SimTooReal
Train robot policies in Isaac Lab & MuJoCo. Auto-tune stalled runs, close the sim-to-real gap with Bayesian DR calibration, and deploy safely. Free plan.
https://www.simtooreal.com/Opens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://www.simtooreal.com/mcpWe add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · www.simtooreal.com
8tools discovered
Call Api
Call any SIMTOOREAL backend REST endpoint. Use this to query runs, metrics, system info, artifacts, training status, fleet, deployments, marketplace, etc. The backend has ~100 routes under /api/v1/.
Analyze Run
Fetch a training run's metrics and logs then use AI to generate a detailed analysis: progress summary, reward trends, stability observations, and recommendations.
Diagnose Failure
Fetch failure events and logs for a run then use AI to identify root causes and suggest specific fixes.
Suggest Hyperparams
Analyze a completed run's config and metrics then use AI to suggest better hyperparameters for the next training run with reasoning for each change.
Robot Move
Send a motion command to a real deployed robot unit in the fleet. Supports joint-space commands (list of angles in radians) or Cartesian end-effector targets (x,y,z + optional quaternion). Use fleet_status first to confirm the unit is online before commanding it. The command is forwarded to the robot's onboard controller via the deployment telemetry channel.
Fleet Status
Get real-time status of all robot fleet units: online/offline, current policy version, task success rate, fault codes, and last telemetry timestamp. Use this before sending robot_move commands to verify the target unit is online and healthy.
Seed Fault Retrain
Create a fault-aware VLA fine-tuning job seeded from fleet unit fault codes. Collects recent fault events from the specified unit, builds a curated training config that targets the observed failure modes, then enqueues a fine-tune job. This implements the Failure→Retrain loop: fleet fault codes → auto-seed fine-tune → deploy fix.
Get Visual Divergence
Compute or retrieve the sim-vs-real visual divergence score for a deployment. Returns per-channel SSIM, color histogram divergence, edge density ratio, and domain adaptation suggestions (lighting range, texture randomization, camera settings). High scores (>0.4) indicate the sim visuals differ significantly from real cameras — use the suggestions to update domain randomization config.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsTrain robot policies in Isaac Lab & MuJoCo. Auto-tune stalled runs, close the sim-to-real gap with Bayesian DR calibration, and deploy safely. Free plan.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate SimTooReal? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles probed 8 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
MCPBundles is an independent platform built on the open Model Context Protocol standard. Not affiliated with Anthropic PBC or Claude.