Anchors attestations to Hedera mainnet for immutable, verifiable compliance records.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Rubric Protocol MCP Server sign this AI decision for EU AI Act"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Post-quantum AI compliance attestation as an MCP server. Works with Claude Desktop, Claude Code, Cursor, Windsurf, Continue, Zed, and any MCP-compatible host.
v2.0 — now with free local tier. No API key required to start attesting.
npm install -g @rubric-protocol/mcp-serverRelated MCP server: TrustAtom MCP Server
Edit claude_desktop_config.json:
{
"mcpServers": {
"rubric": {
"command": "npx",
"args": ["-y", "@rubric-protocol/mcp-server"],
"env": { "RUBRIC_API_KEY": "optional-for-hcs-anchoring" }
}
}
}Restart Claude Desktop. Rubric tools appear in the MCP menu.
attest — PQ-signed Merkle leaves stored in ~/.rubric/local-bundles/
verify — check local attestations
framework_detect — detect applicable regulations offline
cost_estimate — project monthly cost
register_agent — request a free key to unlock HCS anchoring
status — federation health
Everything above, plus:
HCS anchoring on Hedera mainnet (tamper-evident third-party timestamp)
get_proof — ZK Merkle inclusion proofs (Noir/Barretenberg)
Request a key via the register_agent tool, or at https://rubric-protocol.com
compliance_tag — attach regulatory framework tags to bundles
bundle_query — filter by leafType, agentId, time range
100K attestations/mo, overage $0.01 each
Higher throughput, SLA, dedicated federation capacity.
Six tools that pay per call in USDC on Base via the x402 protocol. No Rubric account or API key required - just a funded wallet. Every response carries a signed, Hedera-anchored attestation ID your agent can cite later.
Tool | Price | What you get |
| $0.01 | Sanctions/export-control screening across OFAC SDN + Consolidated, UN, UK OFSI, EU, and BIS lists (76K+ entries): per-list results, list file hashes, anchored attestation - audit evidence you screened, against which versions, and what it said |
| $0.01 | gpt-4o-mini completion plus attestation binding prompt hash, response hash, exact model version, timestamp - evidence of which model said what, when |
| $0.005 | Unforgeable operating history for any agent attesting through Rubric - record count, first-seen, continuity - from HCS-anchored records that cannot be backdated |
| $0.005 | Attested x402 payment history for any Base/EVM buyer wallet, from an append-only settlement ledger - evidence, not opinion |
| $0.002 | Independent audit of any Rubric attestation: signature, HCS sequence, mirror-node confirmation - a signed verdict with its own attestation ID |
| $0.001 | One attested Hedera network fact (exchange rate, gas, supply, nodes, throughput, topic state) |
Create a wallet and fund it with a few dollars of USDC on Base (Coinbase -> withdraw USDC -> network: Base)
Set RUBRIC_WALLET_KEY to the wallet's private key in your MCP server environment
Optional: RUBRIC_X402_DAILY_LIMIT (default 1.00 USD/day)
No wallet key? Paid tools return setup guidance - never errors, never charges.
Daily ceiling. Spending stops at your limit; the tool returns a budget error your agent can read. Resets 00:00 UTC.
Price protection. Before paying, each tool checks the server's quoted price against its documented maximum and refuses anything higher - even we cannot overcharge you.
Full accounting. Every paid response includes spentTodayUsd.
Your key never leaves the MCP process. A failed operation is never charged.
Catalog, prices, and terms are machine-readable at x402.json and openapi.json.
Tools load by module via RUBRIC_MCP_MODULES (default: core,x402).
Available: core, x402, attestation, verification, compliance,
regulatory, governance, registry, ops, or all.
EU AI Act (Articles 9–15, 17, 26, 49, 72, 73, Annexes IV/XI/XII), SR 11-7, OCC, FDIC, NIST AI RMF 1.0, TX TRAIGA, CO AI Act, HIPAA, EU DSA, NIS2, SEC, CFTC, ECOA Reg B, NYC LL144.
