_mesh(...)
start_solver(case_name="pipe1") → get_job_status(job_id=...)
summarize_results / compare_to_analytical
export_for_paraview → open zip/VTK in ParaView

OpenFOAM modes

Mode	Env	Use when
`mock`	`VCFD_OPENFOAM_MODE=mock`	Unit tests, no OF install
`docker`	`VCFD_OPENFOAM_MODE=docker`	Mac or EC2 with Docker
`native`	`VCFD_OPENFOAM_MODE=native`	Ubuntu with OF packages

See .env.example for all settings.

Voice agent (Grok Voice Agent Builder)

Deploy public MCP (EC2: ./deploy/aws/launch-ec2.sh).
Follow prompts/voice_agent_builder.md — console steps + MCP fields.
System prompt: prompts/voice_agent_system.md.
Code / paste helpers: voice/session.example.json, scripts/voice_session_snippet.py --from-latest.

./deploy/aws/launch-ec2.sh
uv run python scripts/voice_session_snippet.py --from-latest
# Paste URL + Bearer token into Voice Agent Builder remote MCP

AWS EC2

Automated launch scripts (AWS CLI on your Mac):

./deploy/aws/launch-ec2.sh --dry-run   # plan only
./deploy/aws/launch-ec2.sh             # launch Ubuntu + Docker + Caddy + MCP
./deploy/aws/status.sh
./deploy/aws/teardown.sh

Details: deploy/aws/README.md.

Project layout

src/vcfd/           # MCP server, OpenFOAM runner, analytics
cases/templates/    # OpenFOAM case templates (not OF source)
tests/              # pytest
deploy/             # Docker, systemd, AWS notes
prompts/            # Voice agent system prompt
scripts/            # dev helpers

License

vCFD code: MIT
OpenFOAM: GPLv3 (external dependency — not distributed as part of this repo’s source)

You may charge for applications or services built with vCFD as an external controller of OpenFOAM. Do not link or redistribute modified OpenFOAM without complying with GPLv3.

Status

Mock OpenFOAM pipeline: tested (uv run pytest)
Real OpenFOAM via Docker (opencfd/openfoam-default:2506, arm64-capable): mesh + simpleFoam + ParaView export verified on Mac Silicon
Grok Build project MCP: .grok/config.toml (grok mcp list)
Next: Voice Agent Builder / remote HTTP MCP on EC2, richer field sampling, more templates

Docker end-to-end

# Requires Docker Desktop running and image pull once:
docker pull opencfd/openfoam-default:2506
./scripts/e2e_docker.sh

Results land under cases/workspace/ (gitignored). Open the .foam or VTK/ export in ParaView.

ParaView via S3 (Mac)

After export_for_paraview on a server with VCFD_S3_BUCKET configured:

# Hands-off: watch S3 → download → open ParaView
./scripts/install_paraview_s3_watch.sh install

# Or one-shot:
./scripts/fetch_paraview_from_s3.sh --latest

Grok Build MCP

Project config is already set (docker mode):

grok mcp list
# tools available after restart / new session in this directory

Support

Dark Factory
Richard Casey
richardcaseyhpc@protonmail.com
+1 970-980-5975

Available Tools

16 tools

check_meshC

Run checkMesh and return a quality summary.

Inputs: case_name (required). Returns: object

clean_caseA

Remove time directories and post-processing output; keep 0/, constant/, system/.

Requires confirm=true.

Inputs: case_name (required), confirm. Returns: object

compare_to_analyticalA

Compare numerical pipe flow to Hagen–Poiseuille analytical solution.

In mock mode, uses an ideal parabolic profile with small noise-free match. With real OpenFOAM results, samples from case parameters (MVP: uses bulk U and analytical profile as reference; full field sampling can be extended).

Inputs: case_name (required). Returns: object

create_caseA

Create a new OpenFOAM case from a template.

Inputs: name (required), template, description. Returns: object

delete_caseA

Permanently delete a case directory. Requires confirm=true.

Inputs: case_name (required), confirm. Returns: object

describe_caseB

Describe a case: template, mesh status, parameters, latest time, solver.

Inputs: case_name (required). Returns: object

export_for_paraviewB

Export case for ParaView via foamToVTK and optional zip package on disk.

Inputs: case_name (required), make_zip. Returns: object

generate_meshA

Run blockMesh for the case. Use background=true for async job.

Inputs: case_name (required), background. Returns: object

get_job_statusA

Get status of a job by job_id, or list jobs for a case / all jobs.

Inputs: job_id, case_name. Returns: object

get_logsC

Return the tail of a solver/mesh job log (filtered residual-friendly).

