SwipeHarbor
Ad archive search (NewsBreak, Rumble, YouTube, Meta). Paid SwipeHarbor members only; token required.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"swipeharbor": {
"url": "https://swipeharbor.com/mcp"
}
}
}Remote endpoints
https://swipeharbor.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (4)
🟢search_ads(query, platform, format, category, subcategory, ...)
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.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 120
},
"platform": {
"type": "string",
"enum": [
"all",
"newsbreak",
"rumble",
"youtube"
]
},
"format": {
"type": "string",
"enum": [
"all",
"image",
"video"
]
},
"category": {
"type": "string",
"maxLength": 64
},
"subcategory": {
"type": "string",
"maxLength": 64
},
"cursor": {
"type": "string",
"maxLength": 2048
},
"days": {
"type": "string",
"enum": [
"all",
"7",
"30",
"90"
]
},
"sort": {
"type": "string",
"enum": [
"newest",
"longest_running"
]
},
"minDays": {
"type": "string",
"enum": [
"all",
"7",
"30",
"90"
]
},
"minSightings": {
"type": "string",
"enum": [
"all",
"2",
"5",
"10",
"25",
"50",
"100"
]
},
"searchIn": {
"type": "string",
"enum": [
"all",
"transcript"
]
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_ad_evidence(platform, id)
Read one captured ad, its recorded category provenance, text evidence, and device context. Does not fetch advertisers or generate previews.
Input Schema
{
"type": "object",
"properties": {
"platform": {
"type": "string",
"enum": [
"newsbreak",
"rumble",
"youtube"
]
},
"id": {
"type": "string",
"minLength": 1,
"maxLength": 512
}
},
"required": [
"platform",
"id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_funnel(platform, id)
Read only the recorded destination path. Unresolved, failed and unvisited steps remain explicit; this tool does not navigate or recover hidden pages.
Input Schema
{
"type": "object",
"properties": {
"platform": {
"type": "string",
"enum": [
"newsbreak",
"rumble",
"youtube"
]
},
"id": {
"type": "string",
"minLength": 1,
"maxLength": 512
}
},
"required": [
"platform",
"id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢compare_ads(ads)
Return recorded evidence for two to four distinct ads for comparison. It does not infer competitor spend or performance.
Input Schema
{
"type": "object",
"properties": {
"ads": {
"type": "array",
"items": {
"type": "object",
"properties": {
"platform": {
"type": "string",
"enum": [
"newsbreak",
"rumble",
"youtube"
]
},
"id": {
"type": "string",
"minLength": 1,
"maxLength": 512
}
},
"required": [
"platform",
"id"
],
"additionalProperties": false
},
"minItems": 2,
"maxItems": 4
}
},
"required": [
"ads"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence