heimdall-mcp-server

概述

Heimdall 是一个 MCP 服务器，为 AI 编程助手创建持久增长的记忆系统。它索引项目文档、Git 历史记录和开发洞察，使 LLM 能够跨对话回忆特定解决方案和模式。服务器使用 Qdrant 进行向量相似性搜索，SQLite 存储元数据，并提供语义搜索能力来存储、检索和管理记忆。

试试问 AI

装完之后，这里有 5 个你可以让 AI 做的事：

• store_memory

  Stores a new piece of information, such as an insight or a solution.

  试试:Remember that we use JWT tokens for authentication in our API试试:Store the solution for the database connection pooling issue we just resolved
• recall_memories

  Performs a semantic search for relevant memories based on a query.

  试试:Find information about our authentication system试试:Recall any previous solutions for handling concurrent database connections
• session_lessons

  Records a key takeaway from the current session for future use.

  试试:Note that we should always validate user input on both client and server sides试试:Remember that the bug was caused by an unexpected null value in the response
• memory_status

  Checks the health and statistics of the memory system.

  试试:How many memories do we currently have stored?试试:Check the memory system health and statistics
• delete_memory

  Delete a specific memory by its unique ID.

  试试:Delete memory with ID 12345试试:Remove that outdated authentication method explanation
• delete_memories_by_tags

  Delete all memories that have any of the specified tags.

  试试:Delete all memories tagged with 'temp-analysis'试试:Remove all task-specific memories

可对比工具

安装

pip install heimdall-mcp

# 初始化项目
heimdall project init

# 对于 Claude Desktop，添加到 config.json:
{
  "mcpServers": {
    "heimdall": {
      "command": "python",
      "args": ["-m", "heimdall.mcp"]
    }
  }
}

FAQ

Heimdall 使用什么数据库？

Heimdall 使用 Qdrant 进行向量相似性搜索，SQLite 存储元数据。

Heimdall 如何与 Git 历史记录集成？

Heimdall 索引整个 Git 历史记录，并可选择安装 Git 钩子来自动在提交时更新记忆。

heimdall-mcp-server 对比