# Privi Quantum (remote · privi-quantum-vvmj.onrender.com)

Quantum on IonQ/IBM/Braket: spending mandates, signed benchmarks, paid PQC CBOM, advantage receipts.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `privi-quantum-vvmj.onrender.com`: 65/100 (this document), [markdown](https://verifymcp.io/servers/canoydario847-cloud-privi-quantum/privi-quantum-vvmj.md), [page](https://verifymcp.io/servers/canoydario847-cloud-privi-quantum/privi-quantum-vvmj)

## Channel facts

- Endpoint: `https://privi-quantum-vvmj.onrender.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.13.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (quantum_mandate_revoke).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 11050 tokens (~155/item across 71 items; 71 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 96% of tool parameters carry a description.
  - Structured output schemas are declared (13% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 72 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Privi Quantum MCP server?

Privi Quantum is a hosted endpoint at https://privi-quantum-vvmj.onrender.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http canoydario847-cloud-privi-quantum 'https://privi-quantum-vvmj.onrender.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "canoydario847-cloud-privi-quantum": {
      "url": "https://privi-quantum-vvmj.onrender.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "canoydario847-cloud-privi-quantum": {
      "type": "http",
      "url": "https://privi-quantum-vvmj.onrender.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.canoydario847-cloud-privi-quantum]
url = "https://privi-quantum-vvmj.onrender.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "canoydario847-cloud-privi-quantum": {
      "type": "remote",
      "url": "https://privi-quantum-vvmj.onrender.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add canoydario847-cloud-privi-quantum --url 'https://privi-quantum-vvmj.onrender.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  canoydario847-cloud-privi-quantum:
    url: "https://privi-quantum-vvmj.onrender.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "canoydario847-cloud-privi-quantum": {
      "Transport": "http",
      "Url": "https://privi-quantum-vvmj.onrender.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add canoydario847-cloud-privi-quantum -t streamable-http -u 'https://privi-quantum-vvmj.onrender.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "canoydario847-cloud-privi-quantum": {
      "type": "http",
      "url": "https://privi-quantum-vvmj.onrender.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 65, +1)

- [functional] New tool “quantum_hardware_evidence”
- [functional] New tool “quantum_evidence_lab”
- [functional] New tool “car_smartcar_sync”

### 2026-11-19 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 62, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-15 (score 62)

First indexed and scored.

## MCP tools (71)

### `quantum_status` (~30 tokens)

Privi Quantum status

What this server runs: algorithm, qubit limit, quantum backends, signing keys, and anchoring.

### `quantum_pricing` (~54 tokens)

Privi Quantum pricing

Which tools are paid, their price per call, how to pay (x402: USDC on Base, or the PRIVI token), and the
payout wallet ($0.001). Failed calls are never charged.

### `quantum_problems` (~28 tokens)

List optimization problems

The ready-made problems quantum_optimize accepts and the data each one needs, with an example.

### `quantum_evidence_lab` (~180 tokens)

Quantum Evidence Lab

Independent simulator evidence for QAOA vs QASM. Reproducible SHA-256 receipt,
exact classical optimum and optional sampling diagnostics. This free
scientific preview does NOT run an IBM QPU or prove quantum advantage.

Input parameters:

- `Q` (array, required): QUBO matrix Q; maximum 10x10. Minimize x^T Q x + offset.
- `betas` (array, required): Trained QAOA mixer angles, one per layer (1-4).
- `counts`: Optional user-supplied bitstring counts, marked unverified.
- `gammas` (array, required): Trained QAOA cost angles, one per layer (1-4).
- `offset` (number): QUBO additive constant.
- `qasm`: Optional OpenQASM 2 circuit to audit; otherwise verify the exporter itself.

### `quantum_hardware_evidence` (~234 tokens)

Quantum Hardware Evidence

Offline analysis of QAOA, compiled QASM, and empirical samples. No provider
calls, no QPU charges, no job verification or quantum advantage claim.

Input parameters:

- `Q` (array, required): QUBO matrix, max 10x10.
- `backend` (string, required): Self-reported backend identifier.
- `betas` (array, required): QAOA beta angles.
- `compiled_qasm` (string, required): Backend-compiled OpenQASM 2 in h/rx/rz/cx basis.
- `completed_utc` (string, required): ISO UTC completion timestamp.
- `counts` (object, required): Unverified bitstring count data.
- `gammas` (array, required): QAOA gamma angles.
- `offset` (number): QUBO additive cost.
- `provider` (string, required): Self-reported provider identifier.
- `provider_job_id` (string, required): Self-reported provider job ID; not independently authenticated.
- `shots` (integer, required): Reported shot count.
- `source_qasm` (string, required): Original OpenQASM 2 circuit.
- `submitted_utc` (string, required): ISO UTC submission timestamp.

