# RQM Studio Jobs

> Delegate 20 fail-closed RQM Studio quantum work products with fixed-request x402.

- name: com.rqmtechnologies/studio
- version: 1.6.0
- connection class: R0 (autonomous)
- trust: 89/100 flags: duplicate-repo
- quality: 97/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.rqmtechnologies%2Fstudio
- tools: https://api.protogrid.dev/v1/servers/com.rqmtechnologies%2Fstudio/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "studio": {
      "type": "http",
      "url": "https://jobs.rqmtechnologies.com/mcp/studio"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-61d-ago -duplicate-repo(4 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 97/100 (strong)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 44 of 44 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- warn `tools.token_cost`: about 15,498 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 1 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 44, about 15,498 tokens to load them all
- tool set hash: 66feb077c117db304e0c4a45310ef162
- tools last changed: 2026-10-11T20:14:31.381Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.rqmtechnologies/studio.svg)](https://protogrid.dev/servers/com.rqmtechnologies/studio)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-11 `describe_quantum_capabilities` added
  - 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.

Full history: https://api.protogrid.dev/v1/servers/com.rqmtechnologies%2Fstudio/changes

## Remotes

- https://jobs.rqmtechnologies.com/mcp/studio (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (44)

- `audit_quantum_transformation`: Audit what another compiler or AI changed, and withhold the candidate unless preservation is verified.
- `cancel_job`: Request cancellation of one authorized product job.
- `check_quantum_circuit`: Check whether this quantum circuit is safe to send downstream, and return a bounded go, no-go, or unsupported decision with evidence.
- `classify_two_qubit_operation`: Classify this two-qubit operation by its nonlocal content and local-equivalence class.
- `compare_quantum_circuits`: Tell me whether these two quantum circuits implement the same operation within the stated phase context.
- `create_funding_session`: Create an idempotent Stripe Checkout URL for human prepaid funding.
- `describe_quantum_capabilities`: 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.
- `diagnose_quantum_phase`: Find the phase, rotation, ordering, or convention bug in this quantum operation.
- `diagnose_quantum_workflow`: Diagnose why this quantum workflow failed and return bounded corrective actions.
- `get_account_balance`: Read the authenticated canonical Account Core prepaid USD balance.
- `get_capability`: Return one full approved public Wave capability descriptor.
- `get_job_result`: Read one completed and already-settled product result.
- `get_job_status`: Read one authorized Wave or Studio managed-simulator job.
- `get_studio_receipt`: Retrieve the durable Account Core receipt for one settled Studio reservation.
- `list_buyer_jobs`: Return complete agent discovery contracts and readiness for the exact 20/20/20 RQM specialist work portfolio.
- `list_capabilities`: Describe the preserved v0/v1 surface or the dynamic v2/v3 Wave catalog.
- `optimize_quantum_circuit`: Make this quantum circuit smaller, but return the original unless equivalence is verified.
- `quantum_circuit_assurance_report_v1`: Problem: Validate, compile, and report bounded assurance evidence for OpenQASM 3. Input: JSON with source. Result: assurance outcome, warnings, normalized source and evidence. Limits: Local software evidence only; 3 verification qubits; 65536 source bytes.
- `quantum_cross_provider_portability_v1`: Problem: Translate this supported OpenQASM 3 circuit to the supplied local toolchain format without silent gate substitution. Input: JSON with source, target format. Result: translated target artifact, explicit gate mapping, source and artifact digests. Limits: Local software evidence only; 65536 source bytes.
- `quantum_execution_plan_select_v1`: Problem: Select a supported execution plan against the supplied cost, depth, duration limits, and weights. Input: JSON with plans, weights, maximum cost usd, maximum depth, maximum duration seconds. Result: ranked feasible plans, objective scores, selected plan identity. Limits: Local software evidence only; 4096 operations; 65536 request bytes.
- `quantum_failed_workflow_diagnosis_v1`: Problem: Diagnose why this bounded quantum workflow failed and return supported corrective actions. Input: JSON with stage, error text. Result: failure class, evidence terms, bounded corrective actions. Limits: Local software evidence only; 65536 request bytes.
- `quantum_gate_basis_decomposition_v1`: Problem: Decompose this supported circuit operation into the supplied bounded gate basis and verify the declared relation. Input: JSON with operation, target basis, phase context. Result: decomposition or withheld candidate, gate list, verification status. Limits: Local software evidence only; 65536 request bytes.
- `quantum_managed_simulator_v1`: Problem: Execute a bounded RQM Circuit IR circuit on the managed local statevector simulator. Input: JSON with circuit ir. Result: typed counts, probabilities, simulation configuration evidence. Limits: Local software evidence only; 16 qubits; 250 operations.
