MCP server that wraps the Dagster GraphQL API — manage runs, assets, schedules, sensors, and backfills from any MCP client
Nothing to run from here
Isaac Sim robot workbench is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
80
downloads in 30d
local
runs on your machine
36
tools declared
What it does
Drive a live Isaac Sim session: any robot, poses, gain tuning, range tests, Isaac Lab training.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'ISAAC_MCP_HOME=${ISAAC_MCP_HOME}' --transport stdio isaac-sim-robot-workbench-mcp '--' uvx dex-isaac-mcp
# 2 — ask your agent for something these tools do
# sim_status, sim_up, sim_down and 33 more
It needs ISAAC_MCP_HOME: this reads it from your environment, so export it first.
Isaac Sim robot workbench costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MIAll 1 server
Milokucia1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Isaac Sim robot workbench as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads ISAAC_MCP_HOME (Path to a clone of github.com/Milokucia/dex-isaac-mcp; the Isaac Sim daemon runs from its docker/ directory) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx ISAAC_MCP_HOME … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'ISAAC_MCP_HOME=${ISAAC_MCP_HOME}' --transport stdio isaac-sim-robot-workbench-mcp '--' uvx dex-isaac-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs settings only you can give it: ISAAC_MCP_HOME — Path to a clone of github.com/Milokucia/dex-isaac-mcp; the Isaac Sim daemon runs from its docker/ directory. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
36 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Report whether the sim daemon is up, its robot, driven joints, poses and parameters.
No parameter schema on file.
No parameter schema on file.
Stop the sim daemon; its container removes itself.
No parameter schema on file.
Restart the daemon to change a spawn property: robot, USD, solver iterations, self-collision.
No parameter schema on file.
List a USD's articulation DOFs, joints excluded from the articulation (loop closures), and roots.
No parameter schema on file.
Joint positions (rad/m) and velocities, plus driven joints' normalized positions and limits.
No parameter schema on file.
Per-joint travel and driven-joint mean tracking error since the last reset.
No parameter schema on file.
Command the driven joints, normalized 0..1 (lower..upper limit).
No parameter schema on file.
Named poses from the robot config, as {pose: {joint_pattern: 0..1}}.
No parameter schema on file.
Command a named pose. amount blends toward it: 1 = as authored, 0.5 = halfway.
No parameter schema on file.
Advance the simulation n physics steps (dt from sim_status, default 1/120 s).
No parameter schema on file.
Run the sim continuously in real time (True) or pause it (False).
No parameter schema on file.
Sweep every driven joint through its range for n steps; return travel stats.
No parameter schema on file.
Drive every driven joint from its lower limit toward target, report the fraction reached.
No parameter schema on file.
Change the driven joints' PD gains and effort limit on the live articulation.
No parameter schema on file.
Change software-coupling ratios live, keyed by follower joint. 0 releases a follower.
No parameter schema on file.
No parameter schema on file.
Every spawned prop with its current world pose (pos in m, rot as w, x, y, z).
No parameter schema on file.
Delete a spawned prop.
No parameter schema on file.
Point the viewport camera, e.g. eye=[1.2, 1.2, 1.0] target=[0, 0, 0.3].
No parameter schema on file.
Capture the viewport as an image. Requires the daemon started with gui=True.
No parameter schema on file.
Aim the capture camera so the whole robot fills the frame.
No parameter schema on file.
Place the capture camera by hand (sim_frame_robot does it automatically).
No parameter schema on file.
Put a plain panel (RGB 0..1) behind the robot, facing the capture camera; no color removes it.
No parameter schema on file.
A frame from the capture camera. Works headless; no GUI or viewport needed.
No parameter schema on file.
Start recording the capture camera: one frame every every physics steps.
No parameter schema on file.
Change the caption drawn on frames recorded from now on ('' for none).
No parameter schema on file.
Stop recording and write an animated GIF; returns its path on the host.
No parameter schema on file.
Compare several values of one live parameter inside the single session.
No parameter schema on file.
Launch a headless Isaac Lab training run in its own container; returns at once.
No parameter schema on file.
List training runs: live or recent containers, and log directories holding checkpoints.
No parameter schema on file.
Container state, checkpoints, and latest TensorBoard scalar values for one run.
No parameter schema on file.
Tail a running training container's stdout/stderr.
No parameter schema on file.
Stop a training run's container.
No parameter schema on file.
List a run's saved checkpoints with step and size.
No parameter schema on file.
TensorBoard scalars for a run: no tag lists tag names; a tag returns its series, downsampled.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Isaac Sim robot workbench or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.1.2 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings2 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest9eda367dcf61af77a025b9dfd30a63c96fc40aa1ca01063fe1ce38da9639e53f
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (36 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| sim_status | no tags | |
| sim_up | no tags | |
| sim_down | no tags | |
| sim_reload | no tags | |
| sim_inspect_joints | no tags | |
| sim_get_joint_state | no tags | |
| sim_get_stats | no tags | |
| sim_set_targets | no tags | |
| sim_list_poses | no tags | |
| sim_set_pose | no tags | |
| sim_step | no tags | |
| sim_play | no tags | |
| sim_wave | no tags | |
| sim_range_test | no tags | |
| sim_set_params | no tags | |
| sim_set_coupling | no tags | |
| sim_spawn_object | no tags | |
| sim_list_objects | no tags | |
| sim_remove_object | no tags | |
| sim_set_camera | no tags | |
| sim_screenshot | no tags | |
| sim_frame_robot | no tags | |
| sim_set_capture_camera | no tags | |
| sim_set_backdrop | no tags | |
| sim_capture | no tags | |
| sim_record_start | no tags | |
| sim_record_caption | no tags | |
| sim_record_stop | no tags | |
| sim_sweep | no tags | |
| train_start | no tags | |
| train_list | no tags | |
| train_status | no tags | |
| train_logs | no tags | |
| train_stop | no tags | |
| train_checkpoints | no tags | |
| train_metrics | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest9eda367dcf61af77
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.2. Pin a release below and the command asks for exactly that one.
0.1.2
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Isaac Sim robot workbench can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.