> ## Documentation Index
> Fetch the complete documentation index at: https://docs.erdo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# SearchDatasetsAPI mirrors the erdo_search_datasets MCP tool as a REST endpoint.




## OpenAPI

````yaml /api/openapi.json get /v1/datasets-search
openapi: 3.0.0
info:
  title: Erdo API
  description: >-
    Erdo's REST API: query and write datasets, run agents, manage threads,
    integrations, pages, evals, workstreams, and experiments. Authenticate with
    a Bearer API key (erdo_api_...) or scoped token (erdo_token_...).
  version: '2026-07-25'
servers:
  - url: https://api.erdo.ai
    description: Production
security:
  - bearerAuth: []
paths:
  /v1/datasets-search:
    get:
      summary: >
        SearchDatasetsAPI mirrors the erdo_search_datasets MCP tool as a REST
        endpoint.
      operationId: GET:mcp.SearchDatasetsAPI
      parameters:
        - allowEmptyValue: true
          explode: true
          in: query
          name: query
          required: false
          schema:
            type: string
          style: form
        - allowEmptyValue: true
          explode: true
          in: query
          name: class
          required: false
          schema:
            type: string
          style: form
      responses:
        '200':
          content:
            application/json:
              schema:
                properties:
                  datasets:
                    items:
                      $ref: '#/components/schemas/mcp.MCPDataset'
                    type: array
                  total:
                    format: int64
                    type: integer
                type: object
          description: Success response
        default:
          $ref: '#/components/responses/APIError'
components:
  schemas:
    mcp.MCPDataset:
      description: |
        Converts sql.NullString fields to plain strings.
      properties:
        class:
          description: |
            legacy-unclassified, which reads as table-equivalent.
          title: >
            Class is the structural dataset class ('table' or 'scratch'). Empty
            means
          type: string
        description:
          type: string
        id:
          format: uuid
          type: string
        integration_config_key:
          type: string
        integration_id:
          description: >
            discover the source connection without relying on dataset-name or
            slug conventions; file/website datasets omit both fields.
          title: >
            Generic provenance for integration-backed datasets. Consumers use
            this to
          type: string
        name:
          type: string
        slug:
          type: string
        status:
          type: string
        sync_status:
          type: string
        type:
          type: string
      title: >
        MCPDataset is a clean representation of a dataset for MCP/REST
        consumers.
      type: object
  responses:
    APIError:
      content:
        application/json:
          schema:
            externalDocs:
              url: https://pkg.go.dev/encore.dev/beta/errs#Error
            properties:
              code:
                description: Error code
                example: not_found
                externalDocs:
                  url: https://pkg.go.dev/encore.dev/beta/errs#ErrCode
                type: string
              details:
                description: Error details
                type: object
              message:
                description: Error message
                type: string
            title: APIError
            type: object
      description: Error response
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: An Erdo API key (erdo_api_...) or scoped token (erdo_token_...).

````