# com.pcrzero/mcp

> Issue signed receipts for AI agent actions; verify any receipt offline - free, no account.

- name: com.pcrzero/mcp
- version: 0.2.0
- connection class: unknown (unknown)
- trust: 63/100
- quality: 77/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.pcrzero%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/com.pcrzero%2Fmcp/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "pcrzero": {
      "type": "http",
      "url": "https://mcp.pcrzero.com/mcp",
      "headers": {
        "Authorization": "Bearer ${PCRZERO_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${PCRZERO_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 0
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website -unreachable(8 failures) ~updated-68d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 77/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: verify_receipt (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_keyset (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); issue_receipt (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 697 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: 67 (weight 15)

- pass `deps.known_vulns`: no known advisory in 196 resolved packages
- fail `deps.mcp_sdk_version`: @modelcontextprotocol/sdk 1.30.1 has 1 known advisory (GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.31.0 or later
- pass `deps.resolvable`: @scytalex-llc/pcrzero-mcp@0.2.0, @scytalex-llc/pcrzero-mcp@0.2.0 resolved: 196 packages

- tools: 3, about 697 tokens to load them all
- tool set hash: 411a743fbec56ed657c57df9a5b85dc4
- badge: [![protogrid quality](https://protogrid.dev/badge/com.pcrzero/mcp.svg)](https://protogrid.dev/servers/com.pcrzero/mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm @scytalex-llc/pcrzero-mcp@0.2.0: resolved, 97 dependencies, MCP SDK @modelcontextprotocol/sdk 1.30.1
  - GHSA-6qxp-vccf-f47h (high) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.31.0 ``, advisory summary: "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server" https://osv.dev/vulnerability/GHSA-6qxp-vccf-f47h
- npm @scytalex-llc/pcrzero-mcp@0.2.0: resolved, 97 dependencies, MCP SDK @modelcontextprotocol/sdk 1.30.1
  - GHSA-6qxp-vccf-f47h (high) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.31.0 ``, advisory summary: "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server" https://osv.dev/vulnerability/GHSA-6qxp-vccf-f47h

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://mcp.pcrzero.com/mcp (streamable-http, auth none, reachable false, uptime30d 0.875)

## Packages

- npm @scytalex-llc/pcrzero-mcp@0.2.0 secrets: PCRZERO_API_KEY
- npm @scytalex-llc/pcrzero-mcp@0.2.0 secrets: PCRZERO_API_KEY

## Tools (3)

- `get_keyset`: Returns the current PCRZERO signing keyset — key ids, public halves, and each key's status. Public and unauthenticated: no API key, no cost, no account. This is the same document an outside party fetches to check a PCRZERO receipt without trusting us, and fetching it is how you stop taking our word for anything.
- `issue_receipt`: Adjudicates an attestation document against a policy and returns the verdict together with a signed receipt pair — the durable, independently checkable proof that this decision was made, by these keys, over this document. **Metered: every call bills one `receipt_verifications` unit against the API key configured for this server, and a `fail` verdict bills exactly like a `pass`. You are paying for the adjudication, not for the answer you wanted.** This is the only tool here that spends. If you already hold a receipt and want to know whether it is genuine, that is `verify_receipt`, which is free and needs no key.
- `verify_receipt`: Checks a PCRZERO receipt pair against the signing keyset: whether the signature holds, and whether the receipt says what it appears to say. **Free, with no API key and no account, and it stays free.** Offline by default — supply `keyset` and this call touches the network not at all; omit it and the server fetches the public keyset from api.pcrzero.com once. The result field `keyset_source` tells you which of the two happened, every time. This tool issues nothing, bills nothing, and cannot spend. It is the half of PCRZERO you never pay for.