Configure MCP servers across IDEs with one click

MCP Linker is a cross-platform desktop app for discovering, adding, and syncing MCP server configurations across AI clients, without needing any LLM calls to do it. It ships a built-in marketplace of 600+ curated MCP servers, including sequential-thinking and desktop-commander, and can sync the same server configs across multiple installed clients on one machine.

Use it to browse and install an MCP server to a chosen client in a few clicks instead of manually editing that client's config JSON, especially when the same server needs to be configured across several supported clients at once. Smart detection of local Python, Node.js, and uv environments removes some of the setup friction for servers that need a specific runtime. Multi-client support and encrypted cloud sync across devices are gated behind a paid Pro plan - the free tier covers local, single-purpose config management. Licensing is dual: AGPL-3.0 for open-source use, or a required commercial license for closed-source, proprietary, hosted, or SaaS use, so embedding it in a closed commercial product needs that separate license.

Input is a server selection from the built-in marketplace, browse, then click Get to preview its configuration, or a manually specified MCP server. Output is that server's configuration written directly into the target client's own config format, ready to use immediately without a manual JSON edit. A companion GUI for the OpenAI Codex CLI, based on the related Codexia project, is also included.

Supports Claude Desktop, Claude Code, Cursor, VS Code, Cline, Windsurf, Codex, and Roo Code as install targets, across macOS, Windows, and Linux. Distribution channels include the AUR for Arch Linux, Homebrew for macOS, and direct downloads for all three platforms. Related projects from the same author include Codexia, a GUI for the OpenAI Codex CLI, awesome-claude-dxt, a curated list of Claude Desktop Extensions, and claw-army/claude-node, a Python subprocess bridge that gives Python code direct access to Claude Code's native capabilities via stream-json.

Developers and AI power users running multiple MCP-compatible clients who want a single place to discover, install, and keep MCP server configurations in sync, rather than editing each client's config file by hand. Support channels include GitHub Discussions for questions and a GitHub Issues tracker for bugs, alongside a project Wiki for troubleshooting. Users who have subscribed to a paid plan should relaunch the app after logging in for the first time for the subscription to take effect.