Local web search for your LLM over MCP. No API keys, and results are ranked on your machine. Formerly mcp-local-rag.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx mcpsurfr==1.2.3Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
MCPSURFR_MAX_CHARS=<value> claude mcp add nkapila6-mcpsurfr -- uvx mcpsurfr==1.2.3在終端機中執行。
{ "mcpServers": { "nkapila6-mcpsurfr": { "command": "uvx", "args": [ "mcpsurfr==1.2.3" ], "env": { "MCPSURFR_MAX_CHARS": "<value>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Local web search for your LLM over MCP. No API keys, and results are ranked on your machine. Formerly mcp-local-rag.
Local web search MCP server, formerly mcp-local-rag. Multi-engine deep research with on-device re-ranking. ✨ no API keys ✨
%%{init: {'theme': 'base'}}%%
flowchart TD
A[LLM] -->|query| S["Search with ddgs (auto: several engines, no keys)"]
S -->|"rag_search, deep_research"| R["Re-rank results locally (MobileBERT on numpy)"]
R --> P[Fetch top pages, keep the main content]
P -->|page text + URLs| A
S -->|search| T1["Tier 1: pick pages by their snippets"]
T1 --> T2["Tier 2: split into passages, keyword match (BM25)"]
T2 -->|few hits| OUT["Best passages + URLs (about 800 tokens)"]
T2 -->|too many or none| T3[Tier 3: rank them by meaning]
T3 --> OUT
OUT --> A
What's in it:
auto mode asks several engines at once and skips blocked ones.search returns just the paragraphs that answer the question, about a tenth of the tokens. When nothing matches well, it can ask you whether you want the full pages instead.truncated, and fallbacks and engine failures show up as warnings. Google blocks often, so it falls back to auto on its own.research prompt, so clients pick up how to use it without setup.Backends: auto (default), brave, duckduckgo, google, grokipedia, mojeek, startpage, wikipedia, yahoo. auto and brave are the dependable ones.
With uv:
{
"mcpServers": {
"mcpsurfr": {
"command": "uvx",
"args": ["--from", "git+https://github.com/nkapila6/mcpsurfr", "mcpsurfr"]
}
}
}
Or with Docker (amd64 and arm64):
{
"mcpServers": {
"mcpsurfr": {
"command": "docker",
"args": ["run", "--rm", "-i", "--init", "ghcr.io/nkapila6/mcpsurfr:latest"]
}
}
}
Full-page tools share a 40k-character budget per call (about 10k tokens). To change it, add "env": {"MCPSURFR_MAX_CHARS": "80000"} to the server entry.
Not sure where your config lives? See the MCP quickstart. Tested with Claude Desktop, Claude Code, Cursor and Goose.
Coming from mcp-local-rag? Your old config keeps working, since the old URL redirects and the mcp-local-rag command still exists. Switching to the config above gets you the new name and drops the --python=3.10 pin (3.10 reaches end of life this month).
The mcpsurfr-search skill tells the model which tool and backend to pick and how to cite. The server serves it as skill://mcpsurfr-search/SKILL.md, so most clients need nothing extra. To add it to Claude Desktop by hand: Settings → Skills → Add from folder, then pick src/mcpsurfr/skills/mcpsurfr-search/.
The research(topic) prompt plans a few search terms, runs deep_research and writes a cited summary.
Asking Claude Desktop about something newer than its training data:
Security audit by MseeP · Issues and PRs welcome · MIT licensed · Buy me a coffee if it helps you
Local web search MCP server, formerly mcp-local-rag. Multi-engine deep research with on-device re-ranking. ✨ no API keys ✨
{ "mcpServers": { "nkapila6-mcpsurfr": { "command": "uvx", "args": [ "mcpsurfr==1.2.3" ], "env": { "MCPSURFR_MAX_CHARS": "<value>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數:MCPSURFR_MAX_CHARS。
Mcpsurfr 透過 stdio 在本機執行。
上次檢查時間:2026-10-27。 Local web search MCP server, formerly mcp-local-rag. Multi-engine deep research with on-device re-ranking. ✨ no API keys ✨