Pipeless Recommendations
Pipeless provides graph-based activity feeds and personalized recommendations from application event data.
Integration
- Vendor
- Pipeless Recommendations
- Category
- other
- Auth
- API_KEY
- Tools
- 10
- Composio slug
pipeless
Tools
- Create Event
Record one typed relationship event for Pipeless activity and recommendation algorithms. Referenced object records may be created or retained and are not removed when the event is later deleted.
- Create Events Batch
Record 1 to 10 relationship events in one Pipeless request. Referenced object records may be created or retained and are not removed when the events are later deleted.
- Delete Eventdestructive
Delete event records matching an exact start object, relationship type and timestamp, and end object. Wildcard deletion is not supported by this tool.
- List Activity Feed
Return one cursor-controlled chronological page of actions by objects followed by a specified object.
- List Object Activity
Return one cursor-controlled page of incoming or outgoing relationship activity involving a specific object.
- List Recent Events
Return the most recent events sent to the app, up to the requested limit; Pipeless provides no continuation cursor for this read.
- List Recommended Content
Return a bounded personalized list of content recommendations for an object using configurable positive, negative, tag, author, follow, and dismissal signals.
- List Related Content
Return content objects related to a target content object using optional tag and collaborative-interaction signals.
- List Users To Follow
Return a bounded personalized list of user or account objects that the specified object may want to follow.
- Rank Content
Rank a supplied set of content IDs for an object and report which IDs Pipeless could rank.
Setup
- Create or open a Switchy Project.
- Open Integrations and connect Pipeless Recommendations.
- Authorise through api_key. Switchy stores the connection against your org.
- Everyone in the Project can now @-mention the Pipeless Recommendations tools in chat.
What teammates see: by default, memories from Pipeless Recommendations are scoped to the Project (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Projects have used this MCP together with a given model.