# Consumer Product Recall Evidence

> Match consumer products to official CPSC recalls and purchase source-linked evidence.

- name: io.github.ThryveBaseline/agent-services-008
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 74/100 flags: no-repository
- quality: 94/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.ThryveBaseline%2Fagent-services-008
- tools: https://api.protogrid.dev/v1/servers/io.github.ThryveBaseline%2Fagent-services-008/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agent-services-008": {
      "type": "http",
      "url": "https://experiment-008-production.up.railway.app/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 35
- drivers: +reachable +uptime-99% ~updated-48d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 94/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000)

### 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: 86 (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
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: build_product_recall_evidence (destructiveHint); match_product_recall (destructiveHint); resolve_consumer_product (destructiveHint)
- pass `tools.token_cost`: about 266 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: n/a (weight 15)

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

- tools: 3, about 266 tokens to load them all
- tool set hash: eb017cba867f89a9a718651743f21780
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.ThryveBaseline/agent-services-008.svg)](https://protogrid.dev/servers/io.github.ThryveBaseline/agent-services-008)
- 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._

## Remotes

- https://experiment-008-production.up.railway.app/mcp (streamable-http, auth none, reachable true, uptime30d 0.991453)

## Packages

_none_

## Tools (3)

- `build_product_recall_evidence`: Purchase a $0.20 CPSC hazard/remedy evidence package; no individual-unit remedy completion or broader safety conclusion is made.
- `match_product_recall`: Purchase a $0.03 exact CPSC recall-notice match result.
- `resolve_consumer_product`: Free: conservatively match an exact model to a published CPSC recall notice; absence is not proof of safety or no recall.