{
  "markdown": "<!-- mcp-name: io.github.snowmanjy/hippodid-mcp-server -->\n\n<p align=\"center\">\n  <img src=\"docs/assets/hippodid-hero.png\" alt=\"HippoDid MCP Server — persistent cloud memory for AI agents\" width=\"780\" />\n</p>\n\n<p align=\"center\">\n  <strong>HippoDid MCP Server</strong><br/>\n  Persistent, portable memory for AI agents. Your AI forgets everything between sessions. HippoDid remembers.\n</p>\n\n---\n\n# HippoDid MCP Server\n\nMCP (Model Context Protocol) server for [HippoDid](https://hippodid.com) — connects Claude Code, Claude Desktop, ChatGPT, Gemini CLI, Codex CLI, Cursor, and any MCP-compatible client to persistent AI character memory.\n\n## What is HippoDid?\n\nHippoDid is a cloud memory infrastructure for AI agents. It stores structured memories (preferences, decisions, skills, relationships) in a searchable database and retrieves them across sessions, tools, and AI providers. Write a memory in Claude Code, recall it in ChatGPT. Switch from Cursor to Gemini — your agent's memory travels with it.\n\nKey features:\n- **Cross-platform memory** — same memories accessible from any MCP client or ChatGPT via OAuth\n- **Structured extraction** — raw text is automatically parsed into categorized facts with salience scores\n- **Temporal decay** — memories fade naturally by category (skills are evergreen, events fade in 14 days)\n- **Character scoping** — each agent/project gets its own memory namespace\n- **BYOK AI** — bring your own OpenAI, Anthropic, or Gemini key for extraction\n\n## Quick Start\n\n### 1. Get an API Key\n\nSign up at [hippodid.com](https://hippodid.com) and create an API key from your dashboard.\n\n### 2. Download the JAR\n\nDownload the latest release from [GitHub Releases](https://github.com/SameThoughts/hippodid-mcp-server/releases).\n\n### 3. Configure Claude Desktop\n\nAdd to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS):\n\n```json\n{\n  \"mcpServers\": {\n    \"hippodid\": {\n      \"command\": \"java\",\n      \"args\": [\"-jar\", \"/path/to/hippodid-mcp-server-1.1.0.jar\"],\n      \"env\": {\n        \"HIPPODID_API_KEY\": \"hd_key_your_key_here\",\n        \"HIPPODID_CHARACTER_ID\": \"your-character-uuid\"\n      }\n    }\n  }\n}\n```\n\n### 4. Start Using\n\nAsk Claude to remember things, search memories, sync files, and more.\n\n## MCP Tools\n\n| Tool | Description |\n|------|-------------|\n| `create_character` | Create a new character to store memories for |\n| `list_characters` | List all characters accessible to you |\n| `add_memory` | Add a memory via the AUDN pipeline (rule-based salience + dedup) |\n| `add_memory_direct` | Write a memory directly, bypassing AUDN pipeline (Starter+ tier) |\n| `search_memories` | Hybrid semantic + keyword search across memories |\n| `sync_file` | Sync a local file to the HippoDid cloud |\n| `import_document` | Import a document and extract memories (Starter+ tier) |\n| `list_synced_files` | List files synced to the cloud for a character |\n| `get_sync_status` | Get sync status summary for a character |\n| `export_character` | Export all memories for a character as Markdown |\n| `add_watch_path` | Sync a file and register the path for background tracking |\n| `list_watch_paths` | List all watched file paths in this session |\n| `force_sync` | Force an immediate sync of all watched paths |\n| `configure_ai` | Configure tenant BYOK AI providers |\n| `test_ai_config` | Test connectivity of saved AI provider configuration |\n\n## Environment Variables\n\n| Variable | Required | Default | Description |\n|----------|----------|---------|-------------|\n| `HIPPODID_API_KEY` | Yes | — | Your HippoDid API key |\n| `HIPPODID_CHARACTER_ID` | No | — | Default character UUID for background sync |\n| `HIPPODID_BASE_URL` | No | `https://api.hippodid.com` | API base URL |\n| `MCP_SYNC_INTERVAL` | No | `300` | Background sync interval in seconds |\n| `MCP_AUTO_CAPTURE` | No | `false` | Disable background watcher (AI handles sync) |\n| `MCP_AUTO_RECALL` | No | `false` | Disable background hydration (AI handles download) |\n| `MCP_RECALL_CACHE_TTL` | No | `120` | Search result cache TTL in seconds |\n\n## Architecture\n\n```\nClaude Desktop → stdio (JSON-RPC) → McpServerRunner → HippoDidClient → HTTP → HippoDid REST API\n```\n\nThe MCP server uses the [hippodid-spring-boot-starter](https://github.com/SameThoughts/hippodid-spring-boot-starter) to communicate with the HippoDid REST API over HTTP. All authentication and tenant isolation is handled server-side via Bearer tokens.\n\n## Building from Source\n\nRequires Java 21+ and Maven 3.8+.\n\n```bash\nmvn clean package -DskipTests\njava -jar target/hippodid-mcp-server-1.1.0.jar\n```\n\n## Versioning\n\nThe MCP server version matches the [hippodid-spring-boot-starter](https://github.com/SameThoughts/hippodid-spring-boot-starter) version. Both must be at the same version for compatibility.\n\n## License\n\nApache License 2.0 — see [LICENSE](LICENSE).",
  "bytes": 4852,
  "sha": "3b56cde86f269135b72cfacc866f0e8834b150809e710cf717ad75e669668dab",
  "repo_slug": "samethoughts/hippodid-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_snowmanjy_hippodid_mcp_server_6e2d2959/readme"
}