RQM Jobs MCP server
com.rqmtechnologies/jobsrqmtechnologies.comstreamable-httpv1.6.0Scanned
Delegate 60 specialist work products: 20 WaveEngine, 20 RQM Studio, and 20 RQM Robotics jobs.
39 tools: 2 can delete or cancel things, 26 change things and 11 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- 10 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the RQM Jobs MCP server can do
The RQM Jobs MCP server is published by rqmtechnologies.com, a domain the MCP Registry verified. It has 39 tools. It can delete or cancel things (2 tools: run_account_job and cancel_job) and create or change data (26 tools: search_buyer_jobs, run_buyer_job, settle_buyer_job, robotics_frame_convention_validation_v1 and 22 more). 11 tools only read.
3 tools bring in text other people can write (describe_quantum_capabilities, run_account_job and create_funding_session).
The fixed checks matched 10 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 11, 2026, version 1.6.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
39 tools
Deletes or cancels 2Claude Code: deny
cancel_jobRequest cancellation of one authorized product job.1 finding
Why it is in this group
- The name "cancel_job" says "cancel": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.
Findings
- Warn
The server marks "cancel_job" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "cancel_job" says "cancel": a word for removing or ending something.
Description, as the server wrote it Request cancellation of one authorized product job.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
run_account_jobPurchase one discovered service using prepaid credits within the account owner's saved spending policy.Reads text others writeNo findings
Why it is in this group
- The name "run_account_job" says "run": a word for a change.
- The description's first verb is "purchase": a word that usually means money moves, which cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Run a job using prepaid RQM credits
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
Changes things 26Claude Code: ask
create_funding_sessionCreate an idempotent Stripe Checkout URL for human prepaid funding.Reads text others writeNo findings
Why it is in this group
- The name "create_funding_session" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Create an idempotent Stripe Checkout URL for human prepaid funding.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
robotics_analyze_force_disturbance_response_v1Problem: Analyze these bounded force and disturbance inputs against the supplied response model and criteria.1 finding
Why it is in this group
- The name "robotics_analyze_force_disturbance_response_v1" says "analyze": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "robotics_analyze_force_disturbance_response_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_analyze_force_disturbance_response_v1" says "analyze": a word for reading.
Description, as the server wrote it Problem: Analyze these bounded force and disturbance inputs against the supplied response model and criteria. Input: JSON with mass kg, damping n s per m, stiffness n per m, time step seconds.... Result: modeled response, metrics and rule results. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_assess_calibration_quality_v1Problem: Assess this bounded calibration dataset against the supplied residual, coverage, and consistency rules.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Assess this bounded calibration dataset against the supplied residual, coverage, and consistency rules. Input: JSON with length unit, observations, rules. Result: pass, fail, or indeterminate verdict, residual metrics, per-rule evaluations. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_check_collision_constraints_v1Problem: Check this bounded geometry and trajectory against the supplied collision and clearance constraints.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Check this bounded geometry and trajectory against the supplied collision and clearance constraints. Input: JSON with trajectory, obstacles, robot radius, minimum clearance. Result: clearance, collision candidates and constraint results. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_compare_controller_responses_v1Problem: Compare these bounded controller responses on identical traces using the supplied objective rules.1 finding
Why it is in this group
- The name "robotics_compare_controller_responses_v1" says "compare": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "robotics_compare_controller_responses_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_compare_controller_responses_v1" says "compare": a word for reading.
Description, as the server wrote it Problem: Compare these bounded controller responses on identical traces using the supplied objective rules. Input: JSON with baseline, candidate, rules. Result: metric values, threshold verdicts, difference series. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_compare_digital_twin_observations_v1Problem: Compare digital-twin output with mapped observations against caller tolerances.1 finding
Why it is in this group
- The name "robotics_compare_digital_twin_observations_v1" says "compare": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "robotics_compare_digital_twin_observations_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_compare_digital_twin_observations_v1" says "compare": a word for reading.
