MCP低风险未认领

Graph-Mem

Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.

Sathvik-1007sathvik-1007/graphmem-mcp★ 1更新于 2026年7月21日

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.Sathvik-1007/graphmem-mcp",
  "description": "Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.",
  "title": "Graph-Mem",
  "repository": {
    "url": "https://github.com/Sathvik-1007/GraphMem-MCP",
    "source": "github"
  },
  "version": "1.0.0",
  "websiteUrl": "https://github.com/Sathvik-1007/GraphMem-MCP#readme",
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "graphmem-mcp",
      "version": "1.0.0",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Path to the SQLite database file. Defaults to .graphmem/graph.db relative to the working directory.",
          "name": "GRAPHMEM_DB_PATH"
        },
        {
          "description": "sentence-transformers model ID used for semantic search. Defaults to all-MiniLM-L6-v2, downloaded on first use.",
          "name": "GRAPHMEM_EMBEDDING_MODEL"
        },
        {
          "description": "Maximum entities visited by a single graph traversal. Defaults to 5000.",
          "name": "GRAPHMEM_TRAVERSAL_NODE_BUDGET"
        },
        {
          "description": "Logging verbosity: DEBUG, INFO, WARNING, ERROR, or CRITICAL. Defaults to WARNING.",
          "name": "GRAPHMEM_LOG_LEVEL"
        }
      ]
    }
  ]
}

权限

声明检测
运行代码—python
安装—pypi:graphmem-mcp@1.0.0
安装时运行脚本—无
网络无无
需要的凭据无无
工作区外的路径—无
智能体工具—无

检查

低风险 · 没有发现需要提醒的地方。

未经人工审核 · 已做规则检查;模型审核尚未开启。

版本

  1. #11.0.0最新2026年10月7日