attest — attest an AI decision (local free, HCS with key)
verify — verify attestation by ID
get_proof — ZK Merkle inclusion proof
register_agent — request free developer API key
status — federation health
framework_detect — auto-detect regulatory frameworks
cost_estimate — monthly cost projection
compliance_tag — attach framework tags (Standard+)
bundle_query — query bundles (Standard+)
Post-quantum signatures: ML-DSA-65 (NIST FIPS 204) via liboqs
Merkle aggregation: N-tier, SHA3-256, up to 1,000,000:1 compression
Anchoring: Hedera mainnet HCS topic 0.0.10416909
Federation: 5 geo-distributed nodes (US, SG, JP, CA, EU)
ZK proofs: Noir beta.19, depth-20 Poseidon2 Merkle inclusion
Homepage: https://rubric-protocol.com
Pricing: https://rubric-protocol.com/pricing
Changelog: ./CHANGELOG.md
PAID ($0.005 USDC): unforgeable operating history for any agent attesting through Rubric - record count, first-seen, continuity, recent activity, from HCS-anchored records that cannot be backdated.
Inputs: agent_id (required).
Attest an AI decision. With RUBRIC_API_KEY: HCS-anchored on Hedera mainnet. Without: PQ-signed local Merkle leaf in ~/.rubric/local-bundles/.
Inputs: payload (required), agent_id, metadata.
PAID ($0.01 USDC): gpt-4o-mini completion plus attestation binding prompt hash, response hash, exact model version, timestamp - evidence of which model said what, when.
Inputs: prompt (required), max_tokens.
Query attestation bundles by leaf type, agent, or time range. Requires Standard+ tier.
Inputs: limit, agentId, leafType.
Estimate monthly Rubric cost from expected decision volume. No key required.
Inputs: decisions_per_day (required).
Auto-detect applicable regulatory frameworks (EU AI Act, SR 26-2, HIPAA, NIST AI RMF, etc.) from decision content. Works offline, no key required.
Inputs: payload (required), metadata.
Generate ZK Merkle inclusion proof (Noir/Barretenberg) for an attestation. Requires API key.
Inputs: attestation_id (required).
PAID ($0.001 USDC): one attested Hedera network fact (exchange-rate, gas-fees, supply, nodes, throughput, topic-state) with the attestation ID of the served snapshot.
Inputs: fact (required).
Register an agent and receive a free Rubric developer API key via email.
Inputs: email (required), agent_name (required), use_case.
PAID ($0.01 USDC): sanctions and export-control screening across OFAC SDN + Consolidated, UN, UK OFSI, EU, and BIS lists (76K+ entries). Returns per-list results plus a signed, Hedera-anchored attestation - audit evidence you screened, against which list versions, and what it said. Requires RUBRIC_WALLET_KEY.
Inputs: name (required), query_id.
Federation health across US/SG/JP/CA/EU nodes + ZK node.
Inputs: no named parameters.
Verify an attestation. Checks local store first, then federation. Merkle inclusion + HCS anchoring.
Inputs: attestation_id (required).
PAID ($0.002 USDC): independent audit of a Rubric attestation - signature, HCS sequence, mirror-node confirmation - returning a signed verdict with its own attestation ID.
Inputs: attestation_id (required).
PAID ($0.005 USDC): attested x402 payment history for a Base/EVM buyer wallet from an append-only settlement ledger - settlements, first/last seen, spend, services. Evidence, not opinion.
Inputs: address (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 14 tools
Most tools target a distinct action (attest, get_proof, screen_entity, wallet_record, cost_estimate, status), so an agent can route correctly. The main risk is the pair verify vs verify_audit, which both check an attestation's signature/HCS anchoring with only subtle stated differences, plus some conceptual overlap between attest and attested_inference.
All names are snake_case, which keeps them readable, but the grammatical pattern is mixed: verb_noun (get_proof, register_agent, screen_entity, verify_audit) alongside noun_noun (wallet_record, agent_record, hedera_fact, cost_estimate, bundle_query) and a bare noun (status). A predictable verb_noun or noun_noun convention throughout would remove the guesswork.
14 tools sits at the top of the well-scoped 3-15 range and each has a plausible role in the attestation lifecycle. The set does sprawl somewhat into unrelated paid data verticals (sanctions screening, wallet history, Hedera facts), which suggests several products folded into one surface.
The core lifecycle is covered: create (attest), retrieve/verify (verify, get_proof, bundle_query), independently audit (verify_audit), plus registration, health, framework detection, and cost estimation. Gaps are minor — no explicit revoke/delete of an attestation and no key rotation or deregistration path for registered agents.
Tamper-evident SHA-256 hash-chained decision notary for EU AI Act, NIST AI RMF & SOC2.
Register every AI agent, log every action, prove it. EU AI Act compliance built in.
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
