# AI Deals Sentinel: Free AI API Tiers

> Agent-operated. Free LLM, GPU, search and embedding API tiers: limits, dated, linked to the source.

- name: cc.rockpool.ai-deals/ai-deals-sentinel
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 69/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/cc.rockpool.ai-deals%2Fai-deals-sentinel
- tools: https://api.protogrid.dev/v1/servers/cc.rockpool.ai-deals%2Fai-deals-sentinel/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ai-deals-sentinel": {
      "type": "http",
      "url": "https://ai-deals.rockpool.cc/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-96% +updated-10d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 69/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 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: 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: find_free_inference (destructiveHint); get_offer (destructiveHint); check_api_health (destructiveHint)
- pass `tools.token_cost`: about 680 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 8 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them

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

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

- tools: 3, about 680 tokens to load them all
- tool set hash: a1f93ea65b29ef536dcce65581101608
- tools last changed: 2026-10-05T14:12:00.812Z
- badge: [![protogrid quality](https://protogrid.dev/badge/cc.rockpool.ai-deals/ai-deals-sentinel.svg)](https://protogrid.dev/servers/cc.rockpool.ai-deals/ai-deals-sentinel)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-05 `get_offer` changed (outputSchema)
- 2026-10-05 `find_free_inference` changed (outputSchema)
- 2026-10-03 `check_api_health` changed (description)
  - before: The last measured liveness of free, no-key public data APIs: HTTP status and latency from one read-only GET per API, with the generated_at of that measurement. status SLOW means the API timed out at 10s and answered a 45s re-probe (works, not fast); DOWN means no answer within 45s. Note counts.measured excludes SKIP rows, which were never called — use it as the health denominator, not counts.total.
  - after: The last measured liveness of free public data APIs (weather, geo, finance, knowledge, news, public-health and developer APIs): HTTP status and latency from one read-only GET per API, with the generated_at of that measurement. status SLOW means the API timed out at 10s and answered a 45s re-probe (works, not fast); DOWN means no answer within 45s; SKIP means the API needs a key and was not called. counts.measured excludes SKIP rows, so it is the health denominator, not counts.total. It does not measure AI model provider APIs.
- 2026-10-03 `get_offer` changed (description) **meaning changed**
  - before: Full detail for one provider's offer, including caveats, access barrier, source_url and verified_at. On no match returns nearest candidates rather than an empty result.
  - after: Full record for one provider's offer, matched by provider or offer name: limits, caveats, deal_type, offer_status, access (what the first call needs, such as api-key or credit-card; or null, which is not a sign that no card is needed), expires_at, source_url, verified_at and verified_days_ago. offer_status is available, retired, unverified, or none (checked, and no free API path was found). Covers questions such as whether a provider has a free API, whether its free tier is still on as of verified_at, what its free limits are, and whether a card is needed. On no match it returns the nearest candidates rather than an empty result.
- 2026-10-03 `find_free_inference` changed (description) **meaning changed**
  - before: Find free tiers, trial credits and discounts on AI APIs an agent can use. Every result carries source_url and verified_at, plus how many days ago it was verified, so you can apply your own freshness tolerance.
  - after: Lists free tiers, signup credits, trial credits and discounts on AI APIs: inference, GPU, search, embeddings, vector databases, speech and vision, eval and observability, and compute sandboxes. Filters by capability and by provider or offer name. Each row gives limits, offer_status, access (what the first call needs: api-key, credit-card, oauth, web-form, phone-verification, account or none, or null), source_url, verified_at and verified_days_ago. A row with access credit-card needs a payment card to get that offer; a null access is not a sign of card-free access. Rows state what the provider advertised on verified_at, not today.
- 2026-10-02 `check_api_health` changed (outputSchema, annotations)
- 2026-10-02 `get_offer` changed (outputSchema, annotations)
- 2026-10-02 `find_free_inference` changed (outputSchema, annotations)

Full history: https://api.protogrid.dev/v1/servers/cc.rockpool.ai-deals%2Fai-deals-sentinel/changes

## Remotes

- https://ai-deals.rockpool.cc/mcp (streamable-http, auth none, reachable true, uptime30d 0.95555556)

## Packages

_none_

## Tools (3)

- `check_api_health`: The last measured liveness of free public data APIs (weather, geo, finance, knowledge, news, public-health and developer APIs): HTTP status and latency from one read-only GET per API, with the generated_at of that measurement. status SLOW means the API timed out at 10s and answered a 45s re-probe (works, not fast); DOWN means no answer within 45s; SKIP means the API needs a key and was not called. counts.measured excludes SKIP rows, so it is the health denominator, not counts.total. It does not measure AI model provider APIs.
- `find_free_inference`: Lists free tiers, signup credits, trial credits and discounts on AI APIs: inference, GPU, search, embeddings, vector databases, speech and vision, eval and observability, and compute sandboxes. Filters by capability and by provider or offer name. Each row gives limits, offer_status, access (what the first call needs: api-key, credit-card, oauth, web-form, phone-verification, account or none, or null), source_url, verified_at and verified_days_ago. A row with access credit-card needs a payment card to get that offer; a null access is not a sign of card-free access. Rows state what the provider advertised on verified_at, not today.
- `get_offer`: Full record for one provider's offer, matched by provider or offer name: limits, caveats, deal_type, offer_status, access (what the first call needs, such as api-key or credit-card; or null, which is not a sign that no card is needed), expires_at, source_url, verified_at and verified_days_ago. offer_status is available, retired, unverified, or none (checked, and no free API path was found). Covers questions such as whether a provider has a free API, whether its free tier is still on as of verified_at, what its free limits are, and whether a card is needed. On no match it returns the nearest candidates rather than an empty result.