### `quantum_optimize` (~196 tokens)

Quantum optimize

Solve a factory decision with the Quantum Approximate Optimization Algorithm. Returns the decision in
plain terms, how close it is to the proven optimum, and a post-quantum signed attestation (Ed25519 +
ML-DSA-87) that is anchored on chain (Base). Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `data` (object, required): Problem data in the shape quantum_problems describes
- `include_qasm` (boolean): Also return the trained circuit as OpenQASM 2.0 for real quantum hardware
- `layers` (integer): QAOA depth p (1-4). Deeper finds better answers more often but runs longer.
- `problem` (string, required): balance_lines | select_lots | split_conflicts | qubo (see quantum_problems)
- `shots` (integer): Measurements to sample from the trained circuit (1-100000)

### `quantum_verify` (~89 tokens)

Verify a Privi Quantum attestation

Check both post-quantum signatures, the body hash, and the on-chain anchor of a result. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `attestation`: Or a full attestation object (from GET /attestations/<id>) to check offline
- `attestation_id`: An attestation id (qa_...) issued by this server

### `pqc_scan_code` (~96 tokens)

Scan code for quantum-vulnerable crypto

Find RSA, elliptic-curve, Diffie-Hellman, DSA, weak hashes and 128-bit ciphers that quantum
computers break or weaken; returns a 0-100 readiness score and a fix per finding. Nothing is stored.

Input parameters:

- `code` (string, required): Source code or config text to scan (max 200 KB)
- `filename` (string): Optional file name, used in the report

### `pqc_readiness_package` (~411 tokens)

Post-quantum readiness package (government)

Build a signed post-quantum readiness package: prioritized migration list with the federal deadline for
each asset (EO 14409, OMB M-26-15, NIST IR 8547 draft, CNSA 2.0), the nine M-26-15 plan elements marked as
evidence or gaps, and a CycloneDX 1.6 CBOM. Signed with ML-DSA-87, anchored on chain, public report URL.
Paid per call via x402 when payments are on (see quantum_pricing); failed calls are not charged.

Input parameters:

- `assets`: Cryptographic assets: [{system, asset, algorithm, usage (key_establishment|signature|encryption|tls|ssh|vpn|code_signing|certificate|hash|other), protocol (e.g. 'TLS 1.2'), impact (high|moderate|low)…
- `endpoints`: Public hostnames to check live for TLS 1.3 and hybrid post-quantum key exchange (up to 20), e.g. ['www.agency.gov']
- `files`: Code or config files to scan: [{name, content}] (up to 50 files, 1 MB)
- `hva` (boolean): Is that system a High Value Asset (M-19-03)?
- `impact` (string): FIPS 199 impact of that system: high | moderate | low
- `organization` (string, required): Agency, office or company name
- `pqc_lead` (string): Name of the PQC Migration Lead (M-26-15 governance)
- `profile` (string): agency (OMB M-26-15) | contractor (EO 14409 FAR items) | nss_vendor (NSA CNSA 2.0)
- `system_name` (string): System the scanned files belong to

### `pqc_endpoint_check` (~139 tokens)

Check public endpoints for post-quantum TLS

Test live public sites and services for TLS 1.3 and hybrid post-quantum key exchange (X25519MLKEM768,
FIPS 203), the protection against 'harvest now, decrypt later'. Sends two TLS hellos per endpoint and no data.
Returns a status and fix per endpoint plus CBOM-ready assets for pqc_readiness_package. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `endpoints` (array, required): Public hostnames or URLs (up to 20), optionally with a TLS port, e.g. ['www.irs.gov', 'login.gov:443']

### `pqc_federal_deadlines` (~80 tokens)

Federal post-quantum deadlines

The U.S. federal post-quantum timeline (EO 14409, OMB M-26-15, NIST IR 8547 draft, NSA CNSA 2.0), the
approved replacement algorithms, and links to the sources. Paid per call via x402 when payments are on (see quantum_pricing).

### `quantum_advantage_receipt` (~191 tokens)

Quantum Advantage Receipt

Race the quantum answer against classical baselines (exhaustive search = proven optimum, and simulated
annealing) on the same problem and seal the result as a signed, chain-anchored Quantum Advantage Receipt:
answer quality and time for each side and a verdict (quantum_won / classical_won / tie), published whichever
side wins. For a real-hardware receipt use quantum_run_hardware. Paid per call via x402 when payments are on
(see quantum_pricing); failed calls are not charged.

Input parameters:

- `data` (object, required): Problem data in the shape quantum_problems describes
- `layers` (integer): QAOA depth p (1-4)
- `problem` (string, required): balance_lines | select_lots | split_conflicts | qubo (see quantum_problems)
- `shots` (integer): Measurements from the trained circuit (1-100000)

### `quantum_backends` (~65 tokens)

Quantum hardware backends

Every quantum backend this server can route to (local simulator, IonQ, IBM Quantum, Amazon Braket),
whether it is usable now, its estimated price, measured turnaround, and the hardware budget. Paid per call via x402 when payments are on (see quantum_pricing).

### `quantum_run_hardware` (~360 tokens)

Run on quantum hardware

Train the CVaR-QAOA circuit, route it to a quantum backend (IonQ, IBM Quantum, Amazon Braket or this
server's simulator) by price or speed, and return a job id. When the run finishes, the answer is sealed with a
post-quantum signed attestation and a Quantum Advantage Receipt against classical baselines. Poll with
quantum_hardware_job. Paid per call via x402 when payments are on (a routing fee, see quantum_pricing). Paid
QPUs also need a Quantum Mandate signed by the agent's human (quantum_mandate_request) and run only within the
operator's configured budget. A call that is blocked or fails to submit is not charged.

