mcpField
M
MCP Config Manager

MCP Config Manager

Local
github.com/easytocloudDeveloper Tools1Updated 91w ago

About MCP Config Manager

MCP Config Manager is a Python package for managing MCP server configurations, aimed at developers setting up Claude Desktop, Cline, or Roo. It detects configuration paths, validates environment variables, and handles extension-specific options.

Key features

  1. 01Detect configuration file paths
  2. 02Support Claude Desktop, Cline, and Roo
  3. 03Validate environment variables
  4. 04Provide generic configuration functions
  5. 05Set extension enablement and auto-approval options

Use cases

  1. 01Add an MCP server to Claude Desktop
  2. 02Write server settings for Cline or Roo
  3. 03Check required configuration variables
  4. 04Manage extension auto-approval settings

MCP support

The package manages MCP server settings for Claude Desktop, Cline, and Roo; it does not provide MCP server tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Config Manager

Configuration management utilities for Model Context Protocol (MCP) servers. This package provides functionality to manage MCP server configurations for different clients like Claude Desktop and VSCode extensions (Cline and Roo).

Features

  • Automatic configuration file path detection for different environments
  • Support for Claude Desktop and VSCode extensions (Cline and Roo)
  • Environment variable validation
  • Generic configuration management functions
  • VSCode extension specific settings (disabled, autoApprove) for Cline and Roo

Installation

pip install mcp-config-manager

Usage

from mcp_config_manager import add_to_config

# Define your required environment variables
REQUIRED_ENV_VARS = ["API_KEY", "API_URL"]

# Add to Claude Desktop configuration
add_to_config(
    server_name="my-mcp-server",
    required_env_vars=REQUIRED_ENV_VARS,
    config_type="claude"
)

# Add to Cline configuration (VSCode extension)
add_to_config(
    server_name="my-mcp-server",
    required_env_vars=REQUIRED_ENV_VARS,
    config_type="cline"  # Will include disabled=False and autoApprove settings
)

# Add to Roo configuration (VSCode extension)
add_to_config(
    server_name="my-mcp-server",
    required_env_vars=REQUIRED_ENV_VARS,
    config_type="roo"  # Will include disabled=False and autoApprove settings
)

# With custom environment variables
env_vars = {
    "API_KEY": "my-key",
    "API_URL": "https://api.example.com"
}

add_to_config(
    server_name="my-mcp-server",
    required_env_vars=REQUIRED_ENV_VARS,
    env_vars=env_vars,
    config_type="cline"
)

Configuration File Locations

The package automatically detects the appropriate configuration file paths:

Claude Desktop
  • EC2: ~/.vscode-server/data/User/globalStorage/anthropic.claude/settings/claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json
VSCode Extensions
Cline
  • EC2: ~/.vscode-server/data/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
  • macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
  • Windows: %APPDATA%/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
Roo
  • EC2: ~/.vscode-server/data/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
  • macOS: ~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
  • Windows: %APPDATA%/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json

VSCode Extension Settings

When adding configurations for VSCode extensions (Cline or Roo), the following additional settings are automatically included:

{
  "disabled": false,  // Server is enabled by default
  "autoApprove": []  // List of operations to auto-approve
}

Development

  1. Clone the repository
  2. Install development dependencies: pip install -e ".[dev]"
  3. Run tests: pytest
  4. Submit pull requests

License

MIT License - see LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.