Description, as the server wrote it Problem: Compare digital-twin output with mapped observations against caller tolerances. Input: JSON with predicted, observed, declared mapping, rules. Result: typed verdict, measured metrics, candidate only when verified. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_compare_planned_observed_trajectories_v1Problem: Compare planned and observed trajectories against caller tolerances.1 finding
Why it is in this group
- The name "robotics_compare_planned_observed_trajectories_v1" says "compare": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "robotics_compare_planned_observed_trajectories_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_compare_planned_observed_trajectories_v1" says "compare": a word for reading.
Description, as the server wrote it Problem: Compare planned and observed trajectories against caller tolerances. Input: JSON with planned, observed, rules. Result: typed verdict, measured metrics, candidate only when verified. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_compare_state_estimators_v1Problem: Compare these bounded estimator outputs against the supplied reference and objective rules.1 finding
Why it is in this group
- The name "robotics_compare_state_estimators_v1" says "compare": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "robotics_compare_state_estimators_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_compare_state_estimators_v1" says "compare": a word for reading.
Description, as the server wrote it Problem: Compare these bounded estimator outputs against the supplied reference and objective rules. Input: JSON with reference, estimators, rules. Result: per-estimator metrics, rule verdicts, deterministic selected estimator or.... Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_compute_actuator_alignment_correction_v1Problem: Compute a bounded actuator alignment correction from these observations and caller acceptance limits.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Compute a bounded actuator alignment correction from these observations and caller acceptance limits. Input: JSON with observations, model, rules. Result: correction parameters, pre/post residuals, applicability verdict. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_diagnose_trajectory_instability_v1Problem: Diagnose this bounded trajectory for the supplied oscillation, divergence, and stability indicators.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Diagnose this bounded trajectory for the supplied oscillation, divergence, and stability indicators. Input: JSON with frame id, length unit, samples, rules. Result: pass, fail, or unsupported verdict, indicator series, violation windows. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_estimate_fused_state_v1Problem: Fuse these bounded synchronized sensor observations under the supplied diagonal uncertainty model and rules.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Fuse these bounded synchronized sensor observations under the supplied diagonal uncertainty model and rules. Input: JSON with observations, model, rules. Result: fused state, diagonal covariance, sensor residuals and verdict. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_frame_convention_validation_v1Problem: Validate this bounded frame graph and report unit, axis, handedness, rotation, and transform-direction violations.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Validate this bounded frame graph and report unit, axis, handedness, rotation, and transform-direction violations. Input: JSON with frames, declared length unit, declared transform direction, declared.... Result: pass, fail, or unsupported verdict, exact findings, normalized evidence. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_normalize_sensor_frames_v1Problem: Convert these bounded sensor observations into the supplied target frame and unit convention.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Convert these bounded sensor observations into the supplied target frame and unit convention. Input: JSON with frame graph, target frame id, observations. Result: normalized or unsupported verdict, normalized observations, transform paths. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_optimize_disturbance_rejection_v1Problem: Tune supported control parameters against this bounded disturbance model and supplied response objectives.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Tune supported control parameters against this bounded disturbance model and supplied response objectives. Input: JSON with mass, damping, disturbance, time step seconds, baseline kp, baseline.... Result: candidate parameters, comparative metrics and constraint results. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_optimize_trajectory_to_constraints_v1Problem: Optimize a bounded trajectory only when speed and duration constraints pass.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Optimize a bounded trajectory only when speed and duration constraints pass. Input: JSON with trajectory, maximum speed, maximum duration s. Result: typed verdict, measured metrics, candidate only when verified. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_reconstruct_smoothed_trajectory_v1Problem: Reconstruct this bounded trajectory under the supplied smoothing model and residual rule.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Reconstruct this bounded trajectory under the supplied smoothing model and residual rule. Input: JSON with samples, model, rules. Result: smoothed trajectory, residual RMSE, caller-rule verdict. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_replay_workcell_trace_v1Problem: Replay this bounded workcell trace against the supplied event assertions.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Replay this bounded workcell trace against the supplied event assertions. Input: JSON with model id, events, assertions. Result: timeline, assertion results and trace digest. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_tune_controller_to_objectives_v1Problem: Tune a supported controller only within supplied bounds and safety limits.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Problem: Tune a supported controller only within supplied bounds and safety limits. Input: JSON with supported controller, current gain, fixture error, target error.... Result: typed verdict, measured metrics, candidate only when verified. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_validate_closed_loop_stability_v1Problem: Accept or reject this bounded closed-loop model under the supplied stability criteria.1 finding
Why it is in this group
- The name "robotics_validate_closed_loop_stability_v1" says "validate": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "robotics_validate_closed_loop_stability_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_validate_closed_loop_stability_v1" says "validate": a word for reading.
