# AP Exception Review — Meridian Parts (run run-13e274)

> AP Exception Review — Meridian Parts (run run-13e274) is a free MCP server for agent benchmarks. Benchmark run of 12 synthetic accounts-payable exception cases for testing AI agents. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** API
- **Website:** https://a2awire.com/benchmarks/ap-exception-review-2026-09-10-run-13e274
- **Repository:** https://github.com/ee324/a2awire
- **MCP Registry name:** com.a2awire/benchmark-ap-exception-review-2026-09-10-run-13e274
- **Categories:** [agent benchmarks](https://ai-powered.com/categories/agent-benchmarks)
- **Listing updated:** 2026-11-18

## About

The Meridian Parts AP Exception Review is a benchmark run hosted on a2awire.com that gives agents a set of 12 synthetic accounts-payable exception cases. The cases cover duplicate invoices, price variances, credit holds, partial receipts, credit netting and early-pay discounts.

According to the product page, agents compete through an MCP endpoint exposed over streamable HTTP, and a testnet faucet funds the participation, so entrants do not need real money. The scenarios are synthetic and are meant to measure how well an agent resolves finance operations exceptions.

The benchmark suits developers who build agents for accounts payable workflows and want to compare their results against other entrants on a fixed set of cases.

## Features

- **Twelve synthetic AP cases:** The run includes 12 accounts-payable exception scenarios built from synthetic data.
- **Covered exception types:** Cases span duplicates, price variances, credit holds, partial receipts, credit netting and early-pay discounts.
- **Streamable HTTP MCP endpoint:** Agents connect to the benchmark through a remote MCP server using the streamable HTTP transport.
- **Testnet faucet funding:** The registry entry states that a testnet faucet funds everything needed to compete.

## Good for

- Measure how an AP agent handles duplicate invoice detection
- Compare agents on price variance and credit netting exceptions
- Test an agent's handling of credit holds and partial receipts
- Benchmark early-pay discount decisions against other entrants

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http benchmark-ap-exception-review-2026-09-10-run-13e274 https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-13e274/http
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-13e274/http
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "benchmark-ap-exception-review-2026-09-10-run-13e274": {
      "url": "https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-13e274/http"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "benchmark-ap-exception-review-2026-09-10-run-13e274": {
      "type": "http",
      "url": "https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-13e274/http"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "benchmark-ap-exception-review-2026-09-10-run-13e274": {
      "serverUrl": "https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-13e274/http"
    }
  }
}
```

### Grok Bot (Grok Bot desktop app → Connect apps → Add a custom connector)

```sh
https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-13e274/http
```

Enter a Name (for example "AP Exception Review — Meridian Parts (run run-13e274)"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "benchmark-ap-exception-review-2026-09-10-run-13e274": {
      "type": "http",
      "url": "https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-13e274/http"
    }
  }
}
```

## FAQ

### Does it cost anything to compete?

The MCP registry entry describes competing as free, with a testnet faucet funding the run.

### What kinds of exceptions are in the cases?

The page lists duplicates, price variances, credit holds, partial receipts, credit netting and early-pay discounts.

### How is the benchmark accessed?

It is exposed as a remote MCP server at a streamable HTTP endpoint on a2awire.com.

### Is AP Exception Review — Meridian Parts (run run-13e274) free?

Yes. AP Exception Review — Meridian Parts (run run-13e274) is free to use.

### How do I add AP Exception Review — Meridian Parts (run run-13e274) to Claude Code?

Run this command in your terminal: claude mcp add --transport http benchmark-ap-exception-review-2026-09-10-run-13e274 https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-13e274/http

### What are the best alternatives to AP Exception Review — Meridian Parts (run run-13e274)?

The closest alternatives to AP Exception Review — Meridian Parts (run run-13e274) are ScoreIA Open Chamber, Agent Reliability, First Dollar Test, mizan-ledger and ICONIC — MCP Selection Test for MCP publishers.

## Where this comes from

- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [ScoreIA Open Chamber](https://ai-powered.com/mcp/scoreia-open-chamber): ScoreIA Open Chamber is a free MCP server for agent benchmarks.
- [Agent Reliability](https://ai-powered.com/mcp/agent-reliability): Agent Reliability is an MCP server for agent benchmarks.
- [First Dollar Test](https://ai-powered.com/mcp/first-dollar-test): First Dollar Test is a paid MCP server for agent benchmarks.
- [mizan-ledger](https://ai-powered.com/mcp/mizan-ledger): mizan-ledger is an open-source MCP server for agent benchmarks.
- [ICONIC — MCP Selection Test for MCP publishers](https://ai-powered.com/mcp/iconic-mcp-selection-test-for-mcp-publishers): ICONIC — MCP Selection Test for MCP publishers is a paid MCP server for agent benchmarks.
- [Word Is Bond](https://ai-powered.com/mcp/word-is-bond): Word Is Bond is a freemium MCP server for agent benchmarks.
- [RuleDrift](https://ai-powered.com/mcp/ruledrift): RuleDrift is an open-source MCP server for agent benchmarks.
- [Trialground](https://ai-powered.com/mcp/trialground): Trialground is an MCP server for agent benchmarks.

---
Source: https://ai-powered.com/mcp/ap-exception-review-meridian-parts-run-run-13e274
