加载中…
Search the web, news, images, videos and books, and extract page content for AI agents.
Open Agent Search 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 Open Agent Search 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 open-agent-search@1.0.5运行此命令前,请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-11T16:11:57.566761Z",
"publishedAt": "2026-10-11T16:11:57.566761Z",
"statusChangedAt": "2026-10-11T16:11:57.566761Z"
}
},
"server": {
"name": "io.github.jayanth-mkv/open-agent-search",
"title": "Open Agent Search",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.0.5",
"packages": [
{
"version": "1.0.5",
"transport": {
"type": "stdio"
},
"identifier": "open-agent-search",
"registryType": "npm",
"packageArguments": [
{
"type": "positional",
"value": "mcp"
}
]
},
{
"version": "1.0.5",
"transport": {
"type": "stdio"
},
"identifier": "open-agent-search",
"runtimeHint": "uvx",
"registryType": "pypi",
"packageArguments": [
{
"type": "positional",
"value": "oas-mcp"
}
],
"runtimeArguments": [
{
"name": "--python",
"type": "named",
"value": "3.12"
},
{
"name": "--from",
"type": "named",
"value": "open-agent-search==1.0.5"
}
]
}
],
"repository": {
"url": "https://github.com/jayanth-mkv/open-agent-search",
"source": "github"
},
"websiteUrl": "https://jayanth-mkv.github.io/open-agent-search/",
"description": "Search the web, news, images, videos and books, and extract page content for AI agents."
}
}