加载中…
Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.
io.github.HarimxChoi/google-surf-mcp 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 io.github.HarimxChoi/google-surf-mcp 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 google-surf-mcp@1.1.4运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-20T01:01:10.879215Z",
"publishedAt": "2026-10-20T01:01:10.879215Z",
"statusChangedAt": "2026-10-20T01:01:10.879215Z"
}
},
"server": {
"name": "io.github.HarimxChoi/google-surf-mcp",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.1.4",
"packages": [
{
"version": "1.1.4",
"transport": {
"type": "stdio"
},
"identifier": "google-surf-mcp",
"registryType": "npm",
"environmentVariables": [
{
"name": "SEARCH_API",
"format": "string",
"isSecret": true,
"description": "SearchApi API key. Required only for SearchApi primary or fallback modes."
},
{
"name": "SURF_SEARCH_PROVIDER",
"format": "string",
"description": "Provider for search and search_parallel: browser, searchapi, or fallback. Defaults to browser."
},
{
"name": "SURF_SCHOLAR_PROVIDER",
"format": "string",
"description": "Provider for scholar_search: browser, searchapi, or fallback. Defaults to browser."
},
{
"name": "SURF_BROWSER_ENGINE",
"format": "string",
"description": "Browser engine: auto, native, or playwright. Auto uses one hidden native Chrome broker shared across local MCP sessions."
},
{
"name": "CHROME_PATH",
"format": "string",
"description": "Absolute path to the Chrome binary. Auto-detected on Windows/macOS/Linux when omitted."
},
{
"name": "SURF_PROFILE_ROOT",
"format": "string",
"description": "Directory for the warm Chrome profile. Defaults to ~/.google-surf-mcp."
},
{
"name": "SURF_RESEARCH",
"format": "string",
"description": "Enable local project memory and hybrid retrieval. Defaults to true."
},
{
"name": "SURF_RETRIEVAL_MODE",
"format": "string",
"description": "Shared route for search and search_parallel: live or hybrid. Defaults to hybrid."
},
{
"name": "SURF_RESEARCH_ROOT",
"format": "string",
"description": "Embedded SurrealDB data directory. Defaults to <profile>/research."
},
{
"name": "SURF_RESEARCH_VECTOR_MODEL",
"format": "string",
"description": "Local model for HNSW retrieval and shared reranking. Defaults to Xenova/multilingual-e5-small; use off to disable."
},
{
"name": "SURF_RESEARCH_VECTOR_LOW_MEMORY",
"format": "string",
"description": "Disable ONNX CPU memory arena and memory pattern. Defaults to true."
},
{
"name": "SURF_RESEARCH_VECTOR_THREADS",
"format": "string",
"description": "ONNX intra-op thread count from 1 to 16. Defaults to 4."
},
{
"name": "SURF_RESEARCH_REPO_AUTO",
"format": "string",
"description": "Sparse-index at most one eligible small GitHub repository per search call. Defaults to true."
},
{
"name": "SURF_RESEARCH_REPO_AUTO_MAX_MB",
"format": "string",
"description": "Maximum searchable repository source-text size in MB. Assets are excluded. Defaults to 20."
},
{
"name": "SURF_RESEARCH_REPO_AUTO_MAX_FILES",
"format": "string",
"description": "Maximum repository source file count for automatic indexing. Defaults to 2000."
},
{
"name": "SURF_RESEARCH_BROKER_IDLE_MS",
"format": "string",
"description": "Shared research broker idle lifetime in milliseconds. Defaults to 60000."
},
{
"name": "SURF_RESEARCH_READ_CONCURRENCY",
"format": "string",
"description": "Maximum concurrent research broker reads. Defaults to 4."
},
{
"name": "SURF_RESEARCH_QUERY_TIMEOUT_MS",
"format": "string",
"description": "Timeout per embedded SurrealDB query in milliseconds. Defaults to 120000; timed-out retrieval lanes are reported as partial."
},
{
"name": "GITHUB_TOKEN",
"format": "string",
"isSecret": true,
"description": "Optional token that raises GitHub API limits for repository inspection."
},
{
"name": "SURF_LOCALE",
"format": "string",
"description": "Browser locale, e.g. en-US."
},
{
"name": "SURF_TZ",
"format": "string",
"description": "IANA timezone, e.g. America/New_York. Defaults to system timezone."
},
{
"name": "SURF_HEADLESS",
"format": "string",
"description": "Controls Playwright extraction, compatibility, and recovery paths. Native search hides normal system Chrome and shows it only for CAPTCHA recovery."
},
{
"name": "SURF_IDLE_CLOSE_MS",
"format": "string",
"description": "Idle ms before closing the sequential ctx and pool. 0 disables idle auto-close. Defaults to 30000."
},
{
"name": "SURF_ALLOW_PRIVATE",
"format": "string",
"description": "Set to 'true' to allow extract on private/loopback addresses (localhost, 10.x, 192.168.x, 169.254.x, etc). Default blocks them as an SSRF guard."
},
{
"name": "SURF_LLM_HEAL",
"format": "string",
"description": "Enable the optional workflow-only LLM selector repair path. Defaults to false."
},
{
"name": "SURF_LLM_PROVIDER",
"format": "string",
"description": "LLM selector repair provider: anthropic or orcarouter. Defaults to anthropic."
},
{
"name": "SURF_LLM_MODEL",
"format": "string",
"description": "Optional model override. OrcaRouter defaults to orcarouter/auto."
},
{
"name": "ANTHROPIC_API_KEY",
"format": "string",
"isSecret": true,
"description": "Anthropic API key for optional LLM-assisted selector repair."
},
{
"name": "ORCAROUTER_API_KEY",
"format": "string",
"isSecret": true,
"description": "OrcaRouter API key for optional LLM-assisted selector repair."
}
]
}
],
"repository": {
"url": "https://github.com/HarimxChoi/google-surf-mcp",
"source": "github"
},
"description": "Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links."
}
}