MCP App Store
by KeenEthics
Robotics Lab icon

Robotics Lab MCP Server for Claude and ChatGPT

By RQM Technologies LLC

Overview

Discover robotics analysis services, inspect required inputs and limitations, and run approved computations through an authenticated RQM account. Find services to check frame units, axes and transform conventions, validate trace timestamps, or assess a closed-loop model against supplied stability criteria. Discovery is free. Execution requires prepaid RQM credits and an account-owner spending policy; a Claude subscription does not fund jobs. Review inputs and the maximum price before execution. Retrieve saved results and receipts, or recover an existing purchase using its original idempotency key. Results are software and model evidence, not live robot control, physical calibration, or safety certification.

How to connect

  1. Claude: Open the Robotics Lab listing in the Claude connectors directory and choose Connect. Claude listing Robotics Lab exposes 6 tools here.
  2. ChatGPT: Open the Robotics Lab listing in the ChatGPT app directory and choose Connect. ChatGPT listing Robotics Lab exposes 12 tools here.

Tools

cancel_cloud_motion

ChatGPT
Request owner-authorized cancellation of the original motion job. Cancellation is complete only after worker termination is confirmed; keep the original job and reservation for recovery. Never starts a replacement job.

get_account_balance

ChatGPT
Read the connected RQM account's existing prepaid USD balance. This read does not purchase credits, reserve funds or grant permission to spend; balance alone does not establish saved policy readiness.

get_cloud_motion_approval

ChatGPT
Open a verified RQM account page for the human to review this exact motion request and maximum price. This read creates no approval or hold. After the human confirms on the account page, submit using the same quote, request and key; the bound consent is recovered automatically.

get_cloud_motion_artifact

ChatGPT
Read owner-scoped motion artifact. Modeled sphere validation is not physical safety certification or permission to actuate.

get_cloud_motion_receipt

ChatGPT
Read owner-scoped motion receipt. Modeled sphere validation is not physical safety certification or permission to actuate.

get_cloud_motion_result

ChatGPT
Read owner-scoped motion result. Modeled sphere validation is not physical safety certification or permission to actuate.

get_cloud_motion_status

ChatGPT
Read owner-scoped motion status. Modeled sphere validation is not physical safety certification or permission to actuate.

get_robotics_lab_capability

ChatGPT
Read the single supported NVIDIA cuRobo planning capability, request conventions and evidence limits. Creates no quote, hold, approval, execution or charge. This contract is not proof that a GPU has run.

quote_cloud_motion

ChatGPT
Quote one modeled Panda motion request against the connected RQM wallet. Creates a quote; does not reserve funds. Funding occurs outside this connector.

recover_cloud_reservation

ChatGPT
Find an uncertain wallet reservation using the original quote, request and stable key, including after expiry. Does not reserve or charge. A missing hold does not prove an in-flight request cannot still commit; preserve the original key.

resolve_cloud_motion

ChatGPT
Reconcile uncertain acceptance using the original request, reservation and key. May close admission and release a wallet hold; this is a mutation.

submit_cloud_motion

ChatGPT
Submit after a trusted human-confirmation receipt approves this exact account, quote, price, request and stable key. May reserve and charge existing RQM funds. Model approval flags do not grant consent.

get_account_balance

Claude
Read the connected account's prepaid USD balance before considering an account-funded job. A positive balance does not establish saved spending-policy readiness or permission for a particular purchase. Does not fund the account or authorize spending.

get_account_job

Claude
Read this agent's saved account-funded job by its returned job ID to check status and recover available result and receipt. Use after submission or when following up on an existing purchase; acceptance is not completion. Report the saved state and only available results, with their limitations. If the job ID was lost, use list_account_jobs with the original idempotency key first. Never authorizes another purchase.

list_account_jobs

Claude
List up to 100 recent jobs for this agent, or find the original account-funded purchase using its idempotency key. Use for purchase history and recovery before retrying an uncertain submission; use list_buyer_jobs or search_buyer_jobs for available services. Omit the key for recent history, or pass the exact original key to recover one purchase. Use a returned job ID with get_account_job for saved status, result and receipt. An empty response does not prove that a timed-out submission cannot still be accepted; preserve the original key and inputs on any retry. This read never purchases or reruns a job.

list_buyer_jobs

Claude
Inventory robotics service contracts when the user asks what is available. For a concrete task, use search_buyer_jobs instead. Read each descriptor's readiness, request schema, required inputs, examples, outputs and limitations before selecting its buyer service_id. The sibling account_execution_contracts map those IDs to run_account_job inputs and prerequisites; catalog readiness does not establish the connected account's saved spending-policy readiness. Examples explain the contract and are not substitutes for user data. Free discovery only: does not execute jobs, authorize spending or quote a binding price.

run_account_job

Claude
Purchase one discovered service using prepaid credits within the account owner's saved spending policy. First search_buyer_jobs for the task and inspect the selected request_schema, required inputs, limits, examples and evidence boundaries. Use its buyer service_id as capability_id; validate the user's inputs and ask for missing data rather than substituting an example. Set max_total_price to the caller-approved USD ceiling; discovery is not a binding quote and balance alone is not policy authorization. Acceptance or a queued job is not completion: retain the returned job ID and use get_account_job to read saved status, result and receipt. If submission times out or its outcome is uncertain, first recover with list_account_jobs using the original idempotency_key. Any retry must preserve the same key, capability, request and price ceiling; never create a new purchase or switch payment rails to recover. This tool never signs x402 or funds the account. Report only observed completion and findings within the service's evidence boundaries.

search_buyer_jobs

Claude
Find a robotics analysis service to check frame units, axes and transform conventions, validate trace timestamps, or assess a closed-loop model against supplied stability criteria. Returns buyer service IDs, exact inputs, examples, evidence boundaries and execution guidance. Software/model evidence only; not live robot control, physical calibration or safety certification. Free discovery; does not execute or purchase jobs.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/robotics-lab"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/robotics-lab)