mcpsurfr

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/nkapila6-mcpsurfr

About

Use cases: web-search, deep-research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

6 read · 0 write · 0 deleteRead-only

Secrets

None asked for

Install scripts

None found

Runs as

Docker image

Tools (6)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• deep_researchDeep research

  Research a topic across several search terms and engines. Each term is searched on each backend, results are re-ranked locally by relevance, duplicates are removed, and the best pages are fetched as text. Backends: auto, brave, duckduckgo, google, grokipedia, mojeek, startpage, wikipedia, yahoo. - "auto" (default): ddgs metasearch over several engines, skipping blocked ones. Most reliable. - "brave": fast and usually available. - "wikipedia": exact article lookups, best with title-like terms. - "google", "startpage", "yahoo", "mojeek": often blocked. Empty engines are reported as warnings, …

• deep_research_ddgsDeep research (ddgs auto)

  Deep research using ddgs "auto" metasearch, which queries several engines per term and skips blocked ones. Results are re-ranked locally, de-duplicated and the best pages fetched as text. Same as deep_research with its default backend. Args: search_terms (List[str]): 2-5 specific, related search queries. num_results_per_term (int): Number of results to rank per search term. top_k_per_term (int): Number of top-ranked results to keep per search term. include_urls (bool): Whether to include each page's source URL. Returns: Same shape as deep_research.

• deep_research_googleDeep research (Google)

  Deep research using only Google: each term is searched, re-ranked locally, de-duplicated and the best pages fetched as text. Google often blocks scrapers. If it returns nothing, the terms are retried with ddgs "auto" metasearch and a warning is sent. Args: search_terms (List[str]): 2-5 specific, related search queries. num_results_per_term (int): Number of results to rank per search term. top_k_per_term (int): Number of top-ranked results to keep per search term. include_urls (bool): Whether to include each page's source URL. Returns: Same shape as deep_research.

• rag_search_ddgsWeb search

  Search the web and return the most relevant pages as text. Default choice for lookups. Uses ddgs "auto" metasearch, which queries several engines (DuckDuckGo, Brave, Wikipedia, ...) and skips any that are blocked. Results are re-ranked locally by semantic similarity to the query before the top pages are fetched. Args: query (str): The search query. Use natural language questions or keywords. Example: "latest developments in quantum computing" num_results (int): Number of initial search results to rank. More results provide better coverage but incr…

• rag_search_googleGoogle search

  Search Google and return the most relevant pages as text, re-ranked locally by semantic similarity. Google often blocks scrapers. When it returns nothing, this retries with ddgs "auto" metasearch and sends a warning saying so. Args: query (str): The query to search for. num_results (int): Number of initial search results to rank. top_k (int): Number of top-ranked pages to fetch and return. include_urls (bool): Whether to include each page's source URL. Returns: Same shape as rag_search_ddgs, with "backend": "auto" and "fallback": true when Google returned nothing.

• searchSearch (passages)

  Search the web and return only the passages that answer the query, not whole pages: usually about a tenth of the text of rag_search_ddgs. Use this first. Tiers, cheapest first: 1. Search, then keep the top_pages results whose title/snippet match best. 2. Fetch those pages, split them into ~600-char passages, keyword-match them (BM25) against the query plus `keywords`. 3. Only if that leaves too many candidates, or matches nothing (a paraphrase), the local embedder ranks them by meaning. If nothing matched the keywords and the client can show questions, the user is asked whether they wan…

Compare and alternatives

Featured in

• Best MCP servers for web search

Signals

Stars

134

Forks

21

Open issues

2

Contributors

5

Last commit

Oct 23, 2026 (7 days ago)

Last release

Oct 23, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.nkapila6/mcpsurfr

Version

1.1.1

Auth

No auth

Packages

oci ghcr.io/nkapila6/mcpsurfr:v1.1.1

License

MIT

Repository

github.com/nkapila6/mcpsurfr

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql