# AI Agent API Tool Caller

**Use case:** 

Give an AI agent one tool to call any API. Batches HTTP requests, parses JSON, and works through the Apify MCP server.

## Input

```json
{
  "requests": [
    {
      "id": "get-data",
      "label": "Get data",
      "url": "https://httpbin.org/get?tool=weather"
    },
    {
      "id": "post-action",
      "label": "Post action",
      "url": "https://httpbin.org/post",
      "method": "POST",
      "body": {
        "action": "create_task",
        "priority": "high"
      }
    }
  ],
  "curlCommand": "",
  "maxConcurrency": 5,
  "requestsPerSecond": 0,
  "timeoutSecs": 30,
  "maxRetries": 2,
  "retryOnStatusCodes": [
    408,
    425,
    429,
    500,
    502,
    503,
    504
  ],
  "followRedirects": true,
  "maxRedirects": 5,
  "parseJson": true,
  "maxResponseBytes": 1000000,
  "saveOversizedBodyToKeyValueStore": true,
  "failOnErrorStatus": false,
  "expectedStatusCodes": [],
  "authType": "none",
  "authBasicUsername": "",
  "proxyConfiguration": {
    "useApifyProxy": false
  },
  "callbackUrl": ""
}
```

## Output

```json
{
  "label": {
    "label": "Label",
    "format": "string"
  },
  "requestedUrl": {
    "label": "URL",
    "format": "string"
  },
  "statusCode": {
    "label": "Status",
    "format": "number"
  },
  "contentType": {
    "label": "Content-Type",
    "format": "string"
  },
  "json": {
    "label": "Parsed JSON",
    "format": "object"
  },
  "body": {
    "label": "Raw Body",
    "format": "string"
  },
  "bodyEncoding": {
    "label": "Encoding",
    "format": "string"
  },
  "bodyBytes": {
    "label": "Bytes",
    "format": "number"
  },
  "bodyStoredKey": {
    "label": "Full Body (KV Store)",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [HTTP Request Runner: Bulk API Calls with Retries](https://apify.com/getascraper/http-request-runner) with a specific input configuration. Visit the [Actor detail page](https://apify.com/getascraper/http-request-runner) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
This Task's input is already configured above — use it as-is rather than inventing a new one.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/getascraper/http-request-runner.md

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).