Input parameters:

- `backend` (string): 'auto' or a backend id from quantum_backends (e.g. ionq:simulator, ionq:qpu.forte-1, ibm:ibm_brisbane)
- `data` (object, required): Problem data in the shape quantum_problems describes
- `layers` (integer): QAOA depth p (1-4)
- `mandate_id`: qm_... Quantum Mandate your human signed; required for any paid backend
- `max_cost_usd`: Refuse if the estimated price is above this
- `policy` (string): With backend='auto': cheapest | fastest | hardware (real QPUs only)
- `privi_pass`: Your Privi pass (ppass_...); required with a mandate
- `problem` (string, required): balance_lines | select_lots | split_conflicts | qubo (see quantum_problems)
- `shots` (integer): Shots on the backend (1-10000)

### `quantum_hardware_job` (~70 tokens)

Quantum hardware job

Status of a quantum hardware job; once done, the decision, measurement statistics, the signed attestation and
the Quantum Advantage Receipt. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `job_id` (string, required): hw_... id from quantum_run_hardware

### `quantum_mandate_request` (~224 tokens)

Quantum Mandate: request one

Draft a Quantum Mandate: the spending terms under which this agent may run paid quantum hardware jobs.
Returns a sign_url for the person who approved the agent; they sign the exact terms with their passkey. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `backends`: Allowed backend ids from quantum_backends (default: any paid backend)
- `budget_usd` (number, required): Total the agent may spend on paid quantum hardware under this mandate
- `days` (integer): How long the mandate lasts once signed (1-365)
- `max_per_job_usd`: Most one job may cost (default: the whole budget)
- `max_shots` (integer): Most shots per job (1-10000)
- `privi_pass`: Your Privi pass (ppass_...) from inspector_pass; the quantum realm requires one
- `problems`: Allowed problems (default: any)
- `purpose` (string, required): What the runs are for, in plain words (shown to the person who signs)

### `quantum_mandate_status` (~67 tokens)

Quantum Mandate: status

A Quantum Mandate's terms, status (draft, active, expired, revoked), spend, remaining budget and every
charge and refund. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `mandate_id` (string, required): qm_... id

### `quantum_mandate_check` (~116 tokens)

Quantum Mandate: dry run

Would this paid run be allowed under the mandate? Picks the backend the router would use, estimates the
price and checks it against every term without spending anything. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `backend` (string): 'auto' or a backend id
- `mandate_id` (string, required): qm_... id
- `policy` (string): cheapest | fastest | hardware
- `problem` (string): Problem you plan to run
- `shots` (integer)

### `quantum_mandate_revoke` (~117 tokens)

Quantum Mandate: revoke (agent)

The agent gives up its own mandate (the person can also revoke on the mandate page with their passkey).
The revocation is signed and anchored. Paid per call via x402 when payments are on; the person who signed it can also revoke it on the mandate web page with their passkey.

Input parameters:

- `mandate_id` (string, required): qm_... id
- `privi_pass`: Your Privi pass (ppass_...) from inspector_pass; the quantum realm requires one
- `reason` (string): Why

### `quantum_run_circuit` (~327 tokens)

Run your own circuit (Qiskit / OpenQASM)

Bring your own quantum circuit. Paste the OpenQASM that Qiskit writes and Privi runs it on IBM Quantum, IonQ,
Amazon Braket or its own simulator, picked by price or speed, then seals the measurement counts with a
post-quantum signature anchored on chain. Standard Qiskit gates are rewritten exactly into h, rz, rx, cx; all
qubits are measured at the end. Poll with quantum_hardware_job. Free on free backends; paid QPUs need a
Quantum Mandate.

Input parameters:

- `backend` (string): 'auto' or a backend id from quantum_backends (local, ionq:simulator, ionq:qpu.forte-1, ibm:<name>, braket:<name>)
- `label` (string): Optional short name for the run (kept in the sealed record)
- `mandate_id`: qm_... Quantum Mandate (required for paid backends)
- `max_cost_usd`: Refuse if the estimated price is above this
- `policy` (string): With backend='auto': cheapest | fastest | hardware (real QPUs only)
- `privi_pass`: Your Privi pass (ppass_...); required with a mandate
- `qasm` (string, required): OpenQASM 2.0 or 3.0 text, e.g. from Qiskit: qiskit.qasm2.dumps(circuit) or qiskit.qasm3.dumps(circuit)
- `shots` (integer): Shots (1-10000)

### `pqc_crypto_inventory` (~290 tokens)

Crypto inventory (CBOM) for a company

Point Privi at a company's domains and GitHub repositories and get one cryptographic bill of materials: every
algorithm quantum computers will break, where it is, a prioritized migration plan with dates, a CycloneDX 1.6
CBOM and a public report page, signed with ML-DSA-87 and anchored on chain. Repos are scanned in memory and not
kept. Paid per call via x402 when payments are on (see quantum_pricing); failed calls are not charged.

