LLM Pulse Recommendations API

Recommendation runs that power the in-app Recommendations page, the endpoint that launches a new one, and the one that completes, archives or restores an item.

GitHub OpenAPI

Operations 4

GET /recommendations List recommendation runs #
POST /recommendations Launch a recommendations generation #
GET /recommendations/{id} Get recommendation run with items #
PATCH /recommendations/{id}/items/{item_id} Complete, archive or restore a recommendation item #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/llmpulse-ai:llmpulse-ai-recommendations-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

llmpulse-ai-recommendations-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: LLM Pulse Recommendations API
  description: 'REST API for the LLM Pulse AI visibility platform. Track brand mentions, citations, sentiment, and Share of Voice across AI-generated answers (ChatGPT, Perplexity, Gemini, Google AI Overviews, Google AI Mode, and optional add-on models). Includes the MCP (Model Context Protocol) endpoint for AI clients. MCP is available on every plan and during eligible trials via OAuth 2.1, with Bearer-token API keys also accepted for headless integrations on the Scale plan or above. Full machine-readable reference at https://llmpulse.ai/api-docs/llms-full.txt. An API key can be limited to one or several projects when it is created, and the set never changes. Such a key sees only those projects: any other project id, domain or name answers ERR_PROJECT_NOT_FOUND exactly like a project that does not exist, listings return only those projects'' rows, and operations on the whole account (creating or deleting a project, the project draft wizard) answer ERR_KEY_PROJECT_SCOPED. Operations carry vendor extensions: x-plan is the plan or entitlement the endpoint requires beyond an API key (growth, scale or reputation_access), x-write marks endpoints that need a read and write key, x-mcp-tool names the MCP tool that returns the same data, x-mcp-plan gives that tool''s plan where it differs, and x-rest-only explains an endpoint with no MCP tool. Parameters are read strictly, on REST and MCP alike: a value outside a documented enum, a boolean other than true, false, 1 or 0, an id or count that is not a plain positive number (12abc, 1.0 or 0), an id of a record the project does not have, or a from later than to answers 422 ERR_INVALID_PARAM naming the parameter, never an ignored filter. A listed value, in a query or a request body, matches in any letter case and is read in its documented spelling (granularity=Week reads as week, aggregation_type=BYPAGE as byPage, event_type=Mention.Created as mention.created). page and per_page keep their own rule: a value that is not a number reads as absent and an out-of-range one is clamped.'
  version: 1.97.0
  contact:
    name: LLM Pulse Support
    url: https://llmpulse.ai
    email: info@llmpulse.ai
  license:
    name: Proprietary
    url: https://llmpulse.ai/terms
servers:
- url: https://api.llmpulse.ai/api/v1
  description: Production API
security:
- BearerAuth: []
tags:
- name: Recommendations
  description: Recommendation runs that power the in-app Recommendations page, the endpoint that launches a new one, and the one that completes, archives or restores an item.
paths:
  /recommendations:
    get:
      tags:
      - Recommendations
      summary: List recommendation runs
      x-llms-description: List recommendation runs for a project (filter by recommendation_type and status).
      operationId: listRecommendations
      x-mcp-tool: list_recommendations
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      - name: recommendation_type
        in: query
        schema:
          type: string
          enum:
          - ai_visibility
          - social_community
          - brand_building
          - sentiment_reputation
      - name: status
        in: query
        schema:
          type: string
          enum:
          - pending
          - processing
          - completed
          - failed
      - $ref: '#/components/parameters/Page'
      - $ref: '#/components/parameters/PerPage'
      responses:
        '200':
          description: Paginated recommendations
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RecommendationsResponse'
    post:
      tags:
      - Recommendations
      summary: Launch a recommendations generation
      x-llms-description: Launch a new recommendations generation (async, 1-3 min; consumes the weekly recommendation budget). Poll GET /recommendations/:id.
      operationId: launchRecommendations
      x-mcp-tool: launch_recommendations
      x-write: true
      description: 'Launches a full-scope recommendations generation (async job, 1-3 minutes; poll GET /recommendations/{id} until status is completed). Consumes the project weekly recommendation-item budget: returns ERR_LIMIT_REACHED when it is exhausted or when a generation of the same type is already pending/processing. sentiment_reputation requires the Scale plan or above. Requires a `read_write` scope API key.'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - project_id
              properties:
                project_id:
                  type: integer
                recommendation_type:
                  type: string
                  enum:
                  - ai_visibility
                  - social_community
                  - brand_building
                  - sentiment_reputation
                  default: ai_visibility
      responses:
        '201':
          description: Generation launched (status pending)
        '403':
          $ref: '#/components/responses/InsufficientScope'
        '422':
          $ref: '#/components/responses/UnprocessableEntity'
  /recommendations/{id}:
    get:
      tags:
      - Recommendations
      summary: Get recommendation run with items
      x-llms-description: Detailed recommendation run with items, action steps, priorities, and resolved source references.
      operationId: getRecommendation
      x-mcp-tool: get_recommendation
      parameters:
      - $ref: '#/components/parameters/ProjectId'
      - name: id