- `quantum_openqasm3_preflight_v1`: Problem: Parse, normalize, and assess OpenQASM 3 before downstream execution. Input: JSON with source. Result: go, no-go, or unsupported verdict, normalized source, warnings and evidence. Limits: Local software evidence only; 3 verification qubits; 65536 source bytes.
- `quantum_openqasm3_repair_v1`: Problem: Repair this bounded OpenQASM 3 program only with the supplied conservative repair policy. Input: JSON with source, allowed repairs. Result: repaired or withheld source, exact edit list, post-repair validation verdict. Limits: Local software evidence only; 65536 source bytes.
- `quantum_optimization_preservation_audit_v1`: Problem: Audit candidate optimization equivalence and qualitative coupling preservation. Input: JSON with original circuit, candidate circuit. Result: preserved or candidate-withheld outcome, input and output hashes, metric and.... Limits: Local software evidence only; 3 verification qubits; 65536 request bytes.
- `quantum_phase_aware_rewrite_v1`: Problem: Rewrite this supported circuit under the supplied phase-equivalence and target constraints. Input: JSON with operation, target gate, phase context. Result: rewritten operation or original, candidate withholding, verification status. Limits: Local software evidence only; 65536 request bytes.
- `quantum_phase_sensitive_inspection_v1`: Problem: Diagnose the phase, rotation, ordering, or convention difference between these supported operations. Input: JSON with reference, candidate, phase context. Result: difference kind, angle delta, correction hint. Limits: Local software evidence only; 65536 request bytes.
- `quantum_provider_readiness_check_v1`: Problem: Accept or reject this bounded circuit for the supplied pinned provider target and readiness rules. Input: JSON with qubit count, operations, target, rules. Result: readiness verdict, rule results and blockers, target provenance. Limits: Local software evidence only; 4096 operations; 65536 request bytes.
- `quantum_provider_result_compare_v1`: Problem: Compare these bounded provider results using the supplied normalization and difference rules. Input: JSON with left counts, right counts, normalization, rules. Result: normalized deltas, probability metrics, caller-rule verdict. Limits: Local software evidence only; 4096 operations; 65536 request bytes.
- `quantum_provider_target_compile_v1`: Problem: Compile this bounded circuit to the supplied pinned provider target and return compatibility evidence. Input: JSON with qubit count, operations, target. Result: compiled artifact, gate mapping, pinned target snapshot and blockers. Limits: Local software evidence only; 4096 operations; 65536 request bytes.
- `quantum_simulation_anomaly_diagnostic_v1`: Problem: Compare this bounded simulation result with the supplied expectation and anomaly rules. Input: JSON with observed probabilities, expected probabilities, maximum l1 error.... Result: L1 and bin deltas, violating outcomes, anomaly verdict. Limits: Local software evidence only; 65536 request bytes.
- `quantum_simulation_result_compare_v1`: Problem: Compare these bounded simulation results using the supplied deterministic probability rules. Input: JSON with left probabilities, right probabilities, rules. Result: probability deltas, distance metrics, threshold verdict. Limits: Local software evidence only; 4096 operations; 65536 request bytes.
- `quantum_supported_circuit_equivalence_v1`: Problem: Compare two RQM Circuit IR circuits within the supported verifier scope. Input: JSON with original circuit, candidate circuit. Result: equivalent, not-equivalent, or unsupported verdict, verification evidence, input.... Limits: Local software evidence only; 3 verification qubits; 65536 request bytes.
- `quantum_two_qubit_local_equivalence_v1`: Problem: Classify this supported two-qubit operation by its bounded local-equivalence class and phase context. Input: JSON with operation, phase context. Result: local-equivalence class, canonical coordinates, explicit phase treatment. Limits: Local software evidence only; 2 qubits.
- `quantum_two_qubit_target_synthesis_v1`: Problem: Choose and verify a bounded target-basis implementation for this supported two-qubit operation under supplied objectives. Input: JSON with operation, target basis, phase context, objectives. Result: verified circuit or original-retained outcome, gate count and depth, class and.... Limits: Local software evidence only; 2 qubits.
- `quantum_verified_circuit_optimization_v1`: Problem: Optimize RQM Circuit IR and return the original unless preservation is verified. Input: JSON with circuit. Result: verified candidate or original fallback, metric deltas, preservation evidence. Limits: Local software evidence only; 3 verification qubits; 65536 request bytes.
- `quote_job`: Return a preserved v0 placeholder or a durable v1 Account Core USD quote.
- `repair_openqasm3`: Repair this invalid OpenQASM 3 program conservatively, or tell me exactly why a safe repair cannot be made.
- `run_buyer_job`: Quote, settle, and submit one allowlisted WaveEngine, Studio, or Robotics buyer job using x402.
- `search_buyer_jobs`: Select RQM buyer jobs from work-language requests using deterministic semantic scoring over instructions, examples, outputs, and next steps.
- `submit_quantum_job`: Reserve an exact quote and submit one bounded managed-simulator job.
- `synthesize_two_qubit_target`: Choose the best verified target-native implementation of this two-qubit block.
- `translate_quantum_circuit`: Translate this circuit to Qiskit/OpenQASM 3 or Braket without silently changing its supported semantics.