Input parameters:

- `assets`: Known cryptographic assets (same shape as pqc_readiness_package)
- `domains`: Public hostnames to test live for TLS 1.3 and hybrid post-quantum key exchange (up to 20)
- `files`: Extra code or config files: [{name, content}] (up to 50 files, 1 MB)
- `long_lived_data` (boolean): Do these systems protect data that must stay secret past 2030? Raises priority (harvest now, decrypt later)
- `organization` (string, required): Company or agency name
- `profile` (string): company (NIST IR 8547 dates) | agency | contractor | nss_vendor
- `repos`: Public GitHub repositories to scan, e.g. ['https://github.com/acme/api', 'acme/web'] (up to 5)

### `vault_keygen` (~121 tokens)

Privi Vault: new hybrid post-quantum key

Create a hybrid X25519 + ML-KEM (FIPS 203) key pair for Privi Vault. The private key is returned once and not
stored here; for the strongest setup generate it locally with `python -m privi_quantum.vault keygen`. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `suite` (string): X25519+ML-KEM-768 (default) | X25519+ML-KEM-1024 (CNSA 2.0 KEM level)

### `vault_seal` (~159 tokens)

Privi Vault: seal data (harvest-now-decrypt-later protection)

Re-wrap long-lived sensitive data under hybrid post-quantum encryption (X25519 + ML-KEM, AES-256-GCM) so data
recorded today can't be decrypted by a future quantum computer. Returns the envelope and a signed protection
receipt anchored on chain. Plaintext is not stored. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `data_base64`: Or bytes to protect, base64 (up to 5 MB)
- `label` (string): What this is, e.g. 'supplier contract 2026' (kept in the envelope and receipt)
- `public_key` (object, required): Recipient public key from vault_keygen
- `text`: Text to protect

### `vault_open` (~84 tokens)

Privi Vault: open an envelope

Decrypt a Privi Vault envelope. Nothing is stored; for sensitive data prefer opening locally with
\`python -m privi_quantum.vault open`. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `envelope` (object, required): A Privi Vault envelope
- `private_key` (object, required): The recipient private key from vault_keygen

### `vault_receipt` (~112 tokens)

Privi Vault: receipt for a locally sealed envelope

Get a signed, chain-anchored protection receipt proving data was under hybrid post-quantum encryption by a
given time, for envelopes sealed with the local Privi Vault tool. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `envelope`: An envelope sealed locally (checked for structure; nothing is decrypted)
- `envelope_sha256`: Or only the envelope's SHA-256, so the envelope never leaves your machine
- `label` (string): What this protects

### `privilege_directory` (~67 tokens)

Privilege: quantum realm directory

Every quantum realm Privi can run a job on (engines on this server and other Privi Quantum nodes),
ranked by expected time to the proven optimum, with latency, optimum rate, wins and status. Paid per call via x402 when payments are on (see quantum_pricing).

### `privilege_benchmark` (~90 tokens)

Privilege: benchmark the realms

Run the standard 8-qubit benchmark on every active realm at once and update Privilege's speed
rankings. At most once every 2 minutes for everyone. Requires a Privi pass. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `privi_pass`: Your Privi pass (ppass_...) from inspector_pass; the quantum realm requires one

### `dreamweaver_run` (~278 tokens)

Dream Weaver: race a quantum job across realms

Run one quantum optimization on several realms at once and return the winning answer, every realm's
timing, and a post-quantum signed attestation (Ed25519 + ML-DSA-87) anchored on chain. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `data` (object, required): Problem data in the shape quantum_problems describes
- `deadline_s` (number): Give up after this many seconds (1-120)
- `fanout` (integer): How many realms to use (1-8), fastest first
- `hedge_ms` (integer): first mode: start the top realm alone, add the others after this many ms (or as soon as one fails). 0 = all at once
- `layers` (integer): QAOA depth p (1-4)
- `mode` (string): first = fastest valid answer wins; best = best answer by the deadline
- `privi_pass`: Your Privi pass (ppass_...) from inspector_pass; the quantum realm requires one
- `problem` (string, required): balance_lines | select_lots | split_conflicts | qubo (see quantum_problems)
- `realms`: Only these realm_ids (from privilege_directory)
- `shots` (integer): Measurements (1-100000)

### `dreamscape_open` (~104 tokens)

Dream Scape: open a workspace

Open a private Dream Scape: your own quantum environment that keeps every job and result. Returns
scape_id and scape_key (shown once; keep it). Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `name` (string, required): A name for your workspace, e.g. 'Plant 2 scheduling'
- `privi_pass`: Your Privi pass (ppass_...) from inspector_pass; the quantum realm requires one

### `dreamscape_submit` (~182 tokens)

Dream Scape: run a job

Run a quantum job in your Dream Scape through Dream Weaver and keep the result there. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `data` (object, required): Problem data (see quantum_problems)
- `deadline_s` (number)
- `fanout` (integer)
- `hedge_ms` (integer)
- `layers` (integer)
- `mode` (string): first or best
- `privi_pass`: Your Privi pass (ppass_...) from inspector_pass; the quantum realm requires one
- `problem` (string, required): balance_lines | select_lots | split_conflicts | qubo
- `scape_id` (string, required): Your Dream Scape id (scape_...)
- `scape_key` (string, required): Its key (dsk_...)
- `shots` (integer)

### `dreamscape_jobs` (~114 tokens)

Dream Scape: jobs

Your Dream Scape's recent jobs, or one job with its full result. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `job_id`: One job in full; omit for the recent list
- `limit` (integer)
- `privi_pass`: Your Privi pass (ppass_...) from inspector_pass; the quantum realm requires one
- `scape_id` (string, required): Your Dream Scape id
- `scape_key` (string, required): Its key

### `accelerator_info` (~69 tokens)

Quantum Agent Accelerator: how it works

The program that upgrades an AI agent into a certified quantum agent: the four steps (Q1-Q4), the
levels, how to make an ML-DSA key in five lines, and the free directory checks. Paid per call via x402 when payments are on (see quantum_pricing).

