HippoDid MCP Server
Provides persistent, cloud-based memory for AI agents, letting them remember preferences, skills, and decisions across sessions via an MCP-compatible interface.
README
<!-- mcp-name: io.github.snowmanjy/hippodid-mcp-server -->
<p align="center"> <img src="docs/assets/hippodid-hero.png" alt="HippoDid MCP Server — persistent cloud memory for AI agents" width="780" /> </p>
<p align="center"> <strong>HippoDid MCP Server</strong><br/> Persistent, portable memory for AI agents. Your AI forgets everything between sessions. HippoDid remembers. </p>
HippoDid MCP Server
MCP (Model Context Protocol) server for HippoDid — connects Claude Code, Claude Desktop, ChatGPT, Gemini CLI, Codex CLI, Cursor, and any MCP-compatible client to persistent AI character memory.
What is HippoDid?
HippoDid 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.
Key features:
- Cross-platform memory — same memories accessible from any MCP client or ChatGPT via OAuth
- Structured extraction — raw text is automatically parsed into categorized facts with salience scores
- Temporal decay — memories fade naturally by category (skills are evergreen, events fade in 14 days)
- Character scoping — each agent/project gets its own memory namespace
- BYOK AI — bring your own OpenAI, Anthropic, or Gemini key for extraction
Quick Start
1. Get an API Key
Sign up at hippodid.com and create an API key from your dashboard.
2. Download the JAR
Download the latest release from GitHub Releases.
3. Configure Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"hippodid": {
"command": "java",
"args": ["-jar", "/path/to/hippodid-mcp-server-1.1.0.jar"],
"env": {
"HIPPODID_API_KEY": "hd_key_your_key_here",
"HIPPODID_CHARACTER_ID": "your-character-uuid"
}
}
}
}
4. Start Using
Ask Claude to remember things, search memories, sync files, and more.
MCP Tools
| Tool | Description |
|---|---|
create_character |
Create a new character to store memories for |
list_characters |
List all characters accessible to you |
add_memory |
Add a memory via the AUDN pipeline (rule-based salience + dedup) |
add_memory_direct |
Write a memory directly, bypassing AUDN pipeline (Starter+ tier) |
search_memories |
Hybrid semantic + keyword search across memories |
sync_file |
Sync a local file to the HippoDid cloud |
import_document |
Import a document and extract memories (Starter+ tier) |
list_synced_files |
List files synced to the cloud for a character |
get_sync_status |
Get sync status summary for a character |
export_character |
Export all memories for a character as Markdown |
add_watch_path |
Sync a file and register the path for background tracking |
list_watch_paths |
List all watched file paths in this session |
force_sync |
Force an immediate sync of all watched paths |
configure_ai |
Configure tenant BYOK AI providers |
test_ai_config |
Test connectivity of saved AI provider configuration |
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
HIPPODID_API_KEY |
Yes | — | Your HippoDid API key |
HIPPODID_CHARACTER_ID |
No | — | Default character UUID for background sync |
HIPPODID_BASE_URL |
No | https://api.hippodid.com |
API base URL |
MCP_SYNC_INTERVAL |
No | 300 |
Background sync interval in seconds |
MCP_AUTO_CAPTURE |
No | false |
Disable background watcher (AI handles sync) |
MCP_AUTO_RECALL |
No | false |
Disable background hydration (AI handles download) |
MCP_RECALL_CACHE_TTL |
No | 120 |
Search result cache TTL in seconds |
Architecture
Claude Desktop → stdio (JSON-RPC) → McpServerRunner → HippoDidClient → HTTP → HippoDid REST API
The MCP server uses the 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.
Building from Source
Requires Java 21+ and Maven 3.8+.
mvn clean package -DskipTests
java -jar target/hippodid-mcp-server-1.1.0.jar
Versioning
The MCP server version matches the hippodid-spring-boot-starter version. Both must be at the same version for compatibility.
License
Apache License 2.0 — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。