Description, as the server wrote it Problem: Accept or reject this bounded closed-loop model under the supplied stability criteria. Input: JSON with discrete state matrix, criteria. Result: eigenvalues, spectral radius and rule results. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_validate_kinematic_dynamic_limits_v1Problem: Accept or reject a bounded trajectory against caller kinematic limits.1 finding
Why it is in this group
- The name "robotics_validate_kinematic_dynamic_limits_v1" says "validate": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "robotics_validate_kinematic_dynamic_limits_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_validate_kinematic_dynamic_limits_v1" says "validate": a word for reading.
Description, as the server wrote it Problem: Accept or reject a bounded trajectory against caller kinematic limits. Input: JSON with trajectory, maximum speed, maximum acceleration. Result: typed verdict, measured metrics, candidate only when verified. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
robotics_validate_trajectory_timing_v1Problem: Validate timestamps, ordering, rates, gaps, and synchronization in this bounded trajectory or sensor trace.1 finding
Why it is in this group
- The name "robotics_validate_trajectory_timing_v1" says "validate": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "robotics_validate_trajectory_timing_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_validate_trajectory_timing_v1" says "validate": a word for reading.
Description, as the server wrote it Problem: Validate timestamps, ordering, rates, gaps, and synchronization in this bounded trajectory or sensor trace. Input: JSON with clock id, samples, rules. Result: pass or fail verdict, normalized timeline, exact timing defects. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
run_buyer_jobQuote, settle, and submit one allowlisted WaveEngine, Studio, or Robotics buyer job using x402.No findings
Why it is in this group
- The name "run_buyer_job" says "run": a word for a change.
Description, as the server wrote it Quote, settle, and submit one allowlisted WaveEngine, Studio, or Robotics buyer job using x402.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_buyer_jobsSelect RQM buyer jobs from work-language requests using deterministic semantic scoring over instructions, examples, outputs, and next steps.1 finding
Why it is in this group
- The name "search_buyer_jobs" says "search": a word for reading.
- The description's first verb is "select": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "search_buyer_jobs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "search_buyer_jobs" says "search": a word for reading.
Description, as the server wrote it Select RQM buyer jobs from work-language requests using deterministic semantic scoring over instructions, examples, outputs, and next steps.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
settle_buyer_jobServer-side Jobs-rail x402 settle for connector hosts that cannot sign.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Server-side Jobs-rail x402 settle for connector hosts that cannot sign. Replays the same idempotency key with PAYMENT-SIGNATURE. An RQM-owned operator signer is not external revenue.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
submit_quantum_jobReserve an exact quote and submit one bounded managed-simulator job.No findings
Why it is in this group
- The name "submit_quantum_job" says "submit": a word for a change.
Description, as the server wrote it Reserve an exact quote and submit one bounded managed-simulator job.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
submit_wave_jobReserve an exact quote and submit one bounded catalog-approved Wave job.No findings
Why it is in this group
- The name "submit_wave_job" says "submit": a word for a change.
Description, as the server wrote it Reserve an exact quote and submit one bounded catalog-approved Wave job.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 11Show 11 read-only tools
describe_quantum_capabilitiesFree, anonymous API-owned scientific capability contracts and domain suggestions.Reads text others writeNo findings
Why it is in this group
- The name "describe_quantum_capabilities" says "describe": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Free, anonymous API-owned scientific capability contracts and domain suggestions. Start here before choosing or funding a quantum job. Inspect separate source, installed, hosted, simulator, live-QPU and public coverage; unknown means unverified. Read schemas, examples and limits; unavailable chemistry, cryptography or hybrid workflows must not be replaced with Bell or promised as execution. This finite registry is not the complete roadmap. Workflow tool references do not promise availability on this endpoint or eligibility for the caller. No account, balance, job, private policy, quote, reservation or hardware execution is accessed. Existing authenticated tools own those operations.
