DocsMCP Server

MCP Server Playground

What is MCP?

Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

MCP helps you build agents and complex workflows on top of LLMs by providing:

  • A growing list of pre-built integrations that your LLM can directly plug into
  • The flexibility to switch between LLM providers and vendors
  • Best practices for securing your data within your infrastructure

Learn more about MCP

Adding the Byterover MCP Server

Most IDEs support JSON configuration for MCP servers, making it easy to get started. Once you update the MCP configuration file in your IDE, the MCP server will be automatically downloaded and enabled.

Configuration Template

{
  "mcpServers": {
    "Byterover Memory MCP": {
      "command": "npx",
      "args": [
        "-y",
        "byterover-mcp",
        "--byterover-public-api-key=YOUR_PUBLIC_KEY",
        "--user-id=YOUR-NAME"
      ]
    }
  }
}

For Windows users, use this configuration instead:

{
  "mcpServers": {
    "Byterover Memory MCP": {
      "command": "cmd",
      "args": [
        "/c",
        "npx",
        "-y",
        "byterover-mcp",
        "--byterover-public-api-key=YOUR_PUBLIC_KEY",
        "--user-id=YOUR-NAME"
      ]
    }
  }
}

IDE-Specific Setup

Different IDEs have their own ways of configuring MCP servers. Here’s how to set it up in popular IDEs:

Cursor

Place the configuration in either:

  • Project-specific: .cursor/mcp.json in your project directory
  • Global: ~/.cursor/mcp.json in your home directory
Automatically Use Byterover MCP with Cursor Rules

This helps you configure Cursor’s Composer Agent to automatically use the Byterover MCP for relevant tasks, so you don’t need to specify “using Byterover MCP” in every prompt.

Steps to Set Up
  1. Understand Cursor Rules:
  • Cursor Rules define project-specific instructions for the Composer Agent, acting like a default guide for all prompts.
  • You can set a rule to make the Agent automatically use Byterover MCP when it’s relevant.
  1. Add a Rule in Cursor Settings:
  • Open Cursor and navigate to Settings > Rules > Project Rules.
  • Add a new Project Rules with Rule Type = Always and rule content:
# Memory Bank:
You have access to a long-term memory bank called "byterover."
This memory bank is used to store and retrieve valuable programming experiences, including detailed technical documentation such as:
- How classes and functions are built and used
- Programming concepts and logical approaches
- Best practices in software development
# Storing Information:
When you successfully complete a task assigned by a human, extract and store any new or useful information gained during the process in the byterover memory bank.
This includes programming concepts, logics, and best practices that could benefit future tasks.
![IMPORTANT] #Retrieving Information:
Before starting any new task, generate an optimal query based on the task’s requirements.
Use this query to retrieve relevant context and support from the byterover memory bank.
Apply the retrieved information to guide your approach, leveraging past experiences and best practices to enhance your performance.
  1. Save and Test:
  • Save your changes in the settings.
  • Test by giving the Composer Agent a task where Byterover MCP is relevant (e.g., a multi-channel data task). The Agent should automatically use Byterover MCP without you mentioning it.

Learn more about Cursor MCP setup

Windsurf

Add the configuration in:

  • ~/.codeium/windsurf/mcp_config.json
Automatically Use Byterover MCP with Windsurf

This guide helps you configure Windsurf’s Cascade Agent to automatically use the Byterover MCP for relevant tasks, so you don’t need to specify “using Byterover MCP” in every prompt.

Steps to Set Up
  1. Understand Windsurf Configurations:
  • Windsurf allows you to define project-specific instructions for the Cascade Agent via configuration files or settings, which act as guidelines for all prompts.
  • You can instruct the Cascade Agent to automatically use Byterover MCP when relevant by setting up custom configurations.
  1. Configure via .windsurfrules File:
  • In your project’s root directory, create a file named .windsurfrules (no extension).
  • Add the following text:
# Memory Bank:
You have access to a long-term memory bank called "byterover."
This memory bank is used to store and retrieve valuable programming experiences, including detailed technical documentation such as:
- How classes and functions are built and used
- Programming concepts and logical approaches
- Best practices in software development
# Storing Information:
When you successfully complete a task assigned by a human, extract and store any new or useful information gained during the process in the byterover memory bank.
This includes programming concepts, logics, and best practices that could benefit future tasks.
![IMPORTANT] #Retrieving Information:
Before starting any new task, generate an optimal query based on the task’s requirements.
Use this query to retrieve relevant context and support from the byterover memory bank.
Apply the retrieved information to guide your approach, leveraging past experiences and best practices to enhance your performance.
  • Save the file. Windsurf’s Cascade Agent will automatically detect and apply this configuration for the project.
  1. Save and Test:
  • Ensure your changes are saved in the .windsurfrules file.
  • Test by giving the Cascade Agent a task where Byterover MCP is relevant (e.g., a multi-channel data task). The Agent should use Byterover MCP without you mentioning it explicitly.

Learn more about Windsurf MCP setup

Cline

Add the configuration to:

  • .clinerules file or your custom instructions

Learn more about Cline MCP setup

Next Steps

The Byterover MCP server is a general-purpose but powerful tool that can be customized to suit your specific needs. Here are some ways to get the most out of it:

  1. Create Memory Rules: Establish rules for when and how your agent should store and retrieve memories.

  2. Integrate with Your Workflow: Use the MCP server alongside your existing development tools and processes.

  3. Monitor and Refine: Keep track of how the MCP server is being used and adjust its configuration based on your needs.

Remember that the power of the Byterover MCP server lies in its flexibility - take time to configure it in a way that enhances your specific development workflow.

PlaygroundAccess Control