# io.github.fishcoco-code/guardrly-mcp

> Non-invasive AI Agent monitoring — audit every API call to Shopify, Meta Ads, and more

- name: io.github.fishcoco-code/guardrly-mcp
- version: 0.1.3
- connection class: L0 (run_local_package)
- trust: 76/100
- quality: –/100 (not scored)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.fishcoco-code%2Fguardrly-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.fishcoco-code%2Fguardrly-mcp/tools

**Runs on your machine: something must execute the package.** Only local packages are published (npm, PyPI, OCI, …). The registry never executes them, so tools are unknown until you run it.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "guardrly-mcp": {
      "command": "uvx",
      "args": [
        "guardrly==0.1.3"
      ],
      "env": {
        "GUARDRLY_API_KEY": "${GUARDRLY_API_KEY}",
        "GUARDRLY_API_URL": "https://api.guardrly.com",
        "HMAC_SECRET": "${HMAC_SECRET}"
      }
    }
  }
}
```

Placeholders to fill: `${GUARDRLY_API_KEY}`, `${HMAC_SECRET}`.

## Trust

- hygiene: 100
- liveness: n/a
- freshness: 45
- provenance: 80
- drivers: +repository +namespace-matches-repo ~liveness-unmeasured -stale-186d
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality –/100 (not scored)

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### 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: n/a (weight 30)

- n/a `tools.descriptions`, `tools.description_length`, `tools.schemas`, `tools.annotations`, `tools.directory_hints`, `tools.token_cost`, `tools.api_dump`: tool list unknown (behind auth, not probed, or empty)

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

- n/a `stability.changes`, `stability.rug_pull`: tool list unknown

### dependencies: 83 (weight 15)

- warn `deps.known_vulns`: 2 advisories of lower severity or without a published fix: GHSA-wj6h-64fc-37mp in ecdsa@0.19.2 (indirect, no fix yet), GHSA-3qf3-8w2g-rqmx in python-jose@3.5.0 (direct, no fix yet)
- pass `deps.mcp_sdk_version`: mcp 2.2.0, no known advisory
- pass `deps.resolvable`: guardrly@0.1.3 resolved: 78 packages

- tools: unknown
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.fishcoco-code/guardrly-mcp.svg)](https://protogrid.dev/servers/io.github.fishcoco-code/guardrly-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

- pypi guardrly@0.1.3: resolved, 77 dependencies, MCP SDK mcp 2.2.0
  - GHSA-3qf3-8w2g-rqmx (critical) in `` python-jose@3.5.0 ``, direct, no fix yet, advisory summary: "python-jose algorithm confusion guard bypassed by DER-encoded public keys" https://osv.dev/vulnerability/GHSA-3qf3-8w2g-rqmx
  - GHSA-wj6h-64fc-37mp (high) in `` ecdsa@0.19.2 ``, indirect, no fix yet, advisory summary: "Minerva timing attack on P-256 in python-ecdsa" https://osv.dev/vulnerability/GHSA-wj6h-64fc-37mp

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

_none_

## Packages

- pypi guardrly@0.1.3 secrets: GUARDRLY_API_KEY, HMAC_SECRET

## Tools (0)

_none observed_