Annotations the server declares
- title: Discover RQM quantum capabilities and domain guidance
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_account_balanceRead the authenticated canonical Account Core prepaid USD balance.No findings
Why it is in this group
- The name "get_account_balance" says "get": a word for reading.
Description, as the server wrote it Read the authenticated canonical Account Core prepaid USD balance.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_account_jobRead this agent's saved account-funded job by its returned job ID to check status and recover available result and receipt.No findings
Why it is in this group
- The name "get_account_job" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Recover an account-funded job
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_capabilityReturn one full approved public Wave capability descriptor.No findings
Why it is in this group
- The name "get_capability" says "get": a word for reading.
Description, as the server wrote it Return one full approved public Wave capability descriptor.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_job_artifactRetrieve one principal-scoped bounded Wave result artifact.No findings
Why it is in this group
- The name "get_job_artifact" says "get": a word for reading.
Description, as the server wrote it Retrieve one principal-scoped bounded Wave result artifact.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_job_resultRead one completed and already-settled product result.No findings
Why it is in this group
- The name "get_job_result" says "get": a word for reading.
Description, as the server wrote it Read one completed and already-settled product result.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_job_statusRead one authorized Wave or Studio managed-simulator job.No findings
Why it is in this group
- The name "get_job_status" says "get": a word for reading.
Description, as the server wrote it Read one authorized Wave or Studio managed-simulator job.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_account_jobsList up to 100 recent jobs for this agent, or find the original account-funded purchase using its idempotency key.No findings
Why it is in this group
- The name "list_account_jobs" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Find this agent's purchases
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_buyer_jobsReturn complete agent discovery contracts and readiness for the exact 20/20/20 RQM specialist work portfolio.No findings
Why it is in this group
- The name "list_buyer_jobs" says "list": a word for reading.
Description, as the server wrote it Return complete agent discovery contracts and readiness for the exact 20/20/20 RQM specialist work portfolio.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_capabilitiesDescribe the preserved v0/v1 surface or the dynamic v2/v3 Wave catalog.No findings
Why it is in this group
- The name "list_capabilities" says "list": a word for reading.
Description, as the server wrote it Describe the preserved v0/v1 surface or the dynamic v2/v3 Wave catalog.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
quote_jobReturn a preserved v0 placeholder or a durable v1 Account Core USD quote.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return a preserved v0 placeholder or a durable v1 Account Core USD quote.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:46 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 29
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://jobs.rqmtechnologies.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://account.rqmtechnologies.com/oauth/chatgpt
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 29 tools that change things (2 destructive, 27 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://jobs.rqmtechnologies.com/mcp: tools/list returned 39 tools to an anonymous client, including run_account_job (destructive), cancel_job (destructive), describe_quantum_capabilities (write), search_buyer_jobs (write), run_buyer_job (write) and 24 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 28 to 29
Findings
Matches of fixed checks, with the text they matched.
The server marks "search_buyer_jobs" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "search_buyer_jobs" says "search": a word for reading.
The server marks "robotics_validate_trajectory_timing_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_validate_trajectory_timing_v1" says "validate": a word for reading.
The server marks "robotics_compare_controller_responses_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_compare_controller_responses_v1" says "compare": a word for reading.
The server marks "robotics_compare_state_estimators_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_compare_state_estimators_v1" says "compare": a word for reading.
The server marks "robotics_compare_planned_observed_trajectories_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_compare_planned_observed_trajectories_v1" says "compare": a word for reading.
The server marks "robotics_compare_digital_twin_observations_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_compare_digital_twin_observations_v1" says "compare": a word for reading.
Show 4 more findingsShow fewer
The server marks "robotics_validate_kinematic_dynamic_limits_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_validate_kinematic_dynamic_limits_v1" says "validate": a word for reading.
The server marks "robotics_validate_closed_loop_stability_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_validate_closed_loop_stability_v1" says "validate": a word for reading.
