retrieveSources

Retrieve relevant content sources from Graphlit knowledge base. Do not use for retrieving content by content identifier - retrieve content resource instead, with URI 'contents://{id}'. Accepts a search prompt, optional recency filter (defaults to all time), and optional content type and file type filters. Also accepts optional feed and collection identifiers to filter content by. Prompt should be optimized for vector search, via text embeddings. Rewrite prompt as appropriate for higher relevance to search results. Returns the ranked content sources, including their content resource URI to retrieve the complete Markdown text.

Input Schema

Name	Required	Description
`collections`	No	Collection identifiers to filter content by, optional.
`contentType`	No	Content type filter, optional. One of: Email, Event, File, Issue, Message, Page, Post, Text.
`feeds`	No	Feed identifiers to filter content by, optional.
`fileType`	No	File type filter, optional. One of: Animation, Audio, Code, Data, Document, Drawing, Email, Geometry, Image, Package, PointCloud, Shape, Video.
`inLast`	No	Recency filter for content 'in last' timespan, optional. Should be ISO 8601 format, for example, 'PT1H' for last hour, 'P1D' for last day, 'P7D' for last week, 'P30D' for last month. Doesn't support weeks or months explicitly.
`prompt`	Yes	Search prompt for content retrieval.

Input Schema (JSON Schema)

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "collections": {
      "description": "Collection identifiers to filter content by, optional.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "contentType": {
      "description": "Content type filter, optional. One of: Email, Event, File, Issue, Message, Page, Post, Text.",
      "enum": [
        "EMAIL",
        "EVENT",
        "FILE",
        "ISSUE",
        "MESSAGE",
        "PAGE",
        "POST",
        "TEXT"
      ],
      "type": "string"
    },
    "feeds": {
      "description": "Feed identifiers to filter content by, optional.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "fileType": {
      "description": "File type filter, optional. One of: Animation, Audio, Code, Data, Document, Drawing, Email, Geometry, Image, Package, PointCloud, Shape, Video.",
      "enum": [
        "ANIMATION",
        "AUDIO",
        "CODE",
        "DATA",
        "DOCUMENT",
        "DRAWING",
        "EMAIL",
        "GEOMETRY",
        "IMAGE",
        "MANIFEST",
        "PACKAGE",
        "POINT_CLOUD",
        "SHAPE",
        "UNKNOWN",
        "VIDEO"
      ],
      "type": "string"
    },
    "inLast": {
      "description": "Recency filter for content 'in last' timespan, optional. Should be ISO 8601 format, for example, 'PT1H' for last hour, 'P1D' for last day, 'P7D' for last week, 'P30D' for last month. Doesn't support weeks or months explicitly.",
      "type": "string"
    },
    "prompt": {
      "description": "Search prompt for content retrieval.",
      "type": "string"
    }
  },
  "required": [
    "prompt"
  ],
  "type": "object"
}

graphlit-mcp-server