# co.pixelcove/citation-tracker

> Checks whether AI search engines cite your domain for a prompt. From $0.15/call via x402 or Stripe.

- name: co.pixelcove/citation-tracker
- version: 0.2.1
- connection class: R0 (autonomous)
- trust: 100/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/co.pixelcove%2Fcitation-tracker
- tools: https://api.protogrid.dev/v1/servers/co.pixelcove%2Fcitation-tracker/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "citation-tracker": {
      "type": "http",
      "url": "https://citation-tracker.pixelcove.co/mcp",
      "headers": {
        "Authorization": "Bearer ${CITATION_TRACKER_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${CITATION_TRACKER_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-100% +updated-1d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (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: citation_tracker_check_one (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); citation_tracker_check (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); citation_tracker_shortlist_gate (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,073 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`: 1 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: 8, about 2,073 tokens to load them all
- tool set hash: d13c76dfdf341e3bca0753c0089d2e2f
- tools last changed: 2026-09-25T16:09:52.913Z
- badge: [![protogrid quality](https://protogrid.dev/badge/co.pixelcove/citation-tracker.svg)](https://protogrid.dev/servers/co.pixelcove/citation-tracker)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-25 `citation_tracker_check_one` added
  - Sends one prompt to one search assistant (Perplexity, OpenAI or Gemini) and reports whether it cites your target domains: cited status, citation count, cited domains, model, and a structured error. For Claude, or several engines in one call, use citation_tracker_check. Paid, $0.15/call; read-only and safe to retry.

Full history: https://api.protogrid.dev/v1/servers/co.pixelcove%2Fcitation-tracker/changes

## Remotes

- https://citation-tracker.pixelcove.co/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (8)

- `citation_tracker_check`: Sends one prompt to 1 to 4 search assistants (Perplexity, OpenAI, Anthropic, Gemini) and reports whether each cites your target domains: cited status, citation count, cited domains, model, and a structured error per engine. Started concurrently; a failed engine returns `cited: null` and does not block the others (PD7). Paid, $0.75/call; read-only and safe to retry.
- `citation_tracker_check_one`: Sends one prompt to one search assistant (Perplexity, OpenAI or Gemini) and reports whether it cites your target domains: cited status, citation count, cited domains, model, and a structured error. For Claude, or several engines in one call, use citation_tracker_check. Paid, $0.15/call; read-only and safe to retry.
- `citation_tracker_check_perplexity`: Sends one prompt to Perplexity (sonar) and reports whether it cites your target domains, with citation count and cited domains. Free: one call per caller and 100 calls total per UTC day; both limits fail closed. A real live evaluation before you pay for citation_tracker_check.
- `citation_tracker_monitor_30`: Buys a monitor: 30 recurring runs of citation_tracker_check for one prompt and 1 to 10 target domains, daily or weekly. The first run happens now and is returned. Later runs are read with citation_tracker_monitor_status using the returned monitor_id (the only credential; it is not recoverable). Each run flags which target domains changed since the last run. Paid once, $18 for the term ($0.6/check); no refund of unused runs; cancel any time with citation_tracker_monitor_cancel. Retains the prompt, domains and results until 30 days after the last run or until cancelled.
- `citation_tracker_monitor_7`: Buys a monitor: 7 recurring runs of citation_tracker_check for one prompt and 1 to 10 target domains, daily or weekly. The first run happens now and is returned. Later runs are read with citation_tracker_monitor_status using the returned monitor_id (the only credential; it is not recoverable). Each run flags which target domains changed since the last run. Paid once, $4.2 for the term ($0.6/check); no refund of unused runs; cancel any time with citation_tracker_monitor_cancel. Retains the prompt, domains and results until 30 days after the last run or until cancelled.
- `citation_tracker_monitor_cancel`: Stops a monitor and deletes its prompt, domains and results. Unused runs are not refunded. Free. Needs the monitor_id.
- `citation_tracker_monitor_status`: Reads a monitor: remaining runs, next run time, and every run so far (most recent first) with the same per-engine rows as citation_tracker_check plus changed_since_last per target domain. Free. Needs the monitor_id.
- `citation_tracker_shortlist_gate`: Checks whether ChatGPT would search the web for one prompt and whether its first search query names any of your supplied brand or product terms (whole-word match). Use it to gate a prompt before spending on citation_tracker_check. Paid, $0.20/call; read-only and safe to retry.