Kagura AI

Kagura AI Retrieval Feedback API

Agent Memory Substrate (epic #885): append-only retrieval-helpful signal per (context, memory). Read-adjacent (Viewer+); collected but not auto-acted-on until the golden eval gate (#344) is green. REST companion to the feedback MCP tool.

GitHub OpenAPI

Operations 2

POST /api/v1/contexts/{context_id}/feedback Record Feedback #
POST /api/v1/contexts/{context_id}/host-feedback Record Host Feedback #

Specifications

⚙
OpenAPI
https://artifacts.apis.io/kagura-ai-com/openapi/kagura-ai-com-retrieval-feedback-api-openapi.yml

Schemas & Data

📊
JSONSchema
https://artifacts.apis.io/kagura-ai-com/json-schema/kagura-ai-com-context-search-config-response-schema.json
📊
JSONSchema
https://artifacts.apis.io/kagura-ai-com/json-schema/kagura-ai-com-remember-request-schema.json
📊
JSONSchema
https://artifacts.apis.io/kagura-ai-com/json-schema/kagura-ai-com-context-search-config-update-schema.json
📊
JSONSchema
https://artifacts.apis.io/kagura-ai-com/json-schema/kagura-ai-com-plan-tier-feature-schema.json
📊
JSONSchema
https://artifacts.apis.io/kagura-ai-com/json-schema/kagura-ai-com-patch-memory-request-schema.json
📊
JSONSchema
https://artifacts.apis.io/kagura-ai-com/json-schema/kagura-ai-com-workspace-connector-create-request-schema.json

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/kagura-ai-com:kagura-ai-com-retrieval-feedback-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. See our Privacy Policy and Terms.

GitHub Google LinkedIn

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

OpenAPI Specification

kagura-ai-com-retrieval-feedback-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Kagura Memory Cloud Retrieval Feedback API
  description: Universal AI Memory Platform - Remote MCP Server + Web Management
  version: 0.158.1
tags:
- name: retrieval-feedback
  description: 'Agent Memory Substrate (epic #885): append-only retrieval-helpful signal per (context, memory). Read-adjacent (Viewer+); collected but not auto-acted-on until the golden eval gate (#344) is green. REST companion to the feedback MCP tool.'
paths:
  /api/v1/contexts/{context_id}/feedback:
    post:
      tags:
      - retrieval-feedback
      summary: Record Feedback
      description: Record an append-only retrieval-feedback event for a recalled memory.
      operationId: record_feedback_api_v1_contexts__context_id__feedback_post
      parameters:
      - name: context_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Context Id
      - name: authorization
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Authorization
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/FeedbackRequest'
      responses:
        '201':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/FeedbackResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/contexts/{context_id}/host-feedback:
    post:
      tags:
      - retrieval-feedback
      summary: Record Host Feedback
      description: Record a server-stamped host verdict from a trusted operator.
      operationId: record_host_feedback_api_v1_contexts__context_id__host_feedback_post
      parameters:
      - name: context_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Context Id
      - name: authorization
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Authorization
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/HostFeedbackRequest'
      responses:
        '201':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/FeedbackResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    HostFeedbackRequest:
      properties:
        memory_id:
          type: string
          format: uuid
          title: Memory Id
          description: The recalled memory being rated
        helpful:
          type: boolean
          title: Helpful
          description: Independent host verdict
        query:
          anyOf:
          - type: string
            maxLength: 1024
          - type: 'null'
          title: Query
        verdict_source:
          type: string
          enum:
          - objective_check
          - trusted_host_check
          - hitl_approval
          title: Verdict Source
        verdict_reference:
          type: string
          maxLength: 1024
          title: Verdict Reference
        experiment_id:
          anyOf:
          - type: string
            maxLength: 255
          - type: 'null'
          title: Experiment Id
        note:
          anyOf:
          - type: string
            maxLength: 2000
          - type: 'null'
          title: Note
      type: object
      required:
      - memory_id
      - helpful
      - verdict_source
      - verdict_reference
      title: HostFeedbackRequest
      description: Trusted operator verdict; provenance is intentionally not caller-settable.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    FeedbackRequest:
      properties:
        memory_id:
          type: string
          format: uuid
          title: Memory Id
          description: The recalled memory being rated
        helpful:
          type: boolean
          title: Helpful
          description: Was this memory useful for the query?
        query:
          anyOf:
          - type: string
            maxLength: 1024
          - type: 'null'
          title: Query
          description: The recall query this feedback is about (optional)
        note:
          anyOf:
          - type: string
            maxLength: 2000
          - type: 'null'
          title: Note
          description: Optional free-text note (e.g. why it was wrong). Max 2000 chars.
      type: object
      required:
      - memory_id
      - helpful
      title: FeedbackRequest
      description: Body for recording retrieval feedback.
    FeedbackResponse:
      properties:
        feedback_id:
          type: string
          format: uuid
          title: Feedback Id
        memory_id:
          type: string
          format: uuid
          title: Memory Id
        helpful:
          type: boolean
          title: Helpful
      type: object
      required:
      - feedback_id
      - memory_id
      - helpful
      title: FeedbackResponse