        in: path
        required: true
        schema:
          type: integer
      - name: item_status
        in: query
        schema:
          type: string
          enum:
          - active
          - completed
          - archived
      - name: resolve_source_refs
        in: query
        schema:
          type: boolean
          default: true
      responses:
        '200':
          description: Recommendation detail with items
        '404':
          $ref: '#/components/responses/NotFound'
  /recommendations/{id}/items/{item_id}:
    patch:
      tags:
      - Recommendations
      summary: Complete, archive or restore a recommendation item
      x-llms-description: Mark one recommendation item as completed, archive it (with an optional reason later runs learn from), or move it back to active, like the buttons on the Recommendations page.
      operationId: updateRecommendationItem
      x-mcp-tool: update_recommendation_item
      x-write: true
      description: 'Moves one item of a recommendation run between `active`, `completed` and `archived`, exactly like the complete, archive and restore buttons on the Recommendations page, and stamps `status_changed_at`. When archiving, an optional `reason` teaches later runs: `not_relevant` and `too_complex` steer the next recommendations away from similar ones, and on a PR & Citation Building item that targets a domain (`metadata.domain`), `competitor` or `not_relevant` stops that site from being suggested again. The reason is stored in `metadata.archive_reason` and dropped when the item leaves `archived`. A reason with another status, an unknown one, or `competitor` on an item without a domain returns `ERR_INVALID_PARAM`. Returns the item in the shape `GET /recommendations/{id}` lists items. Requires a `read_write` scope API key and, for team members, create permission on Recommendations (the permission the page uses for these buttons).'
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: integer
        description: Recommendation run id
      - name: item_id
        in: path
        required: true
        schema:
          type: integer
        description: Item id, from the items of GET /recommendations/{id}
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - project_id
              - status
              properties:
                project_id:
                  type: integer
                status:
                  type: string
                  enum:
                  - active
                  - completed
                  - archived
                  description: completed, archived, or active to restore the item
                reason:
                  type: string
                  enum:
                  - not_relevant
                  - too_complex
                  - competitor
                  description: Optional, with status archived only. competitor only on a PR & Citation Building item that targets a domain.
      responses:
        '200':
          description: The updated item
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RecommendationItemUpdateResponse'
        '403':
          $ref: '#/components/responses/InsufficientScope'
        '404':
          $ref: '#/components/responses/NotFound'
        '422':
          $ref: '#/components/responses/UnprocessableEntity'
components:
  schemas:
    RecommendationItemUpdateResponse:
      type: object
      required:
      - project_id
      - item
      - request_id
      properties:
        project_id:
          type: integer
        item:
          $ref: '#/components/schemas/RecommendationItem'
        request_id:
          type: string
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            code:
              type: string
              enum:
              - ERR_MISSING_AUTH
              - ERR_INVALID_API_KEY
              - ERR_REVOKED_API_KEY
              - ERR_INSUFFICIENT_SCOPE
              - ERR_INSUFFICIENT_PERMISSION
              - ERR_KEY_PROJECT_SCOPED
              - ERR_PLAN_REQUIRED
              - ERR_INTEGRATION_UNAVAILABLE
              - ERR_GENERATION_FAILED
              - ERR_ACCOUNT_INACTIVE
              - ERR_DRAFT_NOT_FOUND
              - ERR_DRAFT_STATE
              - ERR_PROJECT_NOT_FOUND
              - ERR_NOT_FOUND
              - ERR_SEARCH_CONSOLE_NOT_CONNECTED
              - ERR_SEARCH_CONSOLE_ACCESS_REVOKED
              - ERR_SEARCH_CONSOLE_UPSTREAM
              - ERR_CMS_NOT_CONNECTED
              - ERR_CMS_ACCESS_REVOKED
              - ERR_CMS_REJECTED
              - ERR_CMS_UPSTREAM
              - ERR_AI_TRAFFIC_NOT_CONNECTED
              - ERR_WEB_ANALYTICS_NOT_CONNECTED
              - ERR_WEB_ANALYTICS_INVALID_QUERY
              - ERR_WEB_ANALYTICS_ACCESS_REVOKED
              - ERR_WEB_ANALYTICS_UPSTREAM
              - ERR_AGENT_TRAFFIC_NOT_CONNECTED
              - ERR_INVALID_PARAM
              - ERR_INVALID_RANGE
              - ERR_LIMIT_REACHED
              - ERR_QUOTA_EXCEEDED
              - ERR_STALE_CONTENT
              - ERR_RATE_LIMITED
            message:
              type: string
            meta:
              type: object
              description: Extra detail for some codes. A not-connected or access-revoked error from the Search Console, AI traffic, web analytics or agent traffic endpoints carries connect_url, the in-app page where the user connects or reconnects the source. A prompt write refused because a launched pitch project's prompts are fixed carries reason pitch_prompts_frozen.
        request_id:
          type: string
    RecommendationItem:
      type: object
      description: One recommendation item, in the shape GET /recommendations/{id} lists items
      required:
      - id
      - recommendation_id
      - recommendation_type
      - category
      - title
      - priority
      - status
      - position
      - action_items
      - source_refs
      - created_at
      - updated_at
      properties:
        id:
          type: integer
        recommendation_id:
          type: integer
        recommendation_type:
          type: string
        category:
          type: string