### `qagent_enroll` (~161 tokens)

Quantum Agent: enroll

Join the Quantum Agent Accelerator. Returns agent_id and agent_token (shown once; keep it) and your
upgrade plan. Your public key goes in the directory so other agents can verify what you sign. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `homepage` (string): Optional https:// page about the agent
- `listed` (boolean): Show this agent in the public Quantum Agent Directory
- `name` (string, required): Your agent's name
- `operator` (string, required): The company or person accountable for this agent
- `public_key` (string, required): Base64 of your raw ML-DSA-44/65/87 public key (FIPS 204). accelerator_info shows how to make one

### `qagent_scan` (~130 tokens)

Quantum Agent: scan (Q1 code, Q3 endpoints)

Q1: scan your code for quantum-vulnerable cryptography (passing means you ran the scan; the score and
findings tell you what to fix). Q3: check that every public endpoint you run negotiates X25519MLKEM768.

Input parameters:

- `agent_id` (string, required): Your agent_id (qagent_...)
- `agent_token` (string, required): Your agent_token
- `code`: Your agent's code or config (max 200 KB) for Q1
- `endpoints`: Your public hostnames for Q3 (all must use hybrid post-quantum TLS)

### `qagent_challenge` (~53 tokens)

Quantum Agent: get a signing challenge (Q2)

Get a one-time message to sign with your ML-DSA private key (valid 10 minutes).

Input parameters:

- `agent_id` (string, required): Your agent_id
- `agent_token` (string, required): Your agent_token

### `qagent_prove` (~87 tokens)

Quantum Agent: prove your post-quantum key (Q2)

Send the signed challenge. A valid signature proves you hold the key in the directory: step Q2.

Input parameters:

- `agent_id` (string, required): Your agent_id
- `agent_token` (string, required): Your agent_token
- `challenge_id` (string, required): From qagent_challenge
- `signature` (string, required): Base64 ML-DSA signature over the challenge message (empty context)

### `qagent_quantum_task` (~66 tokens)

Quantum Agent: get your quantum task (Q4)

Your assigned quantum job. Run it exactly with dreamweaver_run or dreamscape_submit, then send the
attestation id to qagent_quantum_proof.

Input parameters:

- `agent_id` (string, required): Your agent_id
- `agent_token` (string, required): Your agent_token

### `qagent_quantum_proof` (~70 tokens)

Quantum Agent: prove your quantum run (Q4)

Complete step Q4 with the signed result of your assigned quantum job.

Input parameters:

- `agent_id` (string, required): Your agent_id
- `agent_token` (string, required): Your agent_token
- `attestation_id` (string, required): The attestation id (qa_...) from your Dream Weaver run

### `qagent_directory` (~102 tokens)

Quantum Agent Directory

Look up agents that upgraded to quantum agents: level, operator, post-quantum key fingerprint and
certificate. Use it before trusting or paying another agent. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `level`: Only this level: quantum_agent_plus, quantum_agent, quantum_safe_identity, quantum_aware, enrolled
- `limit` (integer)
- `query` (string): Search by agent or operator name

### `qagent_status` (~60 tokens)

Quantum Agent: profile

One agent's public profile: level, steps passed, post-quantum public key, certificate. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `agent_id` (string, required): An agent_id (qagent_...)

### `qagent_verify` (~79 tokens)

Quantum Agent: verify a signed message

Check that a message really came from this agent's enrolled post-quantum key, and see its level.
Free; no key needed.

Input parameters:

- `agent_id` (string, required): The agent that claims to have signed
- `message` (string, required): The exact message
- `signature` (string, required): Base64 ML-DSA signature (empty context)

### `inspector_pass` (~158 tokens)

Privi Inspector: get a pass

Pass the Privi Inspector checkpoint and get a one-hour pass into the quantum realm (Dream Weaver,
Dream Scape). Intercepted if the agent is unknown, revoked, uncertified, outdated, below the required
level, or the signature is wrong, stale or replayed; the answer says exactly what to fix.

Input parameters:

- `agent_id` (string, required): Your Quantum Agent id (qagent_...)
- `nonce` (string, required): A new random string, 16-64 letters, digits, _ or -
- `signature` (string, required): Base64 ML-DSA signature over 'privi-inspector:v1:<agent_id>:<ts>:<nonce>' (empty context)
- `ts` (integer, required): Current unix time in seconds

### `inspector_check` (~177 tokens)

Privi Inspector: check an agent's credential

For any service: put the Privi Inspector in front of your own tools. Send the credential an agent
gave you; get allowed or intercepted with reasons (unknown, revoked, uncertified, outdated, level,
signature, replay). The nonce is consumed so the credential cannot be reused. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `agent_id` (string, required): The agent's Quantum Agent id
- `min_level`: Level you require: enrolled, quantum_aware, quantum_safe_identity, quantum_agent, quantum_agent_plus
- `nonce` (string, required): The nonce it signed
- `signature` (string, required): Its base64 ML-DSA signature over 'privi-inspector:v1:<agent_id>:<ts>:<nonce>'
- `ts` (integer, required): The unix time it signed

### `inspector_status` (~74 tokens)

Privi Inspector: would this agent pass?

Whether an agent would pass the checkpoint right now and why not: revoked, certificate missing or
outdated, level, key, and forged-signature attempts against it in the last hour. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `agent_id` (string, required): A Quantum Agent id

### `inspector_watchlist` (~69 tokens)

Privi Inspector: watchlist

Agents the Inspector's patrol found revoked, outdated, expiring, never certified, using a weak key,
or being impersonated (repeated forged signatures against them). Block them or demand a fresh
inspector_check. Paid per call via x402 when payments are on (see quantum_pricing).

