Batchit

🚀 MCP BatchIt Tool Guide

MCP BatchIt is a powerful tool designed to execute multiple operations through a single request. It offers the following key features:

• Parallel Processing: Enables the simultaneous execution of multiple sub - operations.
• Error - Stopping: Allows you to halt subsequent operations if a sub - operation fails.
• Connection Caching: To enhance efficiency, BatchIt caches connections to the target server until an idle timeout occurs.

🚀 Quick Start

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

To use the MCP BatchIt tool, follow these steps:

1. Specify the Target Server:

{
  "targetServer": {
    "name": "filesystem",
    "serverType": {
      "type": "filesystem",
      "config": {
        "rootDirectory": "C:/Users/Chewy/Documents/GitHub/ryanjoachim/mcp-batchit"
      }
    },
    "transport": {
      "type": "stdio",
      "command": "cmd.exe",
      "args": [
        "/c",
        "npx",
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "C:/Users/Chewy/Documents/GitHub/ryanjoachim/mcp-batchit"
      ]
    }
  }
}

2. Define Operations:

{
  "operations": [
    {
      "tool": "create_directory",
      "arguments": {
        "path": "C:/Users/Chewy/Documents/GitHub/ryanjoachim/mcp-batchit/memory-bank"
      }
    },
    {
      "tool": "write_file",
      "arguments": {
        "path": "C:/Users/Chewy/Documents/GitHub/ryanjoachim/mcp-batchit/memory-bank/productContext.md",
        "content": "# MCP BatchIt Product Context\\n\\n## Purpose\\n..."
      }
    }
    // Other operations follow a similar pattern
  ]
}

3. Configure Options:

{
  "options": {
    "maxConcurrent": 1,
    "stopOnError": true,
    "timeoutMs": 30000
  }
}

📚 Documentation

Frequently Asked Questions

Q1: If sub - operation #2 depends on the result of sub - operation #1, do I need to call BatchIt multiple times?

Yes. BatchIt does not pass data within the same request. It is recommended to use multi - stage calls (as shown in the above example).

Q2: Why do I sometimes see the error “Tool create_directory not found”?

This is because your transport might be pointing to the aggregator script itself instead of the actual MCP server. Make sure to reference a real MCP server like @modelcontextprotocol/server-filesystem.

Q3: Can I achieve both parallel processing and error - stopping?

Absolutely. If a sub - operation fails, other already - started sub - operations will continue, but those not yet started will be skipped.

Q4: Does BatchIt restart the target server on each call?

Not necessarily. By default, BatchIt caches connections until an idle timeout occurs. You can also control this behavior by setting the keepAlive configuration option.

Q5: Can I get partial results if an error occurs in the middle?

Yes. The final response will include the status of all sub - operations completed before the error, as well as the failed sub - operation. If stopOnError is enabled, subsequent operations will be skipped.

📄 License

MIT