加载中…
Free web search and long-term memory for AI assistants. No API keys; data stays local.
Search Memory 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 78/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 Search Memory 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
npx -y search-memory-mcp@1.1.0运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-25T08:56:40.341271Z",
"publishedAt": "2026-10-25T08:56:40.341271Z",
"statusChangedAt": "2026-10-25T08:56:40.341271Z"
}
},
"server": {
"name": "io.github.kefyusuf/search-memory-mcp",
"title": "Search Memory",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.1.0",
"packages": [
{
"version": "1.1.0",
"transport": {
"type": "stdio"
},
"identifier": "search-memory-mcp",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"environmentVariables": [
{
"name": "SEARCH_PROVIDERS",
"description": "Comma-separated search provider order, for example duckduckgo,marginalia,bing"
},
{
"name": "CACHE_DB_PATH",
"description": "Path of the local SQLite database for cache, memory, and index"
},
{
"name": "INGEST_ALLOWED_DIRS",
"description": "Comma-separated directories whose files ingest_document may read; local file reading is off when unset"
},
{
"name": "SEARXNG_BASE_URL",
"description": "Base URL of a SearXNG instance with JSON output, used by the searxng provider"
},
{
"name": "BRAVE_SEARCH_API_KEY",
"isSecret": true,
"description": "Optional Brave Search API key; the brave provider then uses the official API instead of scraping"
},
{
"name": "TAVILY_API_KEY",
"isSecret": true,
"description": "Optional Tavily API key; adds the tavily provider with news-topic search and publish dates"
},
{
"name": "EXA_API_KEY",
"isSecret": true,
"description": "Optional Exa API key; adds the exa provider with neural (semantic) web search"
},
{
"name": "READER_FALLBACK_URL",
"description": "Optional reader service (for example https://markdown.new/) used when a page cannot be fetched directly; sends the page URL to that service"
}
]
}
],
"repository": {
"url": "https://github.com/kefyusuf/search-memory-mcp",
"source": "github"
},
"description": "Free web search and long-term memory for AI assistants. No API keys; data stays local."
}
}