mTarsier
mTarsier - The Open Source MCP & Skill Manager for Claude, Cursor, VS Code & any AI client.
What is mTarsier?
mTarsier is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mtarsier - the open source mcp & skill manager for claude, cursor, vs code & any ai client.
mTarsier - The Open Source MCP & Skill Manager for Claude, Cursor, VS Code & any AI client.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- mTarsier - The Open Source MCP & Skill Manager for Claude, C
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mtarsierConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use mTarsier
mTarsier is an open-source MCP and skill manager that provides a unified dashboard to install, configure, and manage Model Context Protocol servers across Claude Desktop, Cursor, VS Code, Windsurf, and Claude Code from a single interface. It includes a marketplace for browsing community MCP servers and skills, a config editor with live JSON validation and rollback support, and a CLI tool (`tsr`) for scriptable management. Developers who maintain MCP setups across multiple AI clients will find mTarsier eliminates the need to hand-edit separate JSON config files for each client.
Prerequisites
- macOS, Windows, or Linux desktop operating system
- At least one supported AI client installed: Claude Desktop, Cursor, VS Code, or Windsurf
- mTarsier binary downloaded from the GitHub Releases page (no npm/pip install — direct binary)
- An MCP client application capable of running local MCP servers
Download the mTarsier binary
Go to the GitHub Releases page at https://github.com/mcp360/mTarsier/releases/latest and download the binary for your platform (macOS, Windows, or Linux). No package manager installation is needed — mTarsier ships as a self-contained executable.
# macOS example after downloading
chmod +x mTarsier-macos
mv mTarsier-macos /usr/local/bin/tsrLaunch the mTarsier dashboard
Run the `tsr` CLI to open the unified dashboard. mTarsier will auto-detect all supported AI clients installed on your system and display a summary of each client's current MCP server configurations.
tsr listBrowse and install an MCP server from the marketplace
Use the `tsr install` command to search the marketplace and install a server. mTarsier will update the correct config file for the target client automatically, without you needing to locate or edit the JSON manually.
tsr install brave-search
# Install to a specific client
tsr install brave-search --client cursorOpen and edit a client config in the built-in editor
The built-in config editor provides syntax highlighting and live JSON validation. Use it to inspect or modify a client's MCP configuration. Changes can be rolled back if something breaks.
tsr config cursor --edit
tsr config claude-desktop --editManage skills across clients
mTarsier also manages Claude Code skills (SKILL.md files). Search the skills marketplace, install skills into specific clients, or copy skills between clients.
tsr skills search "frontend design"
tsr skills install anthropics/courses/prompt-eng --client claude-codeRun a health check on installed servers
Use the ping command to verify that your MCP servers are responding correctly. This is useful after making config changes to confirm a server is up before starting your AI client.
tsr ping brave-searchmTarsier Examples
Client configuration
mTarsier itself does not run as an MCP server; it manages the config files for your AI clients. Below is an example of what mTarsier would write into claude_desktop_config.json when you install a server like brave-search.
{
"mcpServers": {
"brave-search": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-brave-search"],
"env": {
"BRAVE_API_KEY": "your-brave-api-key"
}
}
}
}Prompts to try
After launching mTarsier via the tsr CLI, these are typical tasks you can perform:
- "List all MCP servers currently installed across my AI clients"
- "Install the filesystem MCP server for Claude Desktop"
- "Show me the config for my Cursor MCP setup"
- "Search the skills marketplace for coding assistant skills"
- "Copy the prompt-engineering skill from Claude Desktop to VS Code"Troubleshooting mTarsier
mTarsier does not detect an installed AI client
Confirm the client is installed at its default path. mTarsier looks for config files at known locations (e.g., ~/Library/Application Support/Claude/ for Claude Desktop on macOS). If you installed the client to a custom path, the auto-detection may not find it.
Config changes made via mTarsier do not appear in the AI client
Restart the AI client after making changes. Most MCP clients (Claude Desktop, Cursor) only read their config files on startup, so a restart is required for new servers to appear.
tsr command not found after downloading the binary
Ensure the binary is executable (`chmod +x`) and is located in a directory on your PATH such as /usr/local/bin. Verify with `which tsr` after moving it.
Frequently Asked Questions about mTarsier
What is mTarsier?
mTarsier is a Model Context Protocol (MCP) server that mtarsier - the open source mcp & skill manager for claude, cursor, vs code & any ai client. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install mTarsier?
Follow the installation instructions on the mTarsier GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with mTarsier?
mTarsier works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is mTarsier free to use?
Yes, mTarsier is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
mTarsier Alternatives — Similar Coding Agents Servers
Looking for alternatives to mTarsier? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up mTarsier in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use mTarsier?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.