Rubric MCP server

Read from the package source without running it. The installed server may list more.

• adversarial_session_conclude

  Conclude an adversarial session with an attested summary record.

• adversarial_session_start

  Open an attested adversarial-testing (red-team) session — every probe becomes evidence.

• agent_add

  Register an agent profile in the Rubric agent registry (identity for the Agent Logbook).

• agent_get

  Fetch an agent profile and its attestation summary.

• agent_record

  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.

• annex4_generate

  Generate a court-admissible EU AI Act Annex IV technical-documentation evidence package (PDF). Returns a job ID.

• annex4_status

  Status of an Annex IV generation job, with download URL when complete.

• attest

  Attest an AI decision. With RUBRIC_API_KEY: HCS-anchored on Hedera mainnet. Without: PQ-signed local Merkle leaf in ~/.rubric/local-bundles/.

• attest_batch

  Batch-attest up to 1,000 AI decisions in one call (tiered path, HCS-anchored at tier-2 flush). Requires API key.

• attestation_get

  Fetch a full attestation record by ID.

• attestation_status

  Anchoring status of an attestation: buffered, flushed, or anchored with HCS sequence.

• attested_inference

  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.

• auditor_token_createwrite action

  Mint a scoped read-only auditor-portal token for external examiners. Enterprise tier.

• bundle_get

  Fetch one attestation bundle by ID.

• bundle_query

  Query attestation bundles by leaf type, agent, or time range. Requires Standard+ tier.

• c2pa_assertion

  Fetch the C2PA assertion for an attestation, ready to embed in a manifest.

• c2pa_attestwrite action

  Create a C2PA-conformant content-provenance attestation (com.rubric-protocol.attestation assertion).

• compliance_query

  Query the compliance index by systemId, rubricEventType, agentId, jurisdiction, contextId, or time range.

• compliance_report

  Generate a compliance evidence report over a time range.

• cost_estimate

  Estimate monthly Rubric cost from expected decision volume. No key required.

• credential_get

  Fetch an issued Verifiable Credential by ID.

• credential_issue

  Issue a W3C Verifiable Credential wrapping an attestation.

• filing_generate

  Generate a regulatory filing document from attested evidence.

• framework_detect

  Auto-detect applicable regulatory frameworks (EU AI Act, SR 26-2, HIPAA, NIST AI RMF, etc.) from decision content. Works offline, no key required.

• get_proof

  Generate ZK Merkle inclusion proof (Noir/Barretenberg) for an attestation. Requires API key.

• gpai_downstream

  List downstream systems registered against a GPAI model.

• gpai_register

  Register a GPAI (general-purpose AI) model relationship for EU AI Act downstream-provider tracking.

• hedera_fact

  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.

• human_review

  Record an attested human-review decision (oversight evidence for Art. 14 / SR 26-2).

• incident_attest

  Attach an attested evidence entry to an incident.

• incident_createwrite action

  Open an attested incident record (EU AI Act Art. 73 / GPAI serious-incident ready).

• incident_resolve

  Resolve an incident with an attested closure record.

• jurisdiction_assess

  Assess a system against a jurisdiction's requirements using attested evidence.

• jurisdiction_gap

  Gap analysis: requirements without supporting attested evidence, per jurisdiction.

• jurisdiction_map

  Map which regulatory frameworks apply across jurisdictions for your attested systems.

• ledger_lookup

  Look up an anchored record by HCS sequence number on topic 0.0.10416909.

• model_get

  Fetch a registered model's record and commitment.

• model_register

  Register a model (hash, version, lineage) for supply-chain attestation.

• nist_rmf_certifywrite action

  Run NIST AI RMF certification against attested evidence for a compliance context. Hard-fails below the evidence floor.

• nist_rmf_status

  NIST AI RMF certification status for a compliance context.

• pipeline_trace

  All attestations for a pipeline ID, in order — the evidentiary trace of a multi-step agent run.

• register_agent

  Register an agent and receive a free Rubric developer API key via email.

• screen_entity

  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.

• status

  Federation health across US/SG/JP/CA/EU nodes + ZK node.

• usage_report

  Current-period usage and quota for your API key.

• verify

  Verify an attestation. Checks local store first, then federation. Merkle inclusion + HCS anchoring.

• verify_audit

  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.

• verify_batch

  Verify many attestation IDs in one call.

• verify_chain

  Verify an attestation and its full hash-chain lineage back to anchor.

• verify_tree

  Verify Merkle-tree membership for an attestation within its anchored forest.

• wallet_record

  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.

• zk_proof_get

  Retrieve a previously generated ZK inclusion proof by attestation ID.

• zk_verify

  Verify a ZK Merkle inclusion proof previously produced by get_proof.

• Code scan5 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancerepository not readable: repo not found3/15
• Maintainer identityno repository or website to verify2/10

Safety score

55/100

higher than 12% of 4,461 AI and agents servers

Tools

53

the typical AI and agents server has 6

Tools that change things

8%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

59

more than 47% of 1,554 AI and agents servers with a package

Rubric: common questions

Is Rubric MCP server safe?

With care: it is graded C, so read the findings first (55/100). Read the Rubric safety report

How do I install Rubric?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Rubric need an API key?

Yes. The registry entry asks for RUBRIC_WALLET_KEY, RUBRIC_API_KEY.

Is Rubric maintained?

The latest release is v2.2.2.

What can I use instead of Rubric?

Servers from other publishers that do the same job: HOL Guard MCP server, Watch Skill MCP server and OpenWorkProof MCP server.

How does Rubric compare with other AI and agents MCP servers?

safety score 55/100 (higher than 12% of 4,461 AI and agents servers); tools 53 (the typical AI and agents server has 6); tools that change things 8% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.