Claude Desktop Config Manager

Created By
eversonla year ago
A lightweight, command-line tool for managing Claude Desktop MCP (Model Context Protocol) configurations. This tool makes it easy to toggle MCP servers on and off, create preset configurations, and manage backups.
Overview

What is Claude Desktop Config Manager?

Claude Desktop Config Manager is a lightweight command-line tool designed for managing Claude Desktop MCP (Model Context Protocol) configurations, allowing users to easily toggle MCP servers, create preset configurations, and manage backups.

How to use Claude Desktop Config Manager?

To use the tool, clone the repository or download the claude-config-manager.js file, update the CLAUDE_DIR to match your Claude installation path, and run the tool from the command line using node claude-config-manager.js.

Key features of Claude Desktop Config Manager?

  • Toggle MCP Servers: Enable or disable individual MCP servers.
  • Custom Configurations: Create configurations based on user needs.
  • Preset Management: Save and load configuration presets.
  • Backup & Restore: Create timestamped backups and restore configurations.
  • Config Validation: Check and fix JSON syntax issues.
  • Color-Coded Interface: User-friendly console interface.

Use cases of Claude Desktop Config Manager?

  1. Managing multiple MCP configurations for different projects.
  2. Quickly toggling MCP servers for testing purposes.
  3. Creating backups before making significant changes to configurations.

FAQ from Claude Desktop Config Manager?

  • What are MCP servers?

MCP servers are components of the Claude Desktop that handle specific tasks based on the Model Context Protocol.

  • Is there a graphical interface for this tool?

No, this tool is command-line based, designed for users comfortable with terminal commands.

  • Can I use this tool without Node.js?

No, Node.js (v12 or higher) is required to run this tool.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
eversonl
Star
0
Language
JavaScript
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago