MCP.so
登录

Memory MCP 服务器

@shadowcz007

关于 Memory MCP 服务器

一键启动 memory mcp ,对外提供sse服务

基本信息

分类

记忆与知识

许可证

MIT

运行时

python

传输方式

stdio

发布者

shadowcz007

配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块,请前往代码仓库查看安装说明。

代码仓库

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Memory MCP 服务器?

Memory MCP 服务器 is a knowledge graph management server based on the MCP Servers memory implementation. It supports multiple startup modes—interactive, command line, and JSON configuration—and offers complete knowledge graph operations along with experimental short story generation tied to the graph's context. It is intended for developers or users who need a self-hosted, persistent knowledge graph accessible through the Model Context Protocol.

How to use Memory MCP 服务器?

Run the executable directly for interactive setup (it prompts for port and memory file path), or use command‑line arguments like --port 8080 --memory-path ./memory.json. You can also pipe a JSON‑RPC configuration string (method start with params) to start the server, or use method help to get usage info. The server listens on port 8080 by default and persists data to ./memory.json (configurable via the memory_path parameter).

Key features of Memory MCP 服务器

  • Multiple startup modes: interactive, command line, and JSON configuration
  • Supports MCP tools, resources, and sampling protocols
  • Automatic data persistence in JSON lines format
  • Complete knowledge graph entity and relation management
  • Experimental short story generation based on graph context
  • Flexible port and memory file path configuration

Use cases of Memory MCP 服务器

  • Manage a local knowledge graph with entities, relations, and observations
  • Serve graph data to MCP‑compatible clients via tools and resource endpoints
  • Generate narrative stories that reflect the knowledge graph's current topics
  • Automate graph creation and manipulation through command line or config files
  • Integrate with other MCP servers that consume or query knowledge graphs

FAQ from Memory MCP 服务器

What runtime or dependencies are required to run Memory MCP 服务器?

The README provides a Windows executable (mcp_server_memory.exe) and does not list any external runtime dependencies. It assumes the user has a compatible Windows environment with read/write permissions for the storage path.

Where does Memory MCP 服务器 store its data?

Data is saved in JSON lines format to a file specified by the memory_path parameter (default ./memory.json). The server automatically creates the file and any missing directories on first run. Configuration is also auto‑saved to config.json.

What MCP resources does Memory MCP 服务器 expose?

Two resource URIs are available: memory://short-story/all returns all generated short stories; memory://short-story/{topic} returns stories filtered by a topic keyword (e.g., "science" or "history").

What transport or authentication does Memory MCP 服务器 use?

The README does not describe authentication or encryption. The server listens on a configurable TCP port (default 8080) and expects JSON‑RPC messages over standard input/output or via the JSON configuration pipe. No transport details beyond TCP are specified.

How does Memory MCP 服务器 differ from the original MCP memory server?

The README states it is a modified version of the MCP Servers memory implementation, adding multiple startup modes, JSON configuration, and experimental short story generation. The original server’s core graph operations are preserved.

评论

记忆与知识 分类下的更多 MCP 服务器