Cernion AI Agent API

The AI Agent API from Cernion — 5 operation(s) for ai agent.

Operations 5

POST /api/agent/analyze Analyze a natural-language energy problem and return an execution plan #
POST /api/agent/execute Execute the planned steps with user-provided parameter values #
GET /api/agent/session/:id Retrieve a persisted agent session by ID #
GET /api/agent/session/:id/csv Re-run the session plan and export results as CSV #
POST /api/agent/rerun Re-run a completed session with the same plan and inputs #

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/cernion-de:cernion-de-ai-agent-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.

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

OpenAPI Specification

cernion-de-ai-agent-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Cernion Energy Tools AI Agent API
  version: 0.99.22
  description: 'MicroService Agent System for Energy Markets - REST API with AI integration.


    CERNION_TOKEN: request at https://cernion.de/ or by email: dev@stromdao.com.


    For the public instance at https://api.cernion.de/, create your token at https://cernion.de/cet-token/.'
servers:
- url: https://api.cernion.de
  description: API Server
tags:
- name: AI Agent
paths:
  /api/agent/analyze:
    post:
      summary: Analyze a natural-language energy problem and return an execution plan
      tags:
      - AI Agent
      operationId: agent_analyze
      parameters:
      - $ref: '#/components/parameters/TokenQuery'
      responses:
        '200':
          description: Execution plan with required user parameters
          content:
            application/json:
              schema:
                type: object
                properties:
                  sessionId:
                    type: string
                  summary:
                    type: string
                  steps:
                    type: array
                    items:
                      type: object
                      properties:
                        step:
                          type: number
                        service:
                          type: string
                        action:
                          type: string
                        description:
                          type: string
                        params:
                          type: object
                  requiredInputs:
                    type: array
                    items:
                      type: object
                      properties:
                        name:
                          type: string
                        label:
                          type: string
                        type:
                          type: string
                        description:
                          type: string
                        example:
                          type: string
                        required:
                          type: boolean
      description: Uses Gemini to reason about the user problem and select which microservices to call, in which order, and which parameters are needed from the user.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - problem
              properties:
                problem:
                  type: string
                  description: Free-text energy research problem or question
                  example: What is the current gas storage level in Germany and is it sufficient for winter?
                token:
                  type: string
                  description: Optional Cernion MCP token for this request. Overrides CERNION_TOKEN when provided.
            examples:
              storageSufficiency:
                summary: Analyze a storage sufficiency question
                value:
                  problem: What is the current gas storage level in Germany and is it sufficient for winter?
  /api/agent/execute:
    post:
      summary: Execute the planned steps with user-provided parameter values
      tags:
      - AI Agent
      operationId: agent_execute
      parameters:
      - $ref: '#/components/parameters/TokenQuery'
      responses:
        '200':
          description: Execution results or re-plan if refinement provided
      description: Runs the execution plan produced by /agent/analyze, substituting user inputs into step params and calling each microservice in sequence. Optionally accepts a free-text refinement which triggers a re-plan.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - sessionId
              properties:
                sessionId:
                  type: string
                  description: Session ID returned by /agent/analyze
                  example: 2a70e478-90ce-4fa5-b996-6f98efdba7cf
                userInputs:
                  type: object
                  description: Key-value map of required input values
                  example:
                    country: de
                    date: '2026-02-01'
                refinement:
                  type: string
                  description: Optional free-text refinement or follow-up question
                  example: Focus on Bavaria and include the next 7 days
                token:
                  type: string
                  description: Optional Cernion MCP token for this request. Overrides CERNION_TOKEN when provided.
            examples:
              executePlan:
                summary: Execute an analyzed plan
                value:
                  sessionId: 2a70e478-90ce-4fa5-b996-6f98efdba7cf
                  userInputs:
                    country: de
                    date: '2026-02-01'
  /api/agent/session/:id:
    get:
      summary: Retrieve a persisted agent session by ID
      tags:
      - AI Agent
      operationId: agent_getSession
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          example: 2a70e478-90ce-4fa5-b996-6f98efdba7cf
        description: Session UUID returned by /agent/analyze
      - $ref: '#/components/parameters/TokenQuery'
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: object
      description: Load a previously executed session so the user can revisit results or re-run.
  /api/agent/session/:id/csv:
    get:
      summary: Re-run the session plan and export results as CSV
      tags:
      - AI Agent
      operationId: agent_csvExport
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          example: 2a70e478-90ce-4fa5-b996-6f98efdba7cf
        description: Session UUID
      - $ref: '#/components/parameters/TokenQuery'
      responses:
        '200':
          description: CSV file
          content:
            text/csv:
              schema:
                type: string
      description: Re-executes the full plan with the saved user inputs, injects format=csv into the last data step, and returns a fresh CSV file. The data is always fetched live from the source.
  /api/agent/rerun:
    post:
      summary: Re-run a completed session with the same plan and inputs
      tags:
      - AI Agent
      operationId: agent_rerun
      parameters:
      - $ref: '#/components/parameters/TokenQuery'
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: object
      description: 'Useful for the shareable-URL feature: load a session and re-execute it.'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - sessionId
              properties:
                sessionId:
                  type: string
                  example: 2a70e478-90ce-4fa5-b996-6f98efdba7cf
                token:
                  type: string
                  description: Optional Cernion MCP token for this request. Overrides CERNION_TOKEN when provided.
            examples:
              rerunSession:
                summary: Re-run a previous session
                value:
                  sessionId: 2a70e478-90ce-4fa5-b996-6f98efdba7cf
components:
  parameters:
    TokenQuery:
      name: token
      in: query
      required: false
      schema:
        type: string
      description: Optional Cernion MCP token as URL query parameter. If provided, it overrides CERNION_TOKEN for this request. Prefer Authorization Bearer header in production to reduce token exposure in URLs/logs.
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: 'Optional Cernion MCP token. If not provided, falls back to CERNION_TOKEN from environment. Request token at https://cernion.de/ or by email: dev@stromdao.com.'