{
  "markdown": "# LLMemory MCP Server\n\nA remote MCP server that lets AI coding agents search and pull context from your imported AI chat history (ChatGPT, Claude, Codex, Claude Code) without copy-pasting. Reads your vault live from your own Google Drive. Zero server-side storage, fully private.\n\n**Server URL:** `https://mcp.llmemory.xyz/mcp`\n**Transport:** Streamable HTTP\n**Auth:** OAuth 2.1 with Dynamic Client Registration (no API keys — browser flow on first use)\n\n## Install in Cline\n\nThis is a **remote MCP server** — no cloning, no npm install, no local process. Cline just needs the URL.\n\n**Option A — Cline Dashboard (recommended):**\n1. Log in to the [Cline Dashboard](https://app.cline.bot) → Organization → MCP Servers\n2. Add a new **Remote MCP server**\n3. Name: `LLMemory` · URL: `https://mcp.llmemory.xyz/mcp`\n4. Save. In VS Code/JetBrains, open the Cline panel → MCP Servers → connect `llmemory`.\n5. On first tool call, a browser window opens — authorize with Google and grant Drive access.\n\n**Option B — Cline MCP config JSON:**\nAdd this to your Cline MCP settings (`cline_mcp_settings.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"llmemory\": {\n      \"type\": \"remote\",\n      \"url\": \"https://mcp.llmemory.xyz/mcp\"\n    }\n  }\n}\n```\n\nRestart the Cline extension. On first tool call, the OAuth browser flow opens automatically.\n\n## Install in other MCP clients\n\nSame URL works in any MCP client that supports Streamable HTTP + OAuth 2.1:\n\n- **Cursor** — [LLMemory Cursor plugin](https://github.com/meir-may/llmemory-cursor-plugin)\n- **VS Code / GitHub Copilot** — add to `.vscode/mcp.json`: `{ \"servers\": { \"llmemory\": { \"type\": \"http\", \"url\": \"https://mcp.llmemory.xyz/mcp\" } } }`\n- **Claude Desktop / Claude Code** — `claude mcp add --transport http llmemory https://mcp.llmemory.xyz/mcp`\n- **Open WebUI** — Admin Settings → External Tools → add Streamable HTTP MCP server with URL `https://mcp.llmemory.xyz/mcp`\n\n## Tools\n\n| Tool | Purpose |\n|---|---|\n| `list_sources` | Show which AI providers have data in your vault and counts |\n| `list_recent` | Recently updated conversations (id, title, source, message count). Filter by `source` |\n| `search_chats` | Full-text search across all imported conversations. Returns snippets + conversation IDs |\n| `get_conversation` | Fetch one full transcript by ID (Markdown or JSON) |\n| `get_context_pack` | Agent-ready briefing (goal, recent state, files, open tasks) for one conversation or a whole folder |\n\n## What it reads\n\nLLMemory reads the `LLMemory/` folder in your Google Drive — a `manifest.json` plus one JSON file per conversation, written by the [LLMemory browser extension](https://llmemory.xyz) or CLI. The server is **read-only** and **zero-storage**: it brokers Google OAuth, streams the result, then forgets everything. Your chats never leave your Drive on a server.\n\n## Privacy\n\n- **Zero server-side storage.** No chat content, no per-user database. Cloudflare Workers free tier.\n- **Your Drive is the storage.** Chats live in your own Google Drive `LLMemory/` folder.\n- **Read-only.** The connector never writes to your vault.\n- **OAuth-scoped.** The server only ever sees your `LLMemory/` Drive folder (`drive.file` scope).\n\nFull privacy posture: [STORE_PRIVACY.md](https://github.com/intrepid37/LLMemory/blob/main/STORE_PRIVACY.md)\n\n## Examples\n\n- *\"What did I figure out about the OAuth worker last week?\"* → searches your vault\n- *\"Pull my most recent Codex session\"* → `list_recent` filtered to `codex`, then `get_conversation`\n- *\"Give me a context pack for the session where we built the Claude connector\"* → `get_context_pack`\n- *\"Show me which chats have data imported\"* → `list_sources`\n\n## Links\n\n- [LLMemory](https://llmemory.xyz)\n- [MCP connector design doc](https://github.com/intrepid37/LLMemory/blob/main/MCP_CONNECTOR.md)\n- [Main repo](https://github.com/intrepid37/LLMemory)\n\n## License\n\nMIT\n",
  "bytes": 3864,
  "sha": "526b40253265f4e0d6b6edcab51f158d902b32733ef9e3bcbaec0b3e3850fa06",
  "repo_slug": "meir-may/llmemory-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_meir_may_llmemory_748c3d1f/readme"
}