Claude-OS MCP Server

How to use Claude-OS MCP Server

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/projects"]
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "your_token" }
    },
    "memory": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-memory"]
    }
  }
}

What is Claude-OS MCP Server?

Claude-OS is a Python MCP server. A concise Claude reference bundle for developers, covering commands, MCP servers, plugins, tools, workflows, and agent frameworks in one place. Designed for fast discovery and practical integration. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Key capabilities

• Tool access support
• Shell commands support
• Browser use support
• Document generation support
• Anthropic provider support
• Ollama provider support
• Connecting agents to external tools and data

Compatibility and setup

• Built for Python
• Built for Go
• Uses SSE transport
• API key required
• Local files
• Database access
• Network access

Requirements and access

Security and permissions

Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.

When to use Claude-OS MCP Server

• Use it for connecting agents to external tools and data.
• Use it for integrations workflows.
• Use it for coding workflows.
• Use it for data workflows.

Built with

Verified compatibility and discovery

Frequently asked questions