Human Models MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Human Models MCP
by UsefulWrong · 0.7.0 · Public Research Preview
AI agents can run inspectable musculoskeletal simulations and retrieve numeric results, model provenance and rendered evidence.

Computed motion, with external joint assistance. This pushup_palms run uses
700 muscle actuators, fixed horizontal supports and a declared wrist-range
derivative. Colors show model activation; lines are transmission paths, not
muscle volumes. No human or clinical validation is claimed.
MP4 · Data and scientific passport
MCP / CLI → MuJoCo → saved states & model data → Blender → evidence
Quick start
Linux x86-64, Docker Engine with Compose, GNU Make and Python with venv support. The first line maps container ownership to your user. The build downloads pinned dependencies, models and Blender; allow several GB of disk space. Scientific execution uses Python 3.12 in Docker. No NVIDIA GPU, desktop or host Blender installation is needed.
export HMM_UID="$(id -u)" HMM_GID="$(id -g)"
make render-build
make render-previewOpen the printed local index.html: five CPU-rendered states, MP4/GIF, numeric
data and provenance. This is a quick preview; the animation above has more
frames. Installation, resources and troubleshooting.
Related MCP server: COMSOL MCP Server
Use with an agent or without AI
Generate an MCP stdio connector for this checkout:
python3 scripts/print_client_config.pyUse the printed command and arguments in your MCP client's configuration. The SDK client and tool guide includes discovery, experiment calls, chunked downloads and structured refusals. MCP is a local, single-user tool; the HTTP transport is container-loopback only.
Run an experiment directly, without an agent or Blender:
export HMM_UID="$(id -u)" HMM_GID="$(id -g)"
make build
python3 scripts/experiment.py --scenario pushup --output outputs/my-pushupChoose a new output directory for each run. The command prints a result page and exports checked CSV/JSON/NPZ artifacts.
Scientific scope
Scenario | Control and interpretation |
| Native 700-muscle recruitment, no external joint/body forces in muscle mode; synthetic reference, added damping and contact proxies. Separate numerical and exercise gates. |
| Full palm cycle shown above; muscle recruitment plus external residual joint assistance, ideal sticking supports and two modified wrist bounds. |
| Neutral fists and tucked elbows; muscle recruitment plus external residual joint assistance, fixed finger posture. Different stance and wrist envelope from palms. |
These configurations are not a controlled human comparison. Activation is not EMG; joint ranges are model settings. Ligaments, deformable tissue, injury risk and patient-specific predictions are unavailable. The included wrist benchmark compares a narrow geometric quantity with published cadaver aggregate data; it does not validate dynamic push-ups.
Reproduce an experiment · Model sources · Rendering · Security · Contribute · Release notes · RC evidence
Wrapper code: MIT. Model and MuJoCo: Apache-2.0. Optional Blender: GPL-3.0-or-later. These are separate licenses; see the component and demo notices and citation.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Physics-based validation of simulation results: receipts with per-check verdicts, via MCP.
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP Server for COMSOL Multiphysics simulation automation via AI agents.782MIT
- AlicenseBqualityCmaintenanceEnables AI agents to automate COMSOL Multiphysics simulations, including model management, geometry building, physics configuration, meshing, solving, and results visualization through the MCP protocol.78MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to automate COMSOL Multiphysics simulations, including model management, geometry building, physics configuration, meshing, solving, and results visualization via the MCP protocol.MIT
- AlicenseBqualityCmaintenanceEnables natural language interaction with ANSYS Mechanical simulation software via gRPC, allowing users to manage geometry, mesh, boundary conditions, solve analyses, and generate reports through MCP-compatible AI clients.3720Apache 2.0