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., "@KeyHalve verify-MCP Verify this KeyHalve-sealed document: https://validpay.example/seal/abc123"
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.
Free, public, no-account MCP server that lets any AI verify KeyHalve-sealed documents — from any platform on the rail (ValidPay, CheckBooks, …). Seal = the door (a platform's paid MCP). Verify = the room (this one, free forever).
Endpoint: https://mcp.keyhalve.com/mcp (Streamable HTTP, stateless)
Tools: keyhalve_verify · keyhalve_status · keyhalve_explain — all read-only, no auth
This server never receives decryption keys. A verify URL carries the holder's key share in
the #key= fragment; parseInput discards any fragment before any other logic runs, and the
response says so. Verification here covers everything provable without the key:
Check | Meaning |
status | active / revoked (with reason) on the issuing platform |
ciphertext integrity | SHA-256 of the served ciphertext = commitment recorded at issuance (v2) |
rail attestation | Ed25519-verified against the pinned rail key; dual-sign content binding when present |
time lock | validity window judged client-side (Patent D semantics) |
issuer trust | fail-closed: |
Reading the sealed contents still happens only in the holder's browser — exactly like the web
verifier. The overall verdict fails closed: any failed check → FAILED — DO NOT TRUST.
Related MCP server: TrustAtom MCP Server
Zero runtime dependencies. WebCrypto only; the whole protocol layer is hand-auditable.
Same reasoning as the pinned-key rail client in keyhalve-website.
Stateless. No sessions, no SSE, no KV, no cookies; every POST gets application/json.
Request bodies are never logged.
Tenant-neutral. Platforms come from the same manifest data as the web verifier
(TENANT_MANIFEST in src/verifier.ts); onboarding a platform = one data entry.
Fail closed. Unreachable rail, malformed share, partial dual-sign binding, unknown id prefix — all report NOT verified, never a soft pass.
npm ci
npm run typecheck && npm test # 32 tests
npm run dev # wrangler devDeploys are manual (deploy.yml via workflow_dispatch, same discipline as rail/console).
Needs the CLOUDFLARE_API_TOKEN repo secret; the route mcp.keyhalve.com is a custom domain
on the business CF account (same account as the watchdog scheduler).
Submitting to the Claude Connectors Directory / ChatGPT App Directory is an outward-facing step — prepared separately, goes out only on Mike's go.
Directory-listing assets live in this repo — reuse them, don't invent copy:
llms-install.md — AI-agent install steps (Cline's AI-driven install; also the canonical per-client snippets).
glama.json — Glama claim file (maintainers; their live schema is maintainers-only).
assets/icon-400.png — 400×400 icon (white split-circle glyph on Ink #0E1116, from the brand kit).
Descriptions must stay byte-consistent with src/tools.ts and pass the approved-claims register (no "split key", no "tamper-proof", no issuer-identity claims).
This server cannot be deployed
Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.
Confidential AI execution with a post-quantum receipt on every job — verifiable by anyone.
AI document intelligence: extract, summarize, claim-check, notarize, and signed action receipts.
Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.
