프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. 리뷰와 계정 기능은 다음 단계에서 열려요.
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

Privi Quantum

제작자: canoydario847-cloud버전 0.9.0i★ –i클라우드에서 실행
레지스트리 이름io.github.canoydario847-cloud/privi-quantum

설치

개요

제작자가 쓴 설명(영어 원문)

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

PopNx MCP의 세 기둥

이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.

할 수 있는 일

이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.

  • 연결 방식: 클라우드에서 실행
  • 전송 방식: Streamable HTTP
  • 카테고리: 기타

설치

쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.

설치하기 전에

필요한 것

어떤 앱을 쓰세요?

위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.

웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:

  1. Settings → Connectors 열기
  2. Add custom connector 누르기
  3. 아래 주소를 붙여 넣고 Add 누르기
  4. 로그인하라고 하면 제작자의 서비스에 로그인하기
SettingsConnectors1+ Add2https://…3
https://privi-quantum.onrender.com/mcp

터미널에서 이 명령어를 실행하세요

claude mcp add --transport http privi-quantum https://privi-quantum.onrender.com/mcp

Cursor에서 열기

또는 설정을 직접 복사하기

프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요

{
  "mcpServers": {
    "privi-quantum": {
      "url": "https://privi-quantum.onrender.com/mcp"
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

VS Code에서 열기

또는 설정을 직접 복사하기

프로젝트의 .vscode/mcp.json에 붙여 넣으세요

{
  "servers": {
    "privi-quantum": {
      "type": "http",
      "url": "https://privi-quantum.onrender.com/mcp"
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:

  1. 웹에서 ChatGPT 열기 → Settings → Connectors (Apps)
  2. Create 또는 Add 누르기(일부 요금제는 먼저 Advanced에서 Developer mode를 켜야 해요)
  3. 아래 주소를 붙여 넣고 이름을 정한 뒤 저장하기
  4. 로그인하라고 하면 제작자의 서비스에 로그인하기
SettingsConnectors1+ Create2https://…3
https://privi-quantum.onrender.com/mcp

메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.

선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.

이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.

할 수 있는 일

도구 이름과 설명은 서버가 2026년 11월 7일에 알려 준 그대로예요. 우리가 아니라 제작자가 쓴 글이고, 일반 텍스트로만 보여 드려요.

  • quantum_status

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

  • 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. Everything else on this server is free. Failed calls are never charged.

  • quantum_problems

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

  • 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). Free.

  • quantum_verify

    Check both post-quantum signatures, the body hash, and the on-chain anchor of a result. Free.

  • pqc_scan_code

    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.

  • pqc_readiness_package

    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, an

  • pqc_endpoint_check

    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 pq

  • pqc_federal_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. Free.

  • 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 / clas

  • quantum_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. Free.

  • quantum_run_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 agai

  • quantum_hardware_job

    Status of a quantum hardware job; once done, the decision, measurement statistics, the signed attestation and the Quantum Advantage Receipt. Free.

  • quantum_mandate_request

    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. Free.

  • quantum_mandate_status

    A Quantum Mandate's terms, status (draft, active, expired, revoked), spend, remaining budget and every charge and refund. Free.

  • quantum_mandate_check

    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. Free.

  • quantum_mandate_revoke

    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. Free.

  • quantum_run_circuit

    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

  • pqc_crypto_inventory

    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 anc

  • vault_keygen

    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`. Free.

  • vault_seal

    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. Free.

  • vault_open

    Decrypt a Privi Vault envelope. Nothing is stored; for sensitive data prefer opening locally with `python -m privi_quantum.vault open`. Free.

  • vault_receipt

    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. Free.

  • privilege_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. Free.

  • privilege_benchmark

    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. Free.

  • dreamweaver_run

    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. Free.

  • dreamscape_open

    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). Free.

  • dreamscape_submit

    Run a quantum job in your Dream Scape through Dream Weaver and keep the result there. Free.

  • dreamscape_jobs

    Your Dream Scape's recent jobs, or one job with its full result. Free.

  • accelerator_info

    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. Free.

  • qagent_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. Free.

  • qagent_scan

    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.

  • qagent_challenge

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

  • qagent_prove

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

  • qagent_quantum_task

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

  • qagent_quantum_proof

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

  • qagent_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. Free.

  • qagent_status

    One agent's public profile: level, steps passed, post-quantum public key, certificate. Free.

  • qagent_verify

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

  • inspector_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 wha

  • inspector_check

    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. Free.

  • inspector_status

    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. Free.

  • 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. Free.

