# ScopeProof

> Machine-verifiable authorization checks for autonomous AI agents.

- name: io.github.davisvillelabs/scopeproof
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 79/100 flags: no-repository
- quality: 86/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.davisvillelabs%2Fscopeproof
- tools: https://api.protogrid.dev/v1/servers/io.github.davisvillelabs%2Fscopeproof/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "scopeproof": {
      "type": "http",
      "url": "https://scopeproof.davisvillelabs.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 45
- drivers: +website +reachable +uptime-94% +updated-24d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 86/100 (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: 100 (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
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 329 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 24 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

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

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 329 tokens to load them all
- tool set hash: 7e37b891172db9eac47a1f55fa2eed11
- tools last changed: 2026-10-09T09:07:54.630Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.davisvillelabs/scopeproof.svg)](https://protogrid.dev/servers/io.github.davisvillelabs/scopeproof)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-09 `verify_receipt` removed
  - Verify the cryptographic integrity of one ScopeProof receipt without exposing the server signing key. Free and repeatable.
- 2026-10-09 `preflight` removed
  - Validate whether a structured authority envelope contains enough explicit constraints for ScopeProof to evaluate one action. Free. Returns no substantive authorization verdict and accepts no credentials, raw prompts, arbitrary request bodies, or secrets.
- 2026-10-09 `check_action` removed
  - Determine whether one proposed action is within explicitly supplied authority. $0.01 stablecoin machine payment. Returns within_scope, outside_scope, or review_required plus deterministic reason codes, policy/action digests, and a tamper-evident receipt. This is scope enforcement against supplied authority, not identity verification, legal authorization, or a safety guarantee.
- 2026-10-09 `scopeproof.verify_receipt` added
  - Free cryptographic verification of a ScopeProof authorization receipt.
- 2026-10-09 `scopeproof.check_action` added
  - Paid $0.01 deterministic comparison of one proposed action against one supplied authority envelope. Returns within_scope, outside_scope, or review_required plus an Ed25519-signed receipt. ScopeProof does not authenticate the authority issuer, grant platform permission, replace Muse or another host approval check, or execute or fetch the target.
- 2026-10-09 `scopeproof.preflight` added
  - Free structural and secret-safety validation. Does not return an authorization verdict.
- 2026-09-30 `scopeproof.verify_receipt` removed
  - Free cryptographic verification of a ScopeProof authorization receipt.
- 2026-09-30 `scopeproof.preflight` removed
  - Free structural and secret-safety validation. Does not return an authorization verdict.
- 2026-09-30 `scopeproof.check_action` removed
  - Paid $0.01 deterministic check of one proposed action against one supplied authority envelope. Returns within_scope, outside_scope, or review_required plus an Ed25519-signed receipt. ScopeProof does not authenticate the authority issuer and does not execute or fetch the target.
- 2026-09-30 `verify_receipt` added
  - Verify the cryptographic integrity of one ScopeProof receipt without exposing the server signing key. Free and repeatable.

Full history: https://api.protogrid.dev/v1/servers/io.github.davisvillelabs%2Fscopeproof/changes

## Remotes

- https://scopeproof.davisvillelabs.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9444444)

## Packages

_none_

## Tools (3)

- `scopeproof.check_action`: Paid $0.01 deterministic comparison of one proposed action against one supplied authority envelope. Returns within_scope, outside_scope, or review_required plus an Ed25519-signed receipt. ScopeProof does not authenticate the authority issuer, grant platform permission, replace Muse or another host approval check, or execute or fetch the target.
- `scopeproof.preflight`: Free structural and secret-safety validation. Does not return an authorization verdict.
- `scopeproof.verify_receipt`: Free cryptographic verification of a ScopeProof authorization receipt.