Skip to main content
Glama

Bookmark Geni MCP Server

by droidnext
mcp.json4.83 kB
{ "mcpServers": { "bookmarkGeni": { "name": "Bookmark Geni", "version": "1.0.0", "description": "MCP server for processing browser bookmarks, extracting HTML content and metadata, and semantic search", "command": "bash", "args": [ "scripts/start_mcp_server.sh" ], "cwd": ".", "env": { "PYTHON_PATH": "python3" }, "transport": "stdio", "capabilities": { "tools": [ { "name": "generate_bookmarks_metadata", "description": "Generate metadata for bookmarks from selected browsers. Reads bookmark files, extracts URLs and folders, fetches HTML content, extracts descriptions from HTML metadata, creates embeddings using all-MiniLM-L6-v2 sentence transformer model, and stores them in ChromaDB.", "parameters": { "browsers": { "type": "string", "description": "Comma-separated list of browser names (e.g., 'Chrome', 'Chrome,Safari') or 'All' for all browsers. Defaults to 'Chrome' if not provided.", "required": false }, "interactive": { "type": "boolean", "description": "Whether to prompt for browser selection (not implemented in MCP, handled by CLI)", "required": false, "default": false } }, "returns": { "type": "string", "description": "JSON string with generation results including processed count, skipped URLs, and statistics" } }, { "name": "query_bookmarks", "description": "Query bookmarks using semantic search. Performs RAG (Retrieval-Augmented Generation) to find relevant bookmarks based on natural language queries.", "parameters": { "query": { "type": "string", "description": "Search query string", "required": true }, "limit": { "type": "integer", "description": "Maximum number of results to return", "required": false, "default": 10 }, "where": { "type": "object", "description": "Metadata filter dictionary (e.g., {'folder': 'Work'} or {'browser': 'Chrome'})", "required": false } }, "returns": { "type": "string", "description": "JSON string with matching bookmarks including URL, name, description, folder, browser, and relevance score" } }, { "name": "list_browsers", "description": "List all available browsers with detected bookmark paths. Shows which browsers are installed and where their bookmark files are located.", "parameters": {}, "returns": { "type": "string", "description": "JSON string with browser information including available browsers and their bookmark file paths" } }, { "name": "get_stats", "description": "Get statistics about the bookmark database. Returns total bookmark count and collection information.", "parameters": {}, "returns": { "type": "string", "description": "JSON string with database statistics including total bookmarks, collection name, and database path" } }, { "name": "export_embeddings", "description": "Export all embeddings and metadata to a pickle file. This allows transferring data to a remote server.", "parameters": { "pickle_path": { "type": "string", "description": "Path to save the pickle file (default: data/bookmarks_embeddings.pkl)", "required": false } }, "returns": { "type": "string", "description": "JSON string with export results including file path and size" } }, { "name": "import_embeddings", "description": "Import embeddings and metadata from a pickle file. This allows loading data on a remote server.", "parameters": { "pickle_path": { "type": "string", "description": "Path to the pickle file to import", "required": true } }, "returns": { "type": "string", "description": "JSON string with import results including total bookmarks imported" } } ] } } } }

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/droidnext/bookmark_geni_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server