        title:
          type: string
        description:
          type:
          - string
          - 'null'
        priority:
          type: string
          enum:
          - high
          - medium
          - low
        estimated_impact:
          type:
          - string
          - 'null'
        action_items:
          type: array
          items:
            type: string
        source_refs:
          type: array
          items:
            type: string
          description: Evidence codes (e.g. P1, C2) resolved in resolved_source_refs
        status:
          type: string
          enum:
          - active
          - completed
          - archived
        status_changed_at:
          type:
          - string
          - 'null'
          format: date-time
        position:
          type: integer
        metadata:
          type: object
          additionalProperties: true
          description: Free-form details. Carries effort (low, medium or high) when the generator rated it, archive_reason (not_relevant, too_complex or competitor) on an item archived with a reason, and domain on PR & Citation Building items.
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
        resolved_source_refs:
          type: array
          items:
            type: object
            additionalProperties: true
          description: The evidence each source_refs code points to (prompt, citation or own page)
        unresolved_source_refs:
          type: array
          items:
            type: string
          description: Present only when a code points to no stored evidence
    PaginatedEnvelope:
      type: object
      description: Envelope shared by the paginated listings; each listing adds its own data rows
      required:
      - project_id
      - page
      - per_page
      - total
      - request_id
      properties:
        project_id:
          type: integer
        page:
          type: integer
        per_page:
          type: integer
        total:
          type: integer
          description: Rows matching the filters across every page
        request_id:
          type: string
    RecommendationsResponse:
      allOf:
      - $ref: '#/components/schemas/PaginatedEnvelope'
      - type: object
        required:
        - data
        properties:
          data:
            type: array
            items:
              $ref: '#/components/schemas/RecommendationSummary'
    RecommendationSummary:
      type: object
      required:
      - id
      - project_id
      - recommendation_type
      - status
      - error_message
      - generated_at
      - created_at
      - updated_at
      - total_recommendations
      - high_priority_count
      - summary
      - context
      properties:
        id:
          type: integer
        project_id:
          type: integer
        recommendation_type:
          type: string
          enum:
          - ai_visibility
          - social_community
          - brand_building
          - sentiment_reputation
        status:
          type: string
          enum:
          - pending
          - processing
          - completed
          - failed
        error_message:
          type:
          - string
          - 'null'
          description: Set only when status is failed
        generated_at:
          type:
          - string
          - 'null'
          format: date-time
          description: Null until the generation completes
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
        total_recommendations:
          type: integer
        high_priority_count:
          type: integer
        summary:
          type: object
          description: Empty until the generation completes
          properties:
            total_recommendations:
              type: integer
            high_priority_count:
              type: integer
            categories:
              type: array
              items:
                type: string
        context:
          type: object
          description: Generation context and run diagnostics as stored; empty until the generation completes. Its keys are not a stable contract
  parameters:
    ProjectId:
      name: project_id
      in: query
      required: true
      schema:
        type: integer
      description: Project ID
    PerPage:
      name: per_page
      in: query
      schema:
        type: integer
        default: 20
        maximum: 100
        minimum: 1
    Page:
      name: page
      in: query
      schema:
        type: integer
        default: 1
        minimum: 1
  responses:
    UnprocessableEntity:
      description: Invalid parameters
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              code: ERR_INVALID_PARAM
              message: invalid metrics
            request_id: abc-123
    NotFound:
      description: Resource not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              code: ERR_PROJECT_NOT_FOUND
              message: project_not_found
            request_id: abc-123
    InsufficientScope:
      description: API key lacks write permission
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            error:
              code: ERR_INSUFFICIENT_SCOPE
              message: insufficient_scope_write_required
            request_id: abc-123
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: API key authentication. Keys are managed at https://llmpulse.ai/app/api_keys (Scale plan or above). Used for the REST API and as a headless option for /mcp. A key can be limited to one or several projects when it is created; the set cannot be changed later.
    OAuth2:
      type: oauth2
      description: OAuth 2.1 with PKCE-S256 and Dynamic Client Registration. Accepted on /mcp only, available on every plan and during eligible trials. Discovery metadata at /.well-known/oauth-authorization-server.
      flows:
        authorizationCode:
          authorizationUrl: https://api.llmpulse.ai/oauth/authorize
          tokenUrl: https://api.llmpulse.ai/oauth/token
          scopes:
            mcp:read: Read data via MCP tools
            mcp:write: Create resources via MCP write tools