@shadowcz007
Basic information
一键启动 memory mcp ，对外提供sse服务
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.
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).
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.
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`.
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").
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.
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.
The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your
Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
Comments