  • inspector_report

    What the checkpoint did: inspections, interceptions by reason, the latest interceptions, and the policy in force. Free.

  • inspector_patrol

    Re-check every enrolled agent now and rebuild the watchlist (also runs automatically every hour). At most once every 5 minutes. Free.

  • qagent_human_request

    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 requ

  • inspector_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. Fr

  • 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

  • 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:

기본 점검i

누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 8일 점검

  • ✓ 통과

    제작자와 저장소 일치

    레지스트리 이름이 GitHub 계정 canoydario847-cloud 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요

  • … 아직 점검 안 함

    계속 관리되고 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • … 아직 점검 안 함

    라이선스 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • ✓ 통과

    엔드포인트 응답

    172ms 만에 응답(HTTP 200)

  • – 해당 없음

    OAuth로 로그인

    로그인 필요 없음

  • ✓ 통과

    도구 설명에 숨겨진 지시 없음

    도구 설명 49개를 읽었고, AI에게 보내는 숨겨진 지시는 없었어요

기타 카테고리의 다른 서버와 비교i

  • 이 카테고리의 다른 서버 18379개 중 0%보다 스타가 많아요
  • 이 카테고리의 다른 서버 18379개 중 79%보다 최근에 레지스트리에 공개됐어요
  • 기본 점검 결과가 이 카테고리의 다른 서버 18379개 중 100%와 같거나 더 좋아요

레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.

자주 묻는 질문

Privi Quantum, 안전한가요?

해당하는 기본 점검 3개 중 3개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.

어떤 키나 코드가 필요한가요?

레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.

내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?

제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.

아직 관리되고 있나요?

GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.9.0)은 11일 전 레지스트리에 올라왔어요.

어떤 앱에서 쓸 수 있나요?

Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.

대신 쓸 수 있는 건 뭐가 있나요?

같은 카테고리에는: Spec Driven Development, Remote Desktop Commander, NexusWindows

대안

같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.

카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i

Spec Driven Development

제작자: formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

내 컴퓨터에서 실행★ 440MIT14개월 전 업데이트
설치

Remote Desktop Commander

제작자: desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

클라우드에서 실행★ 211그저께 업데이트
설치

NexusWindows

제작자: pironjulien

Windows computer use in the background: desktop apps driven without your mouse or keyboard.

내 컴퓨터에서 실행오늘 업데이트
설치

제작자의 README

README 열기

제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.

Privi Quantum

Quantum optimization for factory decisions, with answers no quantum computer can forge. A Privi World Co product · Copyright (c) 2026 Privi World Co. All rights reserved.

Endpoint (MCP, streamable HTTP): https://privi-quantum.onrender.com/mcp. Most tools are free; four are paid per call with x402 (see Pricing). Public benchmarks: https://privi-quantum.onrender.com/benchmarks

{ "mcpServers": { "privi-quantum": { "url": "https://privi-quantum.onrender.com/mcp" } } }

What it does

Privi Quantum joins three things into one pipeline:

  1. Quantum optimization (CVaR-QAOA). A factory decision becomes a QUBO, then an Ising Hamiltonian, then a QAOA circuit. Angles are trained on the CVaR objective (Barkoutsos et al., *Quantum* 2020) and deepened with the INTERP schedule (Zhou et al., *PRX* 2020). The circuit runs on an exact statevector simulator (up to 16 qubits) and exports as OpenQASM 2.0 for IBM Quantum, Amazon Braket or Azure Quantum hardware.
  2. Proof of quality. Every answer is compared against the classical exhaustive optimum, so the result states plainly whether the quantum run found the best decision and how much it amplified the chance of finding it versus a random guess.
  3. Post-quantum, on-chain proof. Every result is an attestation signed with Ed25519 + ML-DSA-87 (NIST FIPS 204, the CNSA 2.0 parameter set). Its hash is batched onto the Privi blockchain through Privi Anchor every 5 minutes. Anyone can verify it: signatures offline with the keys at /keys, the anchor on chain.

