Skip to main content
Glama
lzmd66

clean-search-mcp

by lzmd66
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

clean-search-mcp 🧹

A lightweight MCP (Model Context Protocol) service that provides clean, spam-free search results for AI agents. Filters out content farms, malware sites, SEO garbage, and low-quality content before they reach your LLM.

Features

  • Three search engines — Yandex + Bing + DuckDuckGo auto-fallback

  • 176K+ domain blocklist — auto-updated from 25+ community sources, covers malware/scam/ads/trackers/content farms

  • Three-layer filtering — domain blacklist → content rules → quality scoring

  • Content extraction — full page text via trafilatura + selectolax

  • Result scoring — 0-1 quality score (official docs 0.8 > tutorials 0.6 > garbage 0)

  • LRU cache — search cache 6h, fetch cache 24h, auto-cleanup

  • User blacklist — add domains on the fly, report bad results

  • Deep mode — optional Playwright fallback for JS-heavy pages

  • No heavy dependencies — pure HTTP, no browser required

Related MCP server: evo-scry

Quick Start

pip install -r requirements.txt
python main.py

MCP Client Config

{
  "mcpServers": {
    "clean-search": {
      "command": "python",
      "args": ["/path/to/clean_search_mcp/main.py"]
    }
  }
}

Test Locally

python test_local.py "your search query" -n 5
python test_local.py "your query" -n 5 --no-content   # skip page content
python test_local.py "your query" --deep               # use Playwright fallback

API

clean_search(query, max_results=5, with_content=True, deep_mode=False)

Param

Default

Description

query

required

Search query

max_results

5

Results to return (max 10)

with_content

True

Include extracted page text

deep_mode

False

Use Playwright fallback for JS pages

Returns [{title, url, snippet, content, score}] sorted by quality.

add_user_blacklist(domain)

Add a domain to personal blocklist.

report_bad_result(url)

Report a low-quality URL (domain auto-blocked).

Configuration

Edit config.py to tune:

  • Search providers: enable/disable Yandex, Bing, DuckDuckGo

  • Blacklist sources: add or remove community blocklist URLs

  • Scoring weights: adjust domain authority, content quality bonuses

  • Caching: TTL, max files, cleanup interval

  • Proxy: set PROXY for HTTP/Playwright

Dependencies

mcp, httpx, selectolax, trafilatura, duckduckgo-search

All lightweight pip packages. Playwright is optional (deep mode only).

License

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

  • SSearchB
    cc.ssearch

    Free web search for AI agents. No API key required. Hosted MCP in active development.

    SearchBrowser Automation
    71
  • qsearchA
    io.github.theYahia

    Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.

    SearchRAG Systems
    22
  • MESSORAA
    dev.messora

    Scrape, crawl and search the web for AI agents via MCP.

    Web ScrapingBrowser AutomationSearch
    51
  • AIsa Web Search & ResearchAOAuth
    one.aisa

    Your agent needs the open web — searched by more than one engine, and read as clean markdown rather than raw HTML. **What you can ask for** • "Search this question with two providers and tell me where they disagree." • "Scrape these 40 URLs into markdown, in one batch." • "Crawl this documentation site and give me every page." • "Do deep research on this topic and cite the sources." • "Find the academic papers behind this claim." **How to use it** Point any MCP client at https://mcp.aisa.one/search/mcp and sign in with OAuth — there is no key to create or paste. 30 tools across several independent providers: Tavily and Exa search, answers, contents and agent runs; Firecrawl scrape, batch scrape, crawl, map and search; Perplexity Sonar, Sonar Pro, reasoning and deep research; Oxylabs AI search and LLM jobs; OpenAI and Anthropic web search; and scholarly search. **Why this rather than the source** Several independent indexes behind one account, because one engine's blind spot is not visible from inside it. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Find the page here, then ask the same agent who links to it or how much traffic it gets — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo-serp/mcp for the Google results page itself, https://mcp.aisa.one/seo-serp-other-engines/mcp for Bing, Baidu and Naver.

    Browser AutomationSearchWeb Scraping
    351

Related MCP Servers

  • evo-scry

    krich11
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP server for internet search via direct Google and DuckDuckGo HTML scraping with AI-powered result normalization and optional summarization, requiring no API keys for search.
    MIT

  • Agent Search

    cedarsaam
    A
    license
    Not graded
    quality
    C
    maintenance
    A self-hosted, MCP-native web-search backend for AI agents that provides meta-search, clean extraction, RAG with citations, and GitHub project selection.
    5
    MIT