# Agent Check: A2A Card, MCP Server & x402 Endpoint Validator (`calcio_you/agent-check`) Actor

Trust check before your AI agent calls or pays another agent: validates A2A Agent Cards (v1.0/v0.3), performs a real MCP handshake (tools, latency, OAuth) and decodes x402 payment offers (network, USDC, price, payTo, red flags). No payment made. Pay per check.

- **URL**: https://apify.com/calcio_you/agent-check.md
- **Developed by:** [Novarithm](https://apify.com/calcio_you) (community)
- **Categories:** AI, Developer tools, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Agent Check: Verify A2A Agent Cards, MCP Servers & x402 Endpoints

A trust check for **agent-to-agent work**. Before your AI agent delegates a task to another agent, plugs in a remote MCP server or pays an x402 endpoint, run one cheap check and get a clear JSON verdict.

Three checks in one Actor:

1. **A2A Agent Card check**: fetches `/.well-known/agent-card.json` (or the legacy `agent.json`), recognises **A2A v1.0 / v0.3 / custom** cards, checks required fields, skills, interfaces (HTTPS, reachable), security schemes and Signed Agent Card. Returns a **0-100 score, a grade A-F**, issues and warnings.
2. **MCP server probe**: a real **MCP Streamable HTTP handshake** (`initialize` + `tools/list`). Protocol version, server name and version, tools and their schemas, latency, and OAuth protected-resource metadata when the server requires auth. **No tool is ever called.**
3. **x402 endpoint probe**: one **unpaid** request, then decodes the `402 Payment Required` offer (x402 v1 body or v2 header): network, asset (known USDC or not), **price in USD**, `payTo`, testnet flag, resource mismatch and red flags. **Nothing is paid.**

Private / internal addresses are refused. Live checks only.

### Use cases

- An orchestrator (CrewAI, LangGraph, AutoGen...) picks a sub-agent: check its A2A card before sending work.
- A coding agent adds a remote MCP server: confirm it is up, speaks MCP and lists the expected tools.
- A buyer agent is about to pay an x402 endpoint: confirm the price, the network, that the asset is real USDC and not a look-alike token.
- An agent marketplace or registry runs a nightly health check on its listings.

### Input

| Field | What it does |
|---|---|
| `agentUrls` | Agent base URLs, domains or direct card URLs to check. |
| `mcpServers` | Remote MCP endpoints (Streamable HTTP) to probe. |
| `x402Endpoints` | Paid endpoint URLs to inspect before paying (GET). |
| `queries` | Advanced: `[{"endpoint": "x402_probe", "params": {"url": "...", "method": "POST"}}]` |
| `maxQueries` | Safety cap on checks per run (default 1000). |

Example:

```json
{
  "agentUrls": ["https://sabli.app"],
  "mcpServers": ["https://mcp.deepwiki.com/mcp"],
  "x402Endpoints": ["https://www.x402financialdata.com/producer-prices"]
}
```

### Output

One dataset item per check. Shortened example from a real check:

```json
{
  "endpoint": "a2a_card_check",
  "input": {"url": "https://sabli.app"},
  "ok": true,
  "result": {
    "card_url": "https://sabli.app/.well-known/agent-card.json",
    "found": true,
    "card_flavour": "v0.3",
    "name": "Sabli",
    "skills_count": 21,
    "interfaces": [{"url": "https://sabli.app/api/a2a", "binding": "JSONRPC", "version": "0.3.0"}],
    "auth_schemes": ["sabli_key", "sabli_oauth"],
    "score": 95,
    "grade": "A",
    "verdict": "conformant",
    "warnings": ["card_not_signed (A2A 1.0 Signed Agent Card absent)"]
  },
  "charged_event": "a2a-card-check",
  "price_usd": 0.01
}
```

x402 probe (shortened): `{"is_x402": true, "x402_version": 2, "service_name": "US Producer Price Index (PPI)", "offers": [{"network": "eip155:8453", "asset_is_known_usdc": true, "price_usd": 0.01, "testnet": false}], "verdict": "payable_looks_safe"}`

### Pricing

Pay per successful check, **$0.01** per A2A card, MCP probe or x402 probe. Errors (card not found, host not found, invalid or private URL) are **never charged**.

### Limits (honest)

- A snapshot check: it does not prove the quality of a paid answer or the honesty of the operator.
- No MCP tool call and no A2A message is sent (no side effects); authentication is not attempted.
- A2A card signatures are detected but not cryptographically verified yet.

Also available pay-per-call over x402 (USDC on Base) and MCP: https://gogeta2-u35175.vm.elestio.app/agents/catalog. Contact: contact@novarithm.com

***

Want this whole store under your brand? → https://gogeta2-u35175.vm.elestio.app/agents/clones/en/cases/api-store-for-ai-agents/

# Actor input Schema

## `agentUrls` (type: `array`):

Agent base URL, domain or direct card URL. Looks for /.well-known/agent-card.json then /.well-known/agent.json. One charged check per agent.

## `mcpServers` (type: `array`):

Streamable HTTP MCP endpoints (e.g. https://mcp.deepwiki.com/mcp). Handshake only, no tool is ever called. One charged probe per server.

## `x402Endpoints` (type: `array`):

Paid endpoint URLs. One unpaid GET request each; the 402 offer is decoded (network, asset, USD price, payTo, testnet, red flags). Nothing is paid. Use `queries` for POST endpoints.

## `queries` (type: `array`):

e.g. \[{"endpoint": "x402_probe", "params": {"url": "https://...", "method": "POST"}}]; endpoints: a2a_card_check, mcp_probe, x402_probe.

## `maxQueries` (type: `integer`):

Safety cap: only the first N checks of the input are processed.

## Actor input object example

```json
{
  "agentUrls": [
    "https://sabli.app"
  ],
  "mcpServers": [
    "https://mcp.deepwiki.com/mcp"
  ],
  "maxQueries": 1000
}
```

# Actor output Schema

## `results` (type: `string`):

All result items in the default dataset (JSON).

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "agentUrls": [
        "https://sabli.app"
    ],
    "mcpServers": [
        "https://mcp.deepwiki.com/mcp"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("calcio_you/agent-check").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "agentUrls": ["https://sabli.app"],
    "mcpServers": ["https://mcp.deepwiki.com/mcp"],
}

# Run the Actor and wait for it to finish
run = client.actor("calcio_you/agent-check").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "agentUrls": [
    "https://sabli.app"
  ],
  "mcpServers": [
    "https://mcp.deepwiki.com/mcp"
  ]
}' |
apify call calcio_you/agent-check --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,calcio_you/agent-check"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/3rqzn4A15uvv8bdfq/builds/VacjuDEKjEwaCcY0N/openapi.json