# Agent Output Contract Validator (`junipr/agent-output-contract-validator`) Actor

Validate AI-agent outputs against expected schemas, required fields, source/citation rules, and structured-output contracts.

- **URL**: https://apify.com/junipr/agent-output-contract-validator.md
- **Developed by:** [junipr](https://apify.com/junipr) (community)
- **Categories:** SEO tools, Developer tools
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $6.50 / 1,000 operation testeds

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/platform/actors/running/actors-in-store#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
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.
Actors are written with capital "A".

## 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.
The best way to integrate Actors is as follows.

- **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 usage examples, see the [API](#api) section below.

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).

# README

## Agent Output Contract Validator

### Store Positioning

**Store title:** Agent Output Contract Validator

**Short description:** Validate AI-agent outputs against expected schemas, required fields, source/citation rules, and structured-output contracts.

**SEO title:** Agent Output Contract Validator — API, schema, and developer QA

**SEO description:** Validate AI-agent outputs against expected schemas, required fields, source/citation rules, and structured-output contracts. Use it to catch contract drift, schema mistakes, unsafe endpoint assumptions, and developer-tool quality issues before release.

**Categories:** SEO\_TOOLS, DEVELOPER\_TOOLS

**Keywords:** agent, output, contract, validator, structured data, schema, api/developer qa

### Pay-Per-Event Pricing

This actor uses pay-per-event pricing. Event prices include Apify platform usage; users are not expected to pay a separate platform-usage pass-through charge for the configured pricing model.

- Tier: A1 — API/developer QA
- Primary event: `operation-tested` at $0.00650 base
- Default max charge: $10.00
- Store discounts: FREE/BRONZE base, SILVER discounted, GOLD deepest approved discount

Event set:

- `actor-start`: base $0.00500, GOLD $0.00400. Agent Output Contract Validator: charged when actor start is completed. The price includes Apify platform usage; no separate usage pass-through is intended.
- `operation-tested`: base $0.00650, GOLD $0.00520. Agent Output Contract Validator: charged when operation tested is completed. The price includes Apify platform usage; no separate usage pass-through is intended.
- `contract-rule-checked`: base $0.00390, GOLD $0.00312. Agent Output Contract Validator: charged when contract rule checked is completed. The price includes Apify platform usage; no separate usage pass-through is intended.
- `report-generated`: base $0.05000, GOLD $0.04000. Agent Output Contract Validator: charged when report generated is completed. The price includes Apify platform usage; no separate usage pass-through is intended.

The actor accepts `actor-start` before work, accepts the primary event before each dataset row, and accepts the configured report event before writing report files. If `maxChargeUsd` or the live PPE limit blocks a charge, the corresponding row or report is not written.

### Public Task Concepts

- Validate Agent Output Contract records from a capped sample
- Find invalid Agent Output Contract values before delivery
- Check Agent Output Contract coverage against expected rules
- Prioritize Agent Output Contract validation failures by severity
- Export Agent Output Contract pass-fail rows with evidence
  Validate AI-agent outputs against JSON schema and citation contracts.

### What It Does

Validates required fields, types, enum constraints, citation/source coverage, refusal/error shape, JSON arrays, and JSONL records.

### Inputs

This actor exposes these input fields in `.actor/input_schema.json`:

- `contractJson`
- `schemaJson`
- `outputsJson`
- `jsonlText`
- `requiredCitationFields`
- `strictMode`
- `maxRecords`
- `includeValidRows`
- `maxChargeUsd`

The exact default validates a bounded public GitHub API observation for `modelcontextprotocol/servers`, captured at 2026-07-12T05:48:00Z, against an explicit schema and source-URL contract.

### Outputs

Dataset rows contain:

- `recordId`
- `isValid`
- `contractRule`
- `fieldPath`
- `expected`
- `actual`
- `errorType`
- `severity`
- `fixHint`
- `sourceCoverageStatus`

Sample outputs in `examples/output.sample.json` and `output.sample.json` were generated from `examples/input.tiny.json` through actor logic.

### Reports

After the configured report charge is accepted, the actor writes its Markdown, JSON, or CSV reports to the key-value store. A rejected report charge leaves those files unwritten.

### Public Task Concepts

- Validate Agent Output Contract Validator before release
- Run a bounded Agent Output Contract Validator QA check
- Generate developer QA evidence for Agent Output Contract Validator

### Safe use

Use small capped runs first. Network paths are bounded; review output quality and costs before increasing limits.

# Actor input Schema

## `contractJson` (type: `object`):

Inline contract JSON object used by Agent Output Contract Validator.

## `schemaJson` (type: `object`):

Inline schema JSON object used by Agent Output Contract Validator.

## `outputsJson` (type: `array`):

Inline outputs JSON object used by Agent Output Contract Validator.

## `jsonlText` (type: `string`):

Supplied JSONL text to analyze directly.

## `requiredCitationFields` (type: `array`):

Require required citation fields during validation and flag rows that do not meet the rule.

## `strictMode` (type: `boolean`):

Strict Mode controlling how Agent Output Contract Validator processes the supplied inputs.

## `maxRecords` (type: `number`):

Maximum records to process in one run; keep defaults low for safe first runs.

## `includeValidRows` (type: `boolean`):

Include valid rows in output rows or reports when available.

## `maxChargeUsd` (type: `number`):

Maximum estimated PPE charge allowed for the run before the actor stops gracefully.

## Actor input object example

```json
{
  "contractJson": {
    "requiredCitationFields": [
      "html_url"
    ],
    "refusalRequiredFields": [
      "reason"
    ]
  },
  "schemaJson": {
    "type": "object",
    "required": [
      "id",
      "name",
      "full_name",
      "html_url",
      "stargazers_count"
    ],
    "properties": {
      "id": {
        "type": "number",
        "title": "Id",
        "description": "Id input value."
      },
      "name": {
        "type": "string",
        "title": "Name",
        "description": "Name input value."
      },
      "full_name": {
        "type": "string",
        "title": "Full Name",
        "description": "Full Name input value."
      },
      "html_url": {
        "type": "string",
        "title": "Html Url",
        "description": "Html Url input value."
      },
      "stargazers_count": {
        "type": "number",
        "title": "Stargazers Count",
        "description": "Stargazers Count input value."
      }
    }
  },
  "outputsJson": [
    {
      "id": 890668799,
      "name": "servers",
      "full_name": "modelcontextprotocol/servers",
      "html_url": "https://github.com/modelcontextprotocol/servers",
      "stargazers_count": 88353
    }
  ],
  "jsonlText": "",
  "requiredCitationFields": [
    "html_url"
  ],
  "strictMode": true,
  "maxRecords": 1,
  "includeValidRows": true,
  "maxChargeUsd": 1
}
```

# 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 = {};

// Run the Actor and wait for it to finish
const run = await client.actor("junipr/agent-output-contract-validator").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 = {}

# Run the Actor and wait for it to finish
run = client.actor("junipr/agent-output-contract-validator").call(run_input=run_input)

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

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

```

## CLI example

```bash
echo '{}' |
apify call junipr/agent-output-contract-validator --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://mcp.apify.com/?tools=junipr/agent-output-contract-validator",
                "--header",
                "Authorization: Bearer <YOUR_API_TOKEN>"
            ]
        }
    }
}

```

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/MZm6lwUHJyRzk4bED/builds/V1UjgJqghZE95K92m/openapi.json