Tools

ToolWhat it does
quantum_problemsLists the ready-made problems and the data each needs
quantum_optimizeSolves a problem; returns the decision, quality vs. the proven optimum, quantum run details, attestation, optional OpenQASM
quantum_verifyChecks both signatures, the body hash and the Privi chain anchor
pqc_scan_codeFinds quantum-vulnerable crypto (RSA, ECC, DH, DSA, weak hashes) in code; 0–100 readiness score
pqc_endpoint_checkTests up to 20 public sites (e.g. www.agency.gov) for TLS 1.3 and hybrid post-quantum key exchange (X25519MLKEM768, FIPS 203); returns a fix per site and CBOM-ready assets
pqc_readiness_packageSigned EO 14409 / OMB M-26-15 package from code, an asset inventory and/or live endpoints: prioritized deadlines, the nine plan elements, CycloneDX 1.6 CBOM
pqc_federal_deadlinesThe federal post-quantum timeline with sources
quantum_statusAlgorithm, limits, backends, signing key, anchoring
quantum_advantage_receiptRaces the quantum answer against classical baselines and seals the verdict, whichever side wins
quantum_backendsIonQ, IBM Quantum, Amazon Braket and local backends with price, measured turnaround and budget
quantum_run_hardware / quantum_hardware_jobRoutes a trained circuit to real hardware by price or speed; the finished run is sealed with an advantage receipt
pqc_crypto_inventoryOne CBOM for a company from its domains and public GitHub repos: every quantum-vulnerable algorithm, where it is, dated plan
vault_keygen / vault_seal / vault_open / vault_receiptPrivi Vault: re-wrap long-lived data under hybrid X25519 + ML-KEM against "harvest now, decrypt later"
quantum_mandate_request / _status / _check / _revokeQuantum Mandates: a human signs spending terms with their passkey before an agent can run paid quantum hardware
quantum_run_circuitBring your own circuit: OpenQASM 2.0/3.0 from Qiskit, run on IBM Quantum, IonQ, Braket or locally, counts sealed
quantum_leaderboardEvery backend ranked only by runs Privi measured and sealed (also /leaderboard, /leaderboard.json)
Ready-made problems
ProblemFactory questionData
balance_linesSplit jobs across two lines so loads are equal{jobs: [{name, minutes}]}
select_lotsInspect exactly *k* lots, maximize risk covered, never two linked lots{lots: [{name, risk}], k, linked: [[a, b]]}
split_conflictsTwo shifts/trucks/cells with conflicting items apart (weighted Max-Cut){items, conflicts: [{a, b, weight}]}
quboAny binary optimization{Q: [[...]], offset}

HTTP: /health, /status, /keys, /attestations/ , /.well-known/mcp/server-card.json. Privi Explorer feed (public, CORS): /explorer/recent?limit&before lists kind, time, body hash and anchor only, never ids or contents; /explorer/lookup?q= takes a qa_ id (returns links) or a body SHA-256 (proves the record exists and checks both signatures, without revealing the id).

Quantum Agent Accelerator and Quantum Agent Directory

Any AI agent can upgrade to a certified quantum agent, free, with every step checked by Privi:

StepWhat Privi checksTools
Q1 Quantum-awareits code or config was scanned for quantum-vulnerable cryptographyqagent_scan
Q2 Quantum-safe identityit holds an ML-DSA (FIPS 204) key: it signs a one-time challengeqagent_challenge, qagent_prove
Q3 Quantum-safe linksevery public endpoint it runs negotiates X25519MLKEM768qagent_scan with endpoints
Q4 Quantum-capableit ran the quantum job assigned to it (bound to its id) through Dream Weaverqagent_quantum_task, qagent_quantum_proof

Quantum Agent = Q1 + Q2 + Q4, Quantum Agent+ = all four; each level gets a certificate signed Ed25519 + ML-DSA-87 and anchored on chain, and a badge (/quantum-agents/ /badge.svg).

The Quantum Agent Directory is public: qagent_directory, qagent_status, qagent_verify (check that a message really came from an agent's enrolled post-quantum key), GET /quantum-agents, GET /quantum-agents/ , POST /quantum-agents/ /verify, and /.well-known/quantum-agents.json. Program page: /accelerator. Agents make their key locally; Privi only ever sees the public key.

Human trust and the Privi grade

The quantum realm now also requires a real, verified human behind every agent:

  • Biometric human approval (passkeys). qagent_human_request gives the agent a one-time link for its human. The person approves that exact agent and its post-quantum key with a passkey (Face ID, Touch ID, Windows Hello or screen lock), user verification required. The biometric check stays on their device; Privi stores only the passkey's public key and verifies the signature, origin, site and counter. Approvals last 180 days. One person's passkey can approve several agents.
  • Human ID verification (Stripe Identity). From the same page the person verifies a government ID with a matching live selfie. Stripe holds the documents; Privi stores only the result, the session id and the date (webhook POST /humans/stripe-webhook, signature checked, or status checked on return). A Privi admin can record an in-person check (POST /humans/ /id-verified), which counts for less.
  • The Privi grade (Inspector). Every agent gets a score out of 100 and a grade A+ to F: quantum level 35, human approval 20, ID verification 25 (Stripe) or 15 (manual), current certificate 10, key strength 5, clean record 5; revocation sets it to 0 and impersonation attempts cost 15. inspector_grade, /inspector/grade/ , and the directory show it.