The server marks "robotics_analyze_force_disturbance_response_v1" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "robotics_analyze_force_disturbance_response_v1" says "analyze": a word for reading.
- Warncancel_job
The server marks "cancel_job" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "cancel_job" says "cancel": a word for removing or ending something.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 28 -> 29.View diff
- Tools that change things, listed without credentials: 28 to 29
Install
Pinned to version 1.6.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http jobs https://jobs.rqmtechnologies.com/mcpclaude mcp add --transport http jobs https://jobs.rqmtechnologies.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__jobs__describe_quantum_capabilities",
"mcp__jobs__get_account_job",
"mcp__jobs__list_account_jobs",
"mcp__jobs__list_buyer_jobs",
"mcp__jobs__list_capabilities",
"mcp__jobs__get_capability",
"mcp__jobs__quote_job",
"mcp__jobs__get_account_balance",
"mcp__jobs__get_job_status",
"mcp__jobs__get_job_result",
"mcp__jobs__get_job_artifact"
],
"ask": [
"mcp__jobs__search_buyer_jobs",
"mcp__jobs__run_buyer_job",
"mcp__jobs__settle_buyer_job",
"mcp__jobs__robotics_frame_convention_validation_v1",
"mcp__jobs__robotics_assess_calibration_quality_v1",
"mcp__jobs__robotics_diagnose_trajectory_instability_v1",
"mcp__jobs__robotics_validate_trajectory_timing_v1",
"mcp__jobs__robotics_normalize_sensor_frames_v1",
"mcp__jobs__robotics_reconstruct_smoothed_trajectory_v1",
"mcp__jobs__robotics_estimate_fused_state_v1",
"mcp__jobs__robotics_compute_actuator_alignment_correction_v1",
"mcp__jobs__robotics_compare_controller_responses_v1",
"mcp__jobs__robotics_compare_state_estimators_v1",
"mcp__jobs__robotics_compare_planned_observed_trajectories_v1",
"mcp__jobs__robotics_compare_digital_twin_observations_v1",
"mcp__jobs__robotics_tune_controller_to_objectives_v1",
"mcp__jobs__robotics_optimize_trajectory_to_constraints_v1",
"mcp__jobs__robotics_validate_kinematic_dynamic_limits_v1",
"mcp__jobs__robotics_optimize_disturbance_rejection_v1",
"mcp__jobs__robotics_validate_closed_loop_stability_v1",
"mcp__jobs__robotics_check_collision_constraints_v1",
"mcp__jobs__robotics_replay_workcell_trace_v1",
"mcp__jobs__robotics_analyze_force_disturbance_response_v1",
"mcp__jobs__create_funding_session",
"mcp__jobs__submit_wave_job",
"mcp__jobs__submit_quantum_job"
],
"deny": [
"mcp__jobs__run_account_job",
"mcp__jobs__cancel_job"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as jobs. Review it before you use it.
Capability tags behind 3 rules
- mcp__jobs__describe_quantum_capabilities untrusted-input
- mcp__jobs__run_account_job untrusted-input
- mcp__jobs__create_funding_session untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.rqmtechnologies/jobs/verify?hash=7d70b2e8fcb788f12c661c6613bdcb94b4637f6a514039d87dd6a88872bb5696" | jq -e '.changed == false'Pinned hash 7d70b2e8fcb7, from Nov 11, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.rqmtechnologies/jobs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.rqmtechnologies/jobs)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:02 UTC.
RQM Jobs MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the RQM Jobs MCP server safe?
- No scan can promise that. What its definitions show: 39 tools, 28 of which can change, send or delete something, and 10 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the RQM Jobs MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: run_account_job and cancel_job.
Can the RQM Jobs MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the RQM Jobs MCP server have?
- 39 tools: 2 destructive, 26 write, 11 read. run_account_job, cancel_job, search_buyer_jobs, run_buyer_job, settle_buyer_job, robotics_frame_convention_validation_v1, robotics_assess_calibration_quality_v1, robotics_diagnose_trajectory_instability_v1 and 31 more.
Does the RQM Jobs MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the RQM Jobs MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the RQM Jobs MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.