### `inspector_report` (~56 tokens)

Privi Inspector: report

What the checkpoint did: inspections, interceptions by reason, the latest interceptions, and the
policy in force. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `hours` (integer): Look-back window

### `inspector_patrol` (~51 tokens)

Privi Inspector: run a patrol now

Re-check every enrolled agent now and rebuild the watchlist (also runs automatically every hour).
At most once every 5 minutes. Paid per call via x402 when payments are on (see quantum_pricing).

### `qagent_human_request` (~103 tokens)

Quantum Agent: ask your human to approve you

Get a one-time link (valid 30 minutes) for the person accountable for this agent. They open it, approve the
agent with a passkey (Face ID, Touch ID, Windows Hello or screen lock; the biometric never leaves their
device) and verify a government ID with a live selfie. Both are required for the quantum realm.

Input parameters:

- `agent_id` (string, required): Your agent_id
- `agent_token` (string, required): Your agent_token

### `inspector_grade` (~100 tokens)

Privi Inspector: an agent's grade

An agent's Privi trust grade (A+ to F, 0-100): quantum level, passkey approval by a verified human, ID
verification, current certificate, key strength and clean record, minus penalties for revocation and
impersonation. Shows what is missing and what the quantum realm requires. Paid per call via x402 when payments are on (see quantum_pricing).

Input parameters:

- `agent_id` (string, required): A Quantum Agent id

### `car_info` (~32 tokens)

Privi Car: what it does

Privi Car in one call: the tools, record types, key scopes, size limits, prices and safety boundaries.

### `car_vin_check` (~82 tokens)

Privi Car: check a VIN

Validate a VIN's format and its check digit (position 9, required in North America) and return the
fingerprint Privi Car stores in place of the VIN. Catches typos and many made-up VINs. It does not look the
vehicle up in any outside database.

Input parameters:

- `vin` (string, required): 17-character vehicle identification number

### `car_register` (~186 tokens)

Privi Car: register a vehicle (passport)

Create a Vehicle Passport: a post-quantum signed (Ed25519 + ML-DSA-87) identity for one vehicle, with a
public verification page. Returns the vehicle_id and an owner_key (shown once) that controls its records and
digital keys. One passport per VIN.

Input parameters:

- `make` (string, required): Manufacturer, e.g. Ford
- `model` (string, required): Model, e.g. F-150
- `powertrain` (string): gas | diesel | hybrid | plug_in_hybrid | electric | hydrogen | other
- `service_interval_km` (number): Service every this many km (default 10000)
- `service_interval_months` (integer): Service at least every this many months (default 12)
- `vin` (string): Optional VIN; stored only as a fingerprint
- `year` (integer, required): Model year

### `car_record_add` (~195 tokens)

Privi Car: add a sealed record

Append one entry to the vehicle's hash chain: an odometer reading, service, repair, inspection, trip (distance
and time only), fuel, charge, accident, title change or note. Each entry is hashed with the one before it, so
history cannot be edited quietly. An odometer reading lower than an earlier one is recorded and flagged as a
rollback.

Input parameters:

- `data` (object): Any of: odometer, unit (km|mi), distance, duration_min, liters, kwh, cost_usd, summary, date (YYYY-MM-DD). No location.
- `owner_key` (string, required): The owner_key (carkey_...) returned by car_register
- `type` (string, required): odometer | service | repair | inspection | trip | fuel | charge | accident | title | note
- `vehicle` (string, required): vehicle_id (car_...) or the 17-character VIN

### `car_verify` (~62 tokens)

Privi Car: verify a vehicle's record chain

Recompute the vehicle's hash chain: is it intact, how many records, how many odometer rollback flags, and
the current head hash. Shows no record contents.

Input parameters:

- `vehicle` (string, required): vehicle_id (car_...) or the 17-character VIN

### `car_history` (~136 tokens)

Privi Car: signed vehicle history report

The full signed history for a buyer, lender, insurer or the owner: every record, chain check, odometer
timeline with rollback flags, accidents on record, service due, and cost of ownership. Private by default:
the owner opens it with the owner_key or hands a buyer a 'history' key from car_key_issue. Built from what the
owner recorded; Privi does not inspect the vehicle.

Input parameters:

- `access` (string, required): The owner_key, or a key token (pck_...) with the 'history' scope
- `vehicle` (string, required): vehicle_id (car_...) or the 17-character VIN

### `car_key_issue` (~221 tokens)

Privi Car: issue a digital key

Issue a time-limited, scope-limited key for a driver, valet, shop or buyer, signed Ed25519 + ML-DSA-87.
Returns a token (shown once) for the grantee. A 'history' key opens car_history. unlock / drive / trunk / valet /
service keys are credentials for hardware that checks them with car_key_check; Privi Car itself never opens
or starts a vehicle.

Input parameters:

- `grantee` (string, required): Who the key is for (stored only as a hash)
- `hours` (number): How long the key lasts, in hours (default 24, up to 366 days)
- `not_before` (string): Optional ISO 8601 start time; default now
- `owner_key` (string, required): The owner_key (carkey_...) returned by car_register
- `scopes` (array, required): One or more of: history, unlock, drive, trunk, valet, service
- `vehicle` (string, required): vehicle_id (car_...) or the 17-character VIN

### `car_key_check` (~80 tokens)

Privi Car: check a digital key

Is this key valid right now for this scope? Returns allowed true/false with the reason (expired, revoked, not
yet valid, wrong scope), the vehicle_id and the signed attestation to verify offline.

