# SwipeHarbor

> Ad archive search (NewsBreak, Rumble, YouTube, Meta). Paid SwipeHarbor members only; token required.

- name: com.swipeharbor/swipeharbor
- version: 1.0.0
- connection class: R1 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 89/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.swipeharbor%2Fswipeharbor
- tools: https://api.protogrid.dev/v1/servers/com.swipeharbor%2Fswipeharbor/tools

**An agent can connect on its own if it already holds `SWIPEHARBOR_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "swipeharbor": {
      "type": "http",
      "url": "https://swipeharbor.com/mcp",
      "headers": {
        "Authorization": "Bearer ${SWIPEHARBOR_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${SWIPEHARBOR_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-6d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 89/100 (new)

### 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`: 4 of 4 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 747 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

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

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 5 of the 7 days needed

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

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

- tools: 4, about 747 tokens to load them all
- tool set hash: e051e3b39b7334fb7b78613d46c465a2
- tools last changed: 2026-10-16T18:44:49.760Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.swipeharbor/swipeharbor.svg)](https://protogrid.dev/servers/com.swipeharbor/swipeharbor)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-16 `compare_ads` changed (inputSchema)
- 2026-10-16 `get_funnel` changed (inputSchema)
- 2026-10-16 `get_ad_evidence` changed (inputSchema)
- 2026-10-16 `search_ads` changed (description, inputSchema)
  - before: Search stored NewsBreak/Rumble ads. Results contain at most 12 ads. sort=newest (default) orders by last observation; sort=longest_running orders by recorded observation span in whole days. minDays=7|30|90 keeps ads observed over at least that span. The span is not proof of continuous runtime or spend. Follow nextCursor with the same query, sort and filters.
  - after: Search stored NewsBreak/Rumble ads. Results contain at most 12 ads. sort=newest (default) orders by last observation; sort=longest_running orders by recorded observation span in whole days. minDays=7|30|90 keeps ads observed over at least that span. minSightings=2|5|10|25|50|100 requires at least that many stored capture observations, not impressions. Counts and spans do not prove continuous runtime or spend. These filters do not apply to transcript search. Follow nextCursor with the same query, sort and filters.
- 2026-10-15 `search_ads` changed (description, inputSchema) **meaning changed**
  - before: Search stored NewsBreak/Rumble ads. Results contain at most 12 ads. Follow nextCursor with the same query and filters.
  - after: Search stored NewsBreak/Rumble ads. Results contain at most 12 ads. sort=newest (default) orders by last observation; sort=longest_running orders by recorded observation span in whole days. minDays=7|30|90 keeps ads observed over at least that span. The span is not proof of continuous runtime or spend. Follow nextCursor with the same query, sort and filters.

Full history: https://api.protogrid.dev/v1/servers/com.swipeharbor%2Fswipeharbor/changes

## Remotes

- https://swipeharbor.com/mcp (streamable-http, auth api_key ${SWIPEHARBOR_TOKEN}, reachable true, uptime30d 1)

## Packages

_none_

## Tools (4)

- `compare_ads`: Return recorded evidence for two to four distinct ads for comparison. It does not infer competitor spend or performance.
- `get_ad_evidence`: Read one captured ad, its recorded category provenance, text evidence, and device context. Does not fetch advertisers or generate previews.
- `get_funnel`: Read only the recorded destination path. Unresolved, failed and unvisited steps remain explicit; this tool does not navigate or recover hidden pages.
- `search_ads`: Search stored NewsBreak/Rumble ads. Results contain at most 12 ads. sort=newest (default) orders by last observation; sort=longest_running orders by recorded observation span in whole days. minDays=7|30|90 keeps ads observed over at least that span. minSightings=2|5|10|25|50|100 requires at least that many stored capture observations, not impressions. Counts and spans do not prove continuous runtime or spend. These filters do not apply to transcript search. Follow nextCursor with the same query, sort and filters.