Read-only verifier for 25 ProofRelay MCP tools and non-confidential evidence bundles.
Scored across 26 tools
Most tools have a recognizable target (x402, Stripe, title, closing, wire, MCP risk, bundles), and descriptions work hard to separate similar items. But several families overlap heavily: adapt_agent_identity_evidence / adapt_x402_payment_proof / map_lender_condition_evidence / map_openapi_operation_evidence / wrap_mcp_tool_evidence all convert external data into hash-only profiles, and normalize_payment_proof vs adapt_x402_payment_proof blur. build_bundle_draft vs build_audit_pack_manifest vs build_closing_proof_pack also require careful reading to distinguish.
Names are consistently snake_case verb_noun with a uniform proofrelay. namespace prefix, which is very predictable. Minor deviation: near-synonymous verbs (adapt_, map_, wrap_, build_) are used for structurally similar operations, so the verb does not reliably signal the operation type.
26 tools exceeds the threshold where a single set stays scannable, and the domain is fragmented across many verticals (identity, x402, Stripe, title/closing, MCP risk, badges). Several builders are near-siblings that could be one parameterized tool with a profile argument.
Coverage is broad on the draft-and-verify side: build evidence profiles, build receipts/badges/registry entries, verify bundles and attestations, plus guidance tools. But the surface is build-heavy with no retrieval, listing, revocation, or finalization/signing step, so an agent that produces a draft has nowhere to go within this server to read or complete it.
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.
Inputs: identity (required). Returns: object
Map public-safe x402 request, 402 challenge, payment payload, facilitator response, and resource response hashes into ProofRelay's payment_context evidence profile.
Inputs: x402 (required). Returns: object
Build a portable hash-only audit pack manifest from bundle, verifier, policy, and evidence hashes without uploading private files or logs.
Inputs: audit_pack (required). Returns: object
Build an unsigned V2 draft from explicit tenant/service IDs and hash-only event evidence, not raw payloads. The producer must sign events locally and recompute bundle_hash before verification. No V1 draft inputs, server signing or certification. Hash adapters accept bare or sha256:-prefixed SHA-256.
Inputs: draft (required). Returns: object
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.
Inputs: closing_pack (required). Returns: object
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.
Inputs: approval (required). Returns: object
Build a public-safe ProofRelay Registry entry draft for an agent, API, MCP server, workflow, or adapter using only hashes and profile markers. Accepts bare or sha256:-prefixed hashes, normalized losslessly to bare hex. Hash presence and eligible badge labels are not verification or authority.
Inputs: entry (required). Returns: object
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.
Inputs: title_evidence (required). Returns: object
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.
Inputs: readiness (required). Returns: object
Return public-safe setup guidance for connecting MCP clients to ProofRelay and preparing hash-only evidence inputs without exposing secrets or requiring package installation.
Inputs: helper (required). Returns: object
Return the agent-native Stripe checkout entitlement workflow for ProofRelay paid verification, including token, status, redemption, and replay expectations.
Inputs: no named parameters. Returns: object
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.
Inputs: receipt (required). Returns: object
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.
Inputs: no named parameters. Returns: object
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.
Inputs: badge (required). Returns: object
Map lender condition text, evidence, reviewer, and waiver hashes into a portable condition profile without satisfying lender conditions.
Inputs: condition (required). Returns: object
Map public OpenAPI operation metadata and schema hashes into a ProofRelay event plan with checkpoint recommendations for paid, mutating, or relied-upon API operations.
Inputs: operation (required). Returns: object
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.
Inputs: payment_proof (required). Returns: object
Return a deterministic replay rejection test plan and optionally classify caller-reported responses. Confirmation requires first 2xx without error, then 409 AND entitlement_replay (Stripe) or x402_payment_replay (x402). Missing, contradictory or unknown-protocol evidence is inconclusive. Does not redeem tokens or call paid endpoints.
Inputs: replay_test (required). Returns: object
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.
Inputs: workflow_context (required). Returns: object
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.
Inputs: vendor (required). Returns: object
Review hash-only wire, payoff, or disbursement change metadata for red flags and required controls without approving funds movement.
Inputs: wire_change (required). Returns: object
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 source code, or certify vulnerability status.
Inputs: risk_scan (required). Returns: object
Summarize public-safe agent action log counts and hashes into a governance review profile without ingesting raw logs or traces.
Inputs: action_log (required). Returns: object
Verify a submitted non-confidential ProofRelay V2 evidence bundle for hash integrity, monotonic ordering, signatures, and chain continuity. Legacy V1 is available only in non-public runtime roles. Caller-supplied public keys do not establish registered producer identity or authority. The tool does not charge, settle, mutate storage, or certify external facts.
Inputs: bundle (required), public_keys, require_chain, require_signature. Returns: object
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.
Inputs: verification (required). Returns: object
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.
Inputs: tool_evidence (required). Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Free, no-account verification of KeyHalve-sealed documents. Read-only; never receives keys.
Read-only Remote MCP for externally grounded AI agent trust receipts.
Read-only MCP server checks and quote verification, free and keyless; results signed and publicly lo
Read-only XRP Ledger MCP tools with proof-annotation envelopes and signed daily snapshots.
Add one secure layer between your agents and this server.
