Feedly

Feedly Prediction API

The Prediction API from Feedly — 1 operation(s) for prediction.

GitHub OpenAPI

Operations 1

POST /prediction Ask AI with structured outputs #

Documentation

📖
Documentation
https://developers.feedly.com/reference/introduction
📖
APIReference
https://developers.feedly.com/reference/introduction
📖
GettingStarted
https://developers.feedly.com/reference/building-your-first-ti-integration
📖
Authentication
https://developers.feedly.com/reference/authorization

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/feedly/refs/heads/main/openapi/feedly-prediction-api-openapi.yml

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/feedly-prediction-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

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

OpenAPI Specification

feedly-prediction-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Entries Prediction API
  version: '1.0'
servers:
- url: https://api.feedly.com/v3/entries/
security:
- sec0: []
tags:
- name: Prediction
paths:
  /prediction:
    post:
      summary: Ask AI with structured outputs
      description: The Feedly Ask AI API allows developers to leverage the power of Large Language Models (LLMs) to ask questions and gather insights from a set of articles.
      operationId: ai-actions-experimental
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                entryIds:
                  type: array
                  description: An array of article IDs to perform AI actions on
                  items:
                    type: string
                prompt:
                  type: string
                  description: The user-generated prompt to ask questions or gather insights from the articles
      responses:
        '200':
          description: '200'
          content:
            application/json:
              examples:
                Result:
                  value: '{}'
              schema:
                type: object
                properties: {}
        '400':
          description: '400'
          content:
            application/json:
              examples:
                Result:
                  value: '{}'
              schema:
                type: object
                properties: {}
      deprecated: false
      tags:
      - Prediction
components:
  securitySchemes:
    sec0:
      type: apiKey
      name: Authorization
      in: header
      x-bearer-format: bearer
x-readme:
  headers: []
  explorer-enabled: true
  proxy-enabled: true
x-readme-fauxas: true