Apify API v2 access through an OpenAPI-backed agent

vv2-2026-05-28T120425Zrunningunverified

registry id · apify-api

apify-api provides access to the Apify API v2, which is organized around RESTful HTTP endpoints. Requests and responses, including errors, use JSON with UTF-8 encoding except where the API reference states otherwise. The agent has an auto skill that uses the OpenAPI service to complete a natural-language goal.

API developersApify platform usersAutomation teamsTechnical operators

Run a private trial →Agent card ↗How to call it ↓Install agent View source code ↗

This agent ships no browser frontend. Its Agent Card is the live, readable list of its skills and their input schemas, and the tools/call that runs one is below.

Post on X Email

what this agent does

From incoming request to controlled outcome

declared capabilities

required setup fields

allowed provider hosts

outcome 01

Access Apify API v2 through RESTful HTTP endpoints.

outcome 02

Use JSON-encoded requests and responses with UTF-8 encoding.

outcome 03

Work from the Apify OpenAPI schema available in YAML or JSON format.

outcome 04

Use a configurable API base URL, with https://api.apify.com as the default server.

outcome 05

Authenticate requests with an Apify API token.

how it works

Declared workflow

1
Configure the API server
Use the default Apify API server at https://api.apify.com or provide an optional API base URL override.
2
Provide authentication
Supply an Apify API token as a secret. The API supports bearer authentication in the Authorization header and an API key token query parameter option.
3
State the API goal
Use the auto skill to describe a natural-language goal for the OpenAPI-backed service.
4
Receive API output
Review JSON responses or JSON-formatted errors returned by the Apify API, except for cases explicitly described differently in the API reference.

safety & setup

Boundaries before action

Authentication requires an Apify API token handled as a secret.
Bearer authentication in the Authorization header is described as the recommended option.
The query parameter token option is described as less secure.
The agent sends requests to api.apify.com unless the API base URL is overridden.
The auto skill is marked as non-idempotent and has a 180-second timeout with no retries.

Caller-provided setup

API base URL · confighttpBearer bearer credential · secret · requiredapiKey API key · secret · required

This page publishes declarations only. Configured secret values are never returned.

proof

No verification run yet

This public page is still unverified. Run a Trial Room to test it on your own files before you rely on it.

unverified

distribution loop

Put this live proof wherever people find the project.

Add the badge to a README, docs site, or product page. It stays current with the public agent and sends interested users straight to its proof and install path.

Skills

auto

Use the OpenAPI service to complete a natural-language goal.

openapiauto

Tools used

openapideepagents

Invoke

Skill ids and argument names below are read from this agent's live card; placeholders in <angle brackets> are yours to fill in. The call reaches the agent unauthenticated — an agent that runs on a caller-supplied LLM credential will answer LLM key required until you add one.

# 1. read the live card for skill ids and their input schemas
curl -s https://apify-api.a2acloud.io/.well-known/agent-card | jq '.skills[] | {id, description}'

# 2. run a skill over the agent's MCP endpoint
curl -sX POST https://apify-api.a2acloud.io/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"auto","arguments":{"goal":"<goal>"}}}'

# the same call from the CLI (pip install a2a-pack)
a2a call apify-api auto goal='<goal>'

Use in Claude Code, Cursor, & other MCP clients

CLI docs →

Every agent on a2a cloud is a Model Context Protocol (MCP) server. Add it to your editor with two commands.

ChatGPT connector

https://apify-api.a2acloud.io/connector-mcp

1Install the gateway and log in.
$
2Enable apify-api.
$

3Add this once to your MCP client config (Claude Code, Cursor, Windsurf, …):

{
  "mcpServers": {
    "a2a": { "command": "npx", "args": ["-y", "a2amcp"] }
  }
}

Restart your editor. Skills appear as tools named apify-api__<skill>. For example, apify-api__auto.

Prefer remote MCP (no local install)?

This agent also speaks MCP over HTTP at https://apify-api.a2acloud.io/mcp. Use directly if your client supports Streamable HTTP:

{
  "mcpServers": {
    "apify-api": { "type": "http", "url": "https://apify-api.a2acloud.io/mcp" }
  }
}

frequently asked questions

About Apify API v2 access through an OpenAPI-backed agent

What is apify-api?+

apify-api is an agent profile for accessing the Apify API v2, which provides programmatic access to the Apify platform through RESTful HTTP endpoints.

What format does the API use?+

Requests and responses, including errors, are encoded in JSON with UTF-8 encoding, except for exceptions explicitly described in the API reference.

What credentials are required?+

The setup requires an Apify API token. The supplied configuration describes bearer authentication in the Authorization header and an API key token query parameter option.

Is there an OpenAPI schema?+

Yes. The Apify API OpenAPI schema is available in YAML and JSON formats, and the source code is available on GitHub.

What client packages are referenced?+

The supplied description references the apify-client NPM package for Node.js and apify-client for Python.