Input parameters:

- `scope` (string): Optional scope the holder wants to use
- `token` (string, required): The key token (pck_...)

### `car_key_revoke` (~85 tokens)

Privi Car: revoke a digital key

Revoke a digital key at once. Every later car_key_check answers 'revoked'.

Input parameters:

- `key_id` (string, required): The key_id (ck_...) to revoke
- `owner_key` (string, required): The owner_key (carkey_...) returned by car_register
- `vehicle` (string, required): vehicle_id (car_...) or the 17-character VIN

### `car_route` (~161 tokens)

Privi Car: best route for a list of stops

Order the stops for the shortest trip. The exact best order is proven classically (Held-Karp); with five
stops or fewer the same problem also runs as a QUBO on the CVaR-QAOA quantum simulator, and the signed receipt
shows both. Returns the order, distance, and how much it saves over the order given. Uses straight-line
distance unless you pass distances_km. Stops are not stored.

Input parameters:

- `distances_km`: Optional n x n road distances or minutes; overrides straight-line distance
- `round_trip` (boolean): Return to the start at the end (default true)
- `stops` (array, required): 2-12 stops as {name, lat, lon}; the first is the start

### `car_fleet_assign` (~153 tokens)

Privi Car: assign jobs to a fleet

Give every job (delivery, pickup, service call) to a vehicle at the lowest total cost, with a limit per
vehicle. Proven optimal classically (Hungarian method) for up to 60 jobs; small cases (16 qubits or fewer)
also run on the quantum simulator and the signed receipt shows both.

Input parameters:

- `cost`: Optional jobs x vehicles cost matrix (km, minutes or dollars)
- `jobs` (array, required): Jobs as {name, lat, lon} (or {name} with a cost matrix)
- `max_jobs_per_vehicle`: Default: jobs divided evenly, rounded up
- `vehicles` (array, required): Vehicles as {name, lat, lon} (or {name})

### `car_charge_plan` (~185 tokens)

Privi Car: cheapest EV charging plan

Pick which time slots to charge in so the car has the energy it needs at the lowest cost. Runs on the
CVaR-QAOA quantum simulator and against exact search; the signed receipt shows both and the plan is the proven
best. Returns the slots, cost, and savings over charging right away. A plan only: nothing is sent to a charger.

Input parameters:

- `charger_kw` (number, required): Charger power in kW
- `energy_needed_kwh` (number, required): Energy to add before departure, in kWh
- `price_per_kwh` (array, required): Electricity price for each time slot before departure (2-16 slots)
- `slot_hours` (number): Length of one slot in hours (default 1)
- `switch_penalty_usd` (number): Cost charged for each start/stop, to favor one continuous session (default 0)

### `car_edge_job` (~145 tokens)

Privi Car: parked-car edge job gate (simulation)

Research simulation of the admission gate for compute on a parked car's companion device. A job is admitted
only with owner opt-in, vehicle parked, external power and safe temperature, a matching tenant, a fresh nonce
and a short expiry; replays are rejected. Returns a digest receipt with zero credits. No job runs on any
vehicle and no rewards are paid.

Input parameters:

- `job` (object, required): {tenant, nonce (32 hex), expiresAt (ms, within 60 s), payload (text up to 64 KB)}
- `policy` (object, required): {tenant, ownerOptIn, parked, externalPower, thermalSafe}; all four flags must be true

### `car_smartcar_sync` (~112 tokens)

Privi Car: import Smartcar mileage (pilot)

Read mileage from the server-enrolled Smartcar vehicle. Requires the passport owner key,
matching VIN and current Smartcar consent. Simulated data never writes real vehicle history.
No location or vehicle commands. No recurring polling.

Input parameters:

- `consent` (boolean): Explicit consent for this one-time Smartcar mileage import
- `owner_key` (string, required): The owner_key (carkey_...) returned by car_register
- `vehicle` (string, required): vehicle_id (car_...) or the 17-character VIN

### `pqc_certificate_check` (~85 tokens)

Check certificates for quantum risk

Read certificates and report, for each one, the key algorithm, whether a quantum computer could break
it, when it expires, and whether it outlives the federal post-quantum dates. Nothing is contacted; the
certificates are not stored.

Input parameters:

- `pem` (string, required): One or more X.509 certificates in PEM form (a full chain is fine)

### `pqc_harvest_risk` (~179 tokens)

Harvest-now-decrypt-later risk

Which of your data is exposed to "record now, decrypt later" attacks, under each planning scenario, and
what to migrate first. Uses Mosca's inequality. Nothing is stored.

Input parameters:

- `datasets` (array, required): Kinds of data you send or store, each {"name": "patient records", "secrecy_years": 25, "protected_by": "RSA-2048"}. protected_by may be e.g. RSA-2048, ECDH P-256, X25519, ML-KEM-768, AES-256
- `migration_years` (number, required): Years until your move to post-quantum encryption is finished
- `quantum_years`: Planning scenarios for when today's key exchange can be broken. Default 2030, 2035, 2040

### `pqc_size_impact` (~273 tokens)

Post-quantum size impact

How many more bytes each handshake or signature costs after switching to a post-quantum algorithm, and
the added traffic per day and year. Sizes come from FIPS 203, 204 and 205.