Defaults (Render env): INSPECTOR_REQUIRE_HUMAN=1, INSPECTOR_REQUIRE_ID=1, INSPECTOR_MIN_GRADE=B. ID verification needs STRIPE_SECRET_KEY (Stripe Identity enabled, about $1.50 per verification) and STRIPE_IDENTITY_WEBHOOK_SECRET; until they are set, no one can complete ID verification, so the realm stays closed to everyone except agents whose human Privi verified in person. WEBAUTHN_RP_ID defaults to the service's host name; passkeys are tied to it.

What this proves and what it does not: a passkey's user-verification flag is reported by the person's device (a device PIN also counts), and Privi does not check authenticator attestation. Together with ID verification it shows a real, present person with a verified ID approved the agent.

Privi Inspector: the checkpoint and the hunt

Dream Weaver and Dream Scape (MCP tools and the WebSocket) require a Privi pass. An agent signs privi-inspector:v1: : : with the ML-DSA key it enrolled and calls inspector_pass (or POST /inspector/pass) for a one-hour pass, then sends privi_pass (tool argument, X-Privi-Pass header, or the WebSocket auth frame). The Inspector intercepts, with the exact fix: no credential, unknown or revoked agent, wrong / stale / replayed signature, no certificate, an outdated certificate (expired after 180 days or issued under an older policy; re-prove Q2 to renew), a level below the realm's minimum (default Quantum-safe identity), or a key below the minimum. Revocation and expiry are re-checked on every call, so a revoked agent's live pass stops working at once.

The hunt: a patrol re-checks every enrolled agent every hour (INSPECTOR_PATROL_MINUTES) and publishes a watchlist (inspector_watchlist, /inspector/watchlist) of agents that are revoked, outdated, expiring, never certified, using a weak key, or being impersonated (5+ forged signatures against their id in an hour). inspector_patrol runs one on demand. Other services put the same checkpoint in front of their own tools with inspector_check / POST /inspector/check (403 when intercepted). inspector_report and /inspector show what was intercepted and why.

Settings: INSPECTOR_MODE = enforce (default) | report (allow but log) | off; INSPECTOR_MIN_LEVEL (default quantum_safe_identity); INSPECTOR_MIN_KEY (default ML-DSA-44). Admin: POST /quantum-agents/ /revoke {reason} and DELETE to reinstate (QUANTUM_ADMIN_KEY). The hunt stays inside Privi: it blocks and publishes; it never probes or attacks outside systems.

The Privi quantum realm: Dream Scape, Dream Weaver, Privilege

  • Dream Scape is your own quantum environment. dreamscape_open gives a private workspace (scape_id + scape_key) that keeps every job and its signed result; dreamscape_submit runs a job, dreamscape_jobs lists them. One WebSocket, /dreamscape/ws, runs up to 16 jobs at once and streams each realm's progress (job.accepted, realm.started, realm.result, weave.done). Page: /dreamscape.
  • Dream Weaver runs one quantum job on several realms at once (dreamweaver_run). mode: "first" returns the first valid answer and cancels the rest; hedge_ms starts the top realm alone and adds the others after a delay or the moment one fails. mode: "best" keeps the best answer by the deadline. The winner is signed (Ed25519 + ML-DSA-87) and anchored like every Privi Quantum result.
  • Privilege is the directory of quantum realms (privilege_directory, public JSON at /privilege). It ranks realms by expected time to the proven optimum (measured latency divided by how often a realm finds the optimum), from real jobs and the shared 8-qubit benchmark (privilege_benchmark).

Realms today: two built-in engines (Dream Scape Exact: CVaR-QAOA at full depth; Dream Scape Swift: depth 1, short training, fastest) plus any other Privi Quantum node. Add a node with DREAMWEAVER_NODES="Dream Scape EU=https://.../mcp;Dream Scape West=https://.../mcp" or POST /privilege/realms (Authorization: Bearer $QUANTUM_ADMIN_KEY, body {name, url, location}).

Racing picks the fastest realm; it does not make any processor or network faster than it is. Realms run on exact simulators today; quantum hardware joins Privilege as a realm once a provider account is connected.

v0.6: proof, real hardware, inventory, vault

Quantum Advantage Receipts. Every receipt runs two classical baselines on the same problem, exhaustive search (the proven optimum) and simulated annealing, and records cost and

앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요

PopNx에게 묻기