MCP.Market

Isaac Sim robot workbench MCP server

by Milokucia·io.github.Milokucia/dex-isaac-mcp·v0.1.2
No reviews yet

Drive a live Isaac Sim session: any robot, poses, gain tuning, range tests, Isaac Lab training.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Isaac Sim robot workbench yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Isaac Sim robot workbench tools (36, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • sim_capture

    A frame from the capture camera. Works headless; no GUI or viewport needed.

  • sim_down

    Stop the sim daemon; its container removes itself.

  • sim_frame_robot

    Aim the capture camera so the whole robot fills the frame.

  • sim_get_joint_state

    Joint positions (rad/m) and velocities, plus driven joints' normalized positions and limits.

  • sim_get_stats

    Per-joint travel and driven-joint mean tracking error since the last reset.

  • sim_inspect_joints

    List a USD's articulation DOFs, joints excluded from the articulation (loop closures), and roots.

  • sim_list_objects

    Every spawned prop with its current world pose (pos in m, rot as w, x, y, z).

  • sim_list_poses

    Named poses from the robot config, as {pose: {joint_pattern: 0..1}}.

  • sim_playwrite action

    Run the sim continuously in real time (True) or pause it (False).

  • sim_range_test

    Drive every driven joint from its lower limit toward `target`, report the fraction reached.

  • sim_record_caption

    Change the caption drawn on frames recorded from now on ('' for none).

  • sim_record_start

    Start recording the capture camera: one frame every `every` physics steps.

  • sim_record_stop

    Stop recording and write an animated GIF; returns its path on the host.

  • sim_reload

    Restart the daemon to change a spawn property: robot, USD, solver iterations, self-collision.

  • sim_remove_objectwrite action

    Delete a spawned prop.

  • sim_screenshot

    Capture the viewport as an image. Requires the daemon started with gui=True.

  • sim_set_backdropwrite action

    Put a plain panel (RGB 0..1) behind the robot, facing the capture camera; no color removes it.

  • sim_set_camera

    Point the viewport camera, e.g. eye=[1.2, 1.2, 1.0] target=[0, 0, 0.3].

  • sim_set_capture_camera

    Place the capture camera by hand (sim_frame_robot does it automatically).

  • sim_set_coupling

    Change software-coupling ratios live, keyed by follower joint. 0 releases a follower.

  • sim_set_params

    Change the driven joints' PD gains and effort limit on the live articulation.

  • sim_set_pose

    Command a named pose. amount blends toward it: 1 = as authored, 0.5 = halfway.

  • sim_set_targets

    Command the driven joints, normalized 0..1 (lower..upper limit).

  • sim_spawn_object

    Add a prop to the live scene: a primitive or a USD file, with collision.

  • sim_status

    Report whether the sim daemon is up, its robot, driven joints, poses and parameters.

  • sim_step

    Advance the simulation n physics steps (dt from sim_status, default 1/120 s).

  • sim_sweep

    Compare several values of one live parameter inside the single session.

  • sim_up

    Start the daemon container and wait until it answers. Idempotent.

  • sim_wave

    Sweep every driven joint through its range for n steps; return travel stats.

  • train_checkpoints

    List a run's saved checkpoints with step and size.

  • train_list

    List training runs: live or recent containers, and log directories holding checkpoints.

  • train_logs

    Tail a running training container's stdout/stderr.

  • train_metrics

    TensorBoard scalars for a run: no tag lists tag names; a tag returns its series, downsampled.

  • train_start

    Launch a headless Isaac Lab training run in its own container; returns at once.

  • train_status

    Container state, checkpoints, and latest TensorBoard scalar values for one run.

  • train_stop

    Stop a training run's container.

Public scan report

scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it

no findings
  • Code scan13 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Isaac Sim robot workbench compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 1,299 Productivity servers
Tools
36
the typical Productivity server has 7
Tools that change things
8%
typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 33 read · 3 change

Install Isaac Sim robot workbench in Claude Code, Cursor or VS Code

claude mcp add dex-isaac-mcp -- uvx dex-isaac-mcp
Add to Cursor

What the publisher says

From the Isaac Sim robot workbench repository's README, as published. We do not edit it. Read it on GitHub

dex-isaac-mcp

<!-- mcp-name: io.github.Milokucia/dex-isaac-mcp -->

Recorded headless with the server's own tools (simframerobot, simsetbackdrop, simrecordstart), driving the Allegro hand example. Each caption is the request and the tool call it became.

An MCP server that lets an AI agent (Claude Code, or any MCP client) drive a live, persistent Isaac Sim session and launch Isaac Lab training runs.

Kit takes tens of seconds to boot. If every experiment is a fresh launch, most of your time goes to waiting. Here Kit starts once inside a daemon and stays up. Each tool call lands in that running session, so changing a gain, stepping physics or taking a screenshot costs a frame, not a relaunch.

MCP client ──stdio──▶ dex_isaac_mcp (host, plain python)
                          │  newline-delimited JSON over a Unix socket
                          ▼
                       scripts/simd.py (Isaac Lab container, Kit stays up)
                          └─ one articulation, described by a robot JSON
  • Any articulated robot. Point it at a USD and a small JSON config. Franka and Allegro examples are included.
  • Normalized joint control. Targets are 0..1, where 0 is a joint's lower limit and 1 its upper limit, so agents don't need to know radians or meters.
  • Named poses per robot (home, fist, …), which can be blended part-way.
  • Headless capture and GIF recording from an auto-framed camera, with captions. The clip above was made this way.
  • Props: spawn a table, a ball or a USD into the running scene and read back where they settle.
  • Measurements: joint state, per-joint travel and tracking error, a range test that finds blocked joints, and parameter sweeps inside one session.
  • Training control: each run is a detached docker compose run. You can poll its status, TensorBoard scalars, checkpoints and logs.

How it differs from other Isaac Sim MCP servers

NVIDIA's official Isaac Sim MCP is a documentation search for coding assistants, and works well alongside this one. Servers like isaacsim-mcp-server and omni-mcp/isaac-sim-mcp run inside the Isaac Sim GUI and cover scene building broadly. This one runs headless, as a daemon in Docker, and focuses on tuning, measuring and training one robot.

Pick an in-GUI server to build a scene by talking to it, interactively, with a wide robot and asset library.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Isaac Sim robot workbench: common questions

Is Isaac Sim robot workbench MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Isaac Sim robot workbench safety report
How do I install Isaac Sim robot workbench?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Isaac Sim robot workbench need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is Isaac Sim robot workbench maintained?
The last commit was 32 days ago (2026-10-03). The latest release is v0.1.2.
What can I use instead of Isaac Sim robot workbench?
Servers from other publishers that do the same job: INSSIST MCP server, Argent MCP server and MCP Server for Excel.
How does Isaac Sim robot workbench compare with other Productivity MCP servers?
safety score 92/100 (higher than 90% of 1,299 Productivity servers); tools 36 (the typical Productivity server has 7); tools that change things 8% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Isaac Sim robot workbench

Same job from other publishers: the closest match first, then the best rated.

  • INSSIST
    Drive your own logged-in Instagram session via the INSSIST extension: read, publish, DMs, analytics.
    A
  • Argent
    Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
    A
  • MCP Server for Excel
    Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.
    A
  • gflow-cli
    Drive Google Flow from an agent: Veo video and Imagen image generation
    A
  • Buoy Gg
    Let AI agents read and drive a running React Native or Flutter app through Buoy's devtools.
    A