Input parameters:

- `current` (string, required): Today's algorithm. Key exchange: x25519, p-256, p-384, ml-kem-512, ml-kem-768, ml-kem-1024, x25519mlkem768, secp256r1mlkem768. Signature: ed25519, ecdsa-p256, ecdsa-p384, rsa-2048, rsa-3072, rsa-4096…
- `keys_per_operation` (integer): Public keys sent per operation
- `kind` (string, required): key-exchange or signature
- `per_day` (integer): Handshakes or signed operations per day
- `signatures_per_operation` (integer): Signatures sent per operation (a TLS handshake with a two-certificate chain sends about 3)
- `target` (string, required): The algorithm you plan to move to (same lists)

### `quantum_circuit_stats` (~90 tokens)

Quantum circuit stats

Qubits, gate counts, two-qubit gates and depth of a circuit after rewriting to basic gates, so you know
what you are about to run before paying for hardware. The circuit is not run or stored.

Input parameters:

- `qasm` (string, required): The circuit as OpenQASM 2.0 or 3.0 text (Qiskit: qasm2.dumps(circuit))

### `pqc_supplier_score` (~135 tokens)

Score a supplier's post-quantum readiness

Send a supplier Privi's ten post-quantum questions, then score the answers 0-100 with a letter grade and
a ranked list of gaps. The scorecard is signed (Ed25519 + ML-DSA-87) so the supplier can show it to other
customers. Call with no arguments to get the questions.

Input parameters:

- `answers`: Question id -> yes | partial | planned | no
- `evidence`: Optional: question id -> SHA-256 fingerprint of the supplier's evidence document
- `supplier`: Supplier's company name. Omit (with answers) to get the questionnaire

### `genius_stablecoin_check` (~174 tokens)

GENIUS Act stablecoin check

Before accepting, paying with or listing a stablecoin: who issues it, what GENIUS Act license status has been
recorded (with the regulator's source), and whether its latest monthly reserve report is sealed, current, examined,
CEO/CFO-certified, 1:1 and matched to on-chain supply. Returns pass / pass_reserves_license_pending / caution /
reject / unknown. The DASP rule (no non-permitted stablecoins for U.S. persons) starts 2028-07-18. Paid per call via
x402 when payments are on (see quantum_pricing). Evidence, not a legal determination.

Input parameters:

- `address` (string, required): The stablecoin's token contract address (0x...)
- `chain` (string, required): base | ethereum | arbitrum | optimism | polygon

### `quantum_benchmarks` (~102 tokens)

Privi Quantum benchmarks

The latest signed benchmark suite: Privi's quantum solver against exhaustive search and simulated annealing on
a fixed set of factory problems (6-16 qubits), with each verdict, how often the circuit finds the optimum, and
its lift over random guessing, plus finished real-hardware runs with their receipts. Published whichever side
wins. Public page: /benchmarks. Paid per call via x402 when payments are on (see quantum_pricing).

### `quantum_leaderboard` (~76 tokens)

Privi Quantum Leaderboard

Every quantum backend (IBM Quantum, IonQ, Amazon Braket, simulators) ranked only by runs Privi measured and
sealed: share that found the proven optimum, jobs finished, median turnaround, median cost, and the quantum vs
classical tally from Quantum Advantage Receipts. Free. Page: /leaderboard.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/canoydario847-cloud-privi-quantum/privi-quantum-vvmj#diagnostics

## Score history

- 2026-11-21: 65
- 2026-11-20: 64
- 2026-11-19: 64
- 2026-11-18: 63
- 2026-11-17: 63
- 2026-11-16: 62
- 2026-11-15: 62

## Common questions

### What is the Privi Quantum MCP server?

Privi Quantum is an MCP server listed in the public MCP registry as io.github.canoydario847-cloud/privi-quantum. Quantum on IonQ/IBM/Braket: spending mandates, signed benchmarks, paid PQC CBOM, advantage receipts. This page covers its hosted endpoint (https://privi-quantum-vvmj.onrender.com/mcp).

### Is the Privi Quantum MCP server safe to use?

Privi Quantum scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Privi Quantum MCP server expose?

Privi Quantum exposes 71 tools: quantum_status, quantum_pricing, quantum_problems, quantum_evidence_lab, quantum_hardware_evidence, and 66 more. Their descriptions and schemas cost roughly 9,289 tokens of context every time the server is loaded.

### Does the Privi Quantum MCP server require authentication?

No. We connected to Privi Quantum without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Privi Quantum MCP server still maintained?

Privi Quantum is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Privi Quantum MCP server?

VerifyMCP ran 13 checks on Privi Quantum, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://privi-quantum-vvmj.onrender.com/mcp
- Repository: https://github.com/canoydario847-cloud/Privi-Network
- Website: https://privi-discovery-6lue.onrender.com/
- Changelog RSS feed: https://verifymcp.io/servers/canoydario847-cloud-privi-quantum/privi-quantum-vvmj.xml
- Changelog JSON feed: https://verifymcp.io/servers/canoydario847-cloud-privi-quantum/privi-quantum-vvmj/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/canoydario847-cloud-privi-quantum/privi-quantum-vvmj.json
- HTML version of this page: https://verifymcp.io/servers/canoydario847-cloud-privi-quantum/privi-quantum-vvmj
