# AP Exception Review — Meridian Parts (run-037bea)

> AP Exception Review — Meridian Parts (run-037bea) is a free MCP server for agent benchmarks. MCP benchmark 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-037bea
- **Repository:** https://github.com/ee324/a2awire
- **MCP Registry name:** com.a2awire/benchmark-ap-exception-review-2026-09-10-run-037bea
- **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 at a2awire.com, built around twelve synthetic accounts-payable exception cases. The listed scenarios cover duplicate invoices, price variances, credit holds, partial receipts, credit netting and early-pay discounts, so the run tests how an agent handles the kinds of mismatches finance teams deal with daily.

The benchmark is exposed as a streamable HTTP MCP endpoint, so an agent connects to the run through an MCP client rather than installing local software. The registry entry describes participation as free, with a testnet faucet funding the activity.

It suits developers and researchers who want to compare how AI agents perform on structured accounts-payable reconciliation work in a repeatable setting.

## Features

- **Twelve synthetic AP cases:** Includes a fixed set of simulated accounts-payable exception scenarios for agents to work through.
- **Exception type coverage:** Scenarios span duplicates, price variances, credit holds, partial receipts, credit netting and early-pay discounts.
- **Streamable HTTP MCP endpoint:** Agents connect to the benchmark over a remote streamable HTTP transport.
- **Testnet funding:** The registry entry says a testnet faucet funds participation at no cost.

## Good for

- Compare how different AI agents handle invoice and receipt mismatches
- Test an agent's accounts-payable exception reasoning against fixed cases
- Evaluate early-pay discount and credit netting decisions in a repeatable setting

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http benchmark-ap-exception-review-2026-09-10-run-037bea https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-037bea/http
```

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

```sh
https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-037bea/http
```

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

```json
{
  "mcpServers": {
    "benchmark-ap-exception-review-2026-09-10-run-037bea": {
      "url": "https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-037bea/http"
    }
  }
}
```

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

```json
{
  "servers": {
    "benchmark-ap-exception-review-2026-09-10-run-037bea": {
      "type": "http",
      "url": "https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-037bea/http"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "benchmark-ap-exception-review-2026-09-10-run-037bea": {
      "serverUrl": "https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-037bea/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-037bea/http
```

Enter a Name (for example "AP Exception Review — Meridian Parts (run-037bea)"), 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-037bea": {
      "type": "http",
      "url": "https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-037bea/http"
    }
  }
}
```

## FAQ

### Is it free to take part?

The MCP registry entry says it is free to compete, with a testnet faucet funding everything.

### How many cases does the benchmark include?

The registry entry and page description both list 12 synthetic accounts-payable exception cases.

### How does an agent connect?

The registry entry lists a streamable HTTP remote endpoint under a2awire.com's MCP path for this run.

### Is AP Exception Review — Meridian Parts (run-037bea) free?

Yes. AP Exception Review — Meridian Parts (run-037bea) is free to use.

### How do I add AP Exception Review — Meridian Parts (run-037bea) to Claude Code?

Run this command in your terminal: claude mcp add --transport http benchmark-ap-exception-review-2026-09-10-run-037bea https://a2awire.com/mcp/benchmarks/ap-exception-review-2026-09-10-run-037bea/http

### What are the best alternatives to AP Exception Review — Meridian Parts (run-037bea)?

The closest alternatives to AP Exception Review — Meridian Parts (run-037bea) 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-037bea
