{
  "markdown": "<p align=\"center\">\n  <img src=\"logo.png\" alt=\"Memphora Logo\" width=\"120\" height=\"120\">\n</p>\n\n<h1 align=\"center\">Memphora MCP Server</h1>\n\n<!-- mcp-name: io.github.Memphora/memphora -->\n\n<p align=\"center\">\n  <strong>Add persistent memory to Claude, Cursor, Windsurf, and other AI assistants using the Model Context Protocol (MCP).</strong>\n</p>\n\n<p align=\"center\">\n  <a href=\"https://pypi.org/project/memphora-mcp/\"><img src=\"https://img.shields.io/pypi/v/memphora-mcp.svg\" alt=\"PyPI\"></a>\n  <a href=\"https://github.com/Memphora/memphora-mcp/blob/main/LICENSE\"><img src=\"https://img.shields.io/badge/license-MIT-blue.svg\" alt=\"License\"></a>\n  <a href=\"https://memphora.ai\"><img src=\"https://img.shields.io/badge/website-memphora.ai-orange.svg\" alt=\"Website\"></a>\n</p>\n\n## What is this?\n\nThis MCP server connects your AI assistant to [Memphora](https://memphora.ai), giving it the ability to:\n\n- **Remember** information across conversations\n- **Search** your personal knowledge base\n- **Extract** insights from conversations automatically\n- **Recall** your preferences, facts, and context\n\n## Quick Start\n\n### 1. Install\n\n```bash\n# Using pip\npip install memphora-mcp\n\n# Or using uvx (recommended for Claude Desktop)\nuvx memphora-mcp\n```\n\n### 2. Get Your API Key\n\n1. Go to [memphora.ai/dashboard](https://memphora.ai/dashboard)\n2. Create an account or sign in\n3. Copy your API key from the dashboard\n\n### 3. Configure Claude Desktop\n\nAdd to your Claude Desktop config file:\n\n**macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`\n**Windows:** `%APPDATA%\\Claude\\claude_desktop_config.json`\n\n```json\n{\n  \"mcpServers\": {\n    \"memphora\": {\n      \"command\": \"uvx\",\n      \"args\": [\"memphora-mcp\"],\n      \"env\": {\n        \"MEMPHORA_API_KEY\": \"your_api_key_here\",\n        \"MEMPHORA_USER_ID\": \"your_unique_user_id\"\n      }\n    }\n  }\n}\n```\n\n### 4. Restart Claude Desktop\n\nClose and reopen Claude Desktop. You should see the Memphora tools available!\n\n## Usage Examples\n\n### Storing Memories\n\nJust tell Claude something about yourself:\n\n```\nYou: \"I work at Google as a software engineer\"\nClaude: [stores memory] \"Got it! I'll remember that you work at Google as a software engineer.\"\n\nYou: \"My favorite programming language is Python\"\nClaude: [stores memory] \"Noted! I'll remember that Python is your favorite programming language.\"\n```\n\n### Recalling Memories\n\nAsk Claude about things you've told it before:\n\n```\nYou: \"Where do I work?\"\nClaude: [searches memories] \"You work at Google as a software engineer.\"\n\nYou: \"What programming languages do I like?\"\nClaude: [searches memories] \"Your favorite programming language is Python.\"\n```\n\n### Automatic Context\n\nClaude will automatically search your memories when relevant:\n\n```\nYou: \"Can you help me with some code?\"\nClaude: [searches memories for context]\n        \"Sure! Since you prefer Python and work at Google, I'll write this in Python \n         following Google's style guide...\"\n```\n\n## Available Tools\n\n| Tool | Description |\n|------|-------------|\n| `memphora_search` | Search memories for relevant information |\n| `memphora_store` | Store new information for future recall |\n| `memphora_extract_conversation` | Extract memories from a conversation |\n| `memphora_list_memories` | List all stored memories |\n| `memphora_delete` | Delete a specific memory |\n\n## Configuration Options\n\n| Environment Variable | Description | Default |\n|---------------------|-------------|---------|\n| `MEMPHORA_API_KEY` | Your Memphora API key | Required |\n| `MEMPHORA_USER_ID` | Unique identifier for your memories | `mcp_default_user` |\n\n## Using with Other MCP Clients\n\n### Cursor\n\nAdd to your Cursor settings:\n\n```json\n{\n  \"mcp\": {\n    \"servers\": {\n      \"memphora\": {\n        \"command\": \"uvx\",\n        \"args\": [\"memphora-mcp\"],\n        \"env\": {\n          \"MEMPHORA_API_KEY\": \"your_api_key_here\"\n        }\n      }\n    }\n  }\n}\n```\n\n### Windsurf\n\nAdd to your Windsurf MCP configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"memphora\": {\n      \"command\": \"python\",\n      \"args\": [\"-m\", \"memphora_mcp\"],\n      \"env\": {\n        \"MEMPHORA_API_KEY\": \"your_api_key_here\"\n      }\n    }\n  }\n}\n```\n\n## Development\n\n### Running Locally\n\n```bash\n# Clone the repo\ngit clone https://github.com/Memphora/memphora-mcp.git\ncd memphora-mcp\n\n# Install dependencies\npip install -e \".[dev]\"\n\n# Set your API key\nexport MEMPHORA_API_KEY=\"your_key\"\n\n# Run the server\npython -m memphora_mcp\n```\n\n### Testing\n\n```bash\npytest tests/\n```\n\n## Privacy & Security\n\n- Your memories are stored securely in Memphora's cloud\n- Each user has isolated memory storage\n- API keys are stored locally on your machine\n- All communication is encrypted via HTTPS\n\n## Support\n\n- Documentation: [memphora.ai/docs](https://memphora.ai/docs)\n- Issues: [GitHub Issues](https://github.com/Memphora/memphora-mcp/issues)\n- Email: support@memphora.ai\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.\n",
  "bytes": 4911,
  "sha": "8a9099744ede849a8777a9cdf020ae7284146454b9215df425cd9f43961fe55a",
  "repo_slug": "memphora/memphora-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_memphora_memphora_aea49ab5/readme"
}