GENESIS MCP server

• Registry nameio.genesisre/proofrelay-mcp-verifierverified in the MCP registry

The registry name sits under genesisre.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-26
• Tools26
• Server calls itselfGENESIS ProofRelay
• Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 271 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer293 ms
• Space in an agent's context≈ 7,162 tokensthe definitions of all its tools (26), which an agent carries on every turn
• Tool definitionsB · 85 of 100
• Typed results26 of 26 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 24 of 26

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• proofrelay.get_verifier_status

  Read the ProofRelay verifier status, accepted bundle shape, and trust boundary before submitting evidence. Use this first when an agent needs to understand what ProofRelay verifies and what it does not.

• proofrelay.recommend_checkpoint

  Choose the next public-safe GENESIS checkpoint for a paid, material, or relied-upon agent workflow. Submit normalized context only; the tool returns reason codes without protected routing internals.

• proofrelay.verify_bundle

  Verify a submitted non-confidential ProofRelay V1 or V2 evidence bundle for hash integrity, monotonic ordering, signatures, and chain continuity. The tool does not charge, settle, mutate storage, or certify external facts.

• proofrelay.normalize_payment_proof

  Validate rail-agnostic payment or entitlement proof hashes and return the ProofRelay payment_context evidence profile. This does not charge, settle, custody funds, or verify external payment finality.

• proofrelay.build_bundle_draft

  Build a canonical, unsigned, non-attesting ProofRelay bundle draft from public-safe event hashes. The public MCP server does not sign or certify caller-provided facts.

• proofrelay.describe_stripe_entitlement_flow

  Return the agent-native Stripe checkout entitlement workflow for ProofRelay paid verification, including token, status, redemption, and replay expectations.

• proofrelay.adapt_x402_payment_proof

  Map public-safe x402 request, 402 challenge, payment payload, facilitator response, and resource response hashes into ProofRelay's payment_context evidence profile.

• proofrelay.plan_replay_rejection_test

  Return a deterministic replay rejection test plan and optionally classify observed first/replay responses. The tool does not redeem tokens or call paid endpoints.

• proofrelay.wrap_mcp_tool_evidence

  Convert hash-only MCP tool request, response, schema, authority, and payment context references into a portable ProofRelay evidence wrapper without ingesting raw prompts, outputs, credentials, or logs.

• proofrelay.map_openapi_operation_evidence

  Map public OpenAPI operation metadata and schema hashes into a ProofRelay event plan with checkpoint recommendations for paid, mutating, or relied-upon API operations.

• proofrelay.generate_paid_tool_receipt

  Generate an unsigned, hash-only paid MCP/API tool receipt draft that callers can include in a signed ProofRelay bundle. The tool does not charge, redeem, settle, or attest to external facts.

• proofrelay.scan_mcp_risk

  Return a read-only, public-metadata MCP risk score from tool descriptors, schemas, and registry claims. Use before listing, integrating, or wrapping another MCP server; it does not fetch network data, require auth, mutate systems, inspect…

• proofrelay.describe_cli_sdk_helper

  Return public-safe setup guidance for connecting MCP clients to ProofRelay and preparing hash-only evidence inputs without exposing secrets or requiring package installation.

• proofrelay.build_human_approval_receipt

  Build an unsigned, hash-only human approval receipt draft for authority, policy, and subject evidence. The tool does not create approval authority or certify the approver's identity.

• proofrelay.build_audit_pack_manifest

  Build a portable hash-only audit pack manifest from bundle, verifier, policy, and evidence hashes without uploading private files or logs.

• proofrelay.summarize_agent_action_log

  Summarize public-safe agent action log counts and hashes into a governance review profile without ingesting raw logs or traces.

• proofrelay.review_vendor_risk_profile

  Review public vendor or MCP server risk metadata for governance signals using hashes and declared boundaries only. This is not legal, security, or procurement certification.

• proofrelay.build_title_production_evidence

  Build a hash-only title production evidence profile from order, property, title-search, commitment, exception, and tax-cert hashes. The tool does not certify title status or legal sufficiency.

• proofrelay.build_closing_proof_pack

  Build a hash-only closing proof pack manifest from settlement, title, lender, funding, notary, disbursement, and approval hashes. The tool does not authorize closing or disbursement.

• proofrelay.review_wire_payoff_change

  Review hash-only wire, payoff, or disbursement change metadata for red flags and required controls without approving funds movement.

• proofrelay.map_lender_condition_evidence

  Map lender condition text, evidence, reviewer, and waiver hashes into a portable condition profile without satisfying lender conditions.

• proofrelay.compute_readiness_signal

  Compute a public-safe readiness signal from title, closing, wire, lender-condition, approval, exception, and risk hashes/counts. The tool does not certify readiness to close or fund.

• proofrelay.adapt_agent_identity_evidence

  Map Concordium, ERC-8004, DID, domain, wallet-controller, or IAM identity references into a hash-only PREP-3 input. ProofRelay accepts identity as evidence; it does not issue identity or certify people.

• proofrelay.build_registry_entry

  Build a public-safe ProofRelay Registry entry draft for an agent, API, MCP server, workflow, or adapter using only hashes and profile markers.

• proofrelay.issue_conformance_badge

  Build an unsigned ProofRelay evidence-conformance badge draft such as PREP-compatible, Verified Bundle, Verified MCP, or Replay Tested. This is not legal, security, model-safety, or platform certification.

• proofrelay.verify_signed_attestation

  Verify a legacy Ed25519 or V2 ES256 ProofRelay artifact using public key material and optional issuer/purpose pins. The tool never accepts private keys and does not sign caller claims.