SwipeHarbor lets an assistant search a stored ad archive for NewsBreak, Rumble, YouTube and Meta, read ad evidence, transcripts and funnels, and manage the user
What you can do
Search stored ads with sorting and minimum observation filters, and compare two to four ads on recorded evidence. Read a single ad's category provenance, text evidence and device context, plus its recorded destination funnel. Research advertisers or destination domains on one platform, grouped by advertiser label or landing domain. Read stored timed transcripts of Rumble video ads, paged by segment. List and save the caller's own saved ads and collections, with notes.
When to use it
Useful for paid SwipeHarbor members who want an assistant to look up archived competitor ads, compare creatives, inspect landing funnels or transcripts, and keep a personal saved-ads library while researching.
Requirements
A remote streamable HTTP endpoint at swipeharbor.com. A paid SwipeHarbor account and a bearer token sent in the Authorization header are required. No local runtime or packages.
Before you install
The Authorization bearer token is a secret and grants access to the account's saved ads and collections. save_ad writes to the user's saved ads and can change notes, so it should only be used when the user asks. Results are limited to what the archive has already recorded; nothing is fetched or transcribed on request.
Connect Authorization token credentials. They are stored privately and never shown on public pages.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.swipeharbor%2Fswipeharbor/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
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.
Read one captured ad, its recorded category provenance, text evidence, and device context. Does not fetch advertisers or generate previews.
Parametersidrequiredplatformrequired
get_funnel
Read only the recorded destination path. Unresolved, failed and unvisited steps remain explicit; this tool does not navigate or recover hidden pages.
Parametersidrequiredplatformrequired
compare_ads
Return recorded evidence for two to four distinct ads for comparison. It does not infer competitor spend or performance.
Parametersadsrequired
research_groups
Research advertisers or destination domains on one platform (newsbreak, rumble or youtube). kind=advertiser groups by the recorded advertiser label; kind=destination groups by the declared or stored landing domain. Without group, returns at most 24 groups with record counts and first/last observation dates; query filters names. With group set to a returned key, returns that group's ads (at most 12 per page) and its exact total. sort=records (default), recent or name. Follow nextCursor with the same arguments. Counts are stored records, not spend or reach.
Read the stored timed transcript of one Rumble video ad, 100 segments per page with start/end milliseconds. state shows when no transcript is ready; nothing is transcribed on request. Follow nextSegmentOffset for later segments.
ParametersidrequiredplatformrequiredsegmentOffset
list_saved_ads
List the caller's own saved ads, newest first, 12 per page, with the caller's collections. collectionId limits the page to one owned collection. Each item has the saved note and an ad summary, or ad_status=unavailable when the ad is no longer in the library. Follow nextOffset.
ParametersoffsetcollectionId
save_ad
Save one library ad to the caller's saved ads; optionally add it to one owned collection (collectionId from list_saved_ads) and set its note. Saving again is safe. A note replaces the existing note only when given. Use only when the user asks to save.
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.