Inputs: job_id (required), lines. Returns: object

list_casesA

List CFD cases in the workspace with mesh and time status.

Inputs: no named parameters. Returns: object

list_templatesA

List available OpenFOAM case templates (e.g. hagen_poiseuille).

Inputs: no named parameters. Returns: object

set_pipe_parametersC

Set Hagen–Poiseuille pipe geometry, fluid properties, and mesh resolution.

Units: meters, Pa·s (dynamic viscosity), kg/m³, m/s.

Inputs: case_name (required), length, radius, density, +4 more. Returns: object

start_solverA

Start the OpenFOAM solver as a background job. Returns job_id immediately.

Inputs: case_name (required), solver. Returns: object

stop_jobA

Stop a running job. force=true sends SIGKILL.

Inputs: job_id (required), force. Returns: object

summarize_resultsC

Summarize latest results for spoken delivery (times, parameters, residuals).

Inputs: case_name (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored 2026-08-08 16:25 across 16 tools

Disambiguation5/5

Each tool targets a distinct aspect of the CFD workflow—case lifecycle, mesh generation, solver jobs, or result analysis—so an agent can reliably select the right one. The slight similarity between describe_case and summarize_results is mitigated by their clear separation of case state versus result outcome.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern (e.g., list_cases, create_case, generate_mesh). Even longer names like set_pipe_parameters and export_for_paraview maintain the same verb-first structure, making the pattern predictable.

Tool Count4/5

At 16 tools, the count is slightly above the typical 3–15 sweet spot, but each tool maps to a necessary step in the CFD pipeline—templates, cases, mesh, solver, results, and export. No tool feels redundant, and the granularity supports a coherent workflow.

Completeness4/5

The tool surface covers the full lifecycle from template listing and case creation through mesh generation, solver execution, job monitoring, result summarization, and ParaView export. Minor gaps, such as editing arbitrary case files or importing custom templates, are outside the apparent intended scope and can likely be worked around.

Maintenance

ActivityMaintained

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Speechtotext Mcp
io.github.varvararatta
MCP server for Speech-to-Text
Speech Processing AI & Machine Learning
2
https://speechtotext_mcp.mcpize.run/mcp
mcp
com.gibsonai
GibsonAI MCP server: manage your databases with natural language
Databases Search
233
https://mcp.gibsonai.com/
llm-orchestration-agent-2
ai.getvda
MCP-Native LLM Orchestration Agent
Agent Orchestration AI & Machine Learning
1
https://llm-orchestration-agent-2.getvda.ai/mcp
Artificial Wit AI
com.artificialwit
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
ERP Systems CRM Knowledge & Memory
2
https://api.artificialwit.com/mcp

Related MCP Servers

ANSYS MCP Server
Command Line Research & Data
Bettertoo2
A
license
B
quality
F
maintenance
Enables natural language-driven ANSYS simulations (Fluent, Mechanical, Geometry) with automatic TUI script generation for reproducibility.
Updated 3 months ago (2026-08-08 15:38 UTC)
41
6
MIT
Foam-Agent
Autonomous Agents Research & Data
KasperHonore
A
license
Not graded
quality
A
maintenance
Automates OpenFOAM CFD simulations via MCP, enabling AI agents to mesh, run, and post-process cases from natural language prompts without any API keys.
Updated 3 months ago (2026-08-07 10:07 UTC)
MIT
Ansys CFX-MCPofficial
Code Execution
ansys
A
license
A
quality
B
maintenance
An MCP server that enables AI assistants to interact with Ansys CFX through PyCFX, supporting natural-language-assisted CFX-Pre, CFX Solver, and CFD-Post workflows for setup, execution, and postprocessing.
Updated 2 days ago (2026-11-08 21:00 UTC)
7
1,053 PyPI
3
Apache 2.0
openfoam-mcp
Aerospace & Astrodynamics
kimlnw
A
license
Not graded
quality
C
maintenance
Turns an AI assistant into an OpenFOAM setup and debugging co-pilot, enabling case scaffolding, dictionary edits, mesh sizing, turbulence calculations, and solver log analysis through natural language.
Updated 3 months ago (2026-08-23 08:49 UTC)
MIT

vCFD

Architecture

Quick start (Mac Silicon)

Requirements

Install

Run tests (mock OpenFOAM)

Run MCP server (stdio)

Attach to Grok Build

First case: Hagen–Poiseuille pipe

OpenFOAM modes

Voice agent (Grok Voice Agent Builder)

AWS EC2

Project layout

License

Status

Docker end-to-end

ParaView via S3 (Mac)

Grok Build MCP

Support

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

ANSYS MCP Server

Foam-Agent

Ansys CFX-MCPofficial

openfoam-mcp