--- title: "Overview" description: "Use machine-memory via the Model Context Protocol when the CLI is not available" --- > Documentation Index > Fetch the complete documentation index at: https://machine-memory.jfa.dev/llms.txt > Use this file to discover all available pages before exploring further. # Overview Machine Memory’s remote Worker can act as a [Model Context Protocol](https://modelcontextprotocol.io) server. Agents connect with OAuth 2.1, then call tools to search and write project memories. Access is limited to the configured GitHub user ID and repository slug, not a shared bearer token. > Only GitHub OAuth is supported for now. ## Who this is for This is made for any users of any primitive that doesn't allow or discourages persistent environments, such as [Amp's Orbs](https://ampcode.com/what-are-orbs) or chatbot-exclusive environments, where there is not a possibility to access such a tool. ## Setup path 1. [Infrastructure](/infrastructure/overview) — deploy the Alchemy stack (Worker, D1, Vectorize, Workers AI). 2. [Enable MCP](/docs/mcp/enable) — GitHub OAuth app + secrets, then redeploy. 3. [Init](/docs/mcp/init) — drop the managed MCP block into `AGENTS.md` (public script or `machine-memory init --mcp`). 4. [Tools](/docs/mcp/tools) — connect a client to `https:///mcp` and use the tool surface. ## Connect a client Point an OAuth-capable MCP client at: ```text https:///mcp ``` Discovery endpoints: - Authorization server: `https:///.well-known/oauth-authorization-server` - Protected resource: `https:///.well-known/oauth-protected-resource` On first connect the browser opens authorization: the client registers, GitHub identity is verified, and tokens carry `mcp:read` and `mcp:write`. After that, tools from [Tools](/docs/mcp/tools) are available. ## Troubleshooting OAuth, cookie signing, sandbox credentials, and deploy gotchas: [Troubleshooting: MCP](/troubleshooting/mcp). Source: https://machine-memory.jfa.dev/docs/mcp/overview/index.mdx