Skip to main content
Glama
Sign In
deenesjakoruzh
Heventure Search MCP

Heventure Search MCP

by HughesCuit
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

中文 | English

PyPI version Python License: MIT Downloads heventure-search-mcp MCP server

🔍 MCP Web Search Server

Free forever. No API key required. A web search MCP server that works out of the box with Claude Desktop, Cursor, and any MCP-compatible AI tool.

pip install heventure-search-mcp

✨ Why?

Most MCP search servers require you to sign up for API keys (Bing, Google, SerpAPI...). This one works immediately — zero configuration, zero cost, zero sign-ups.

Feature

This Server

Others

No API key needed

✅

❌

DuckDuckGo (free)

✅

varies

Bing (free)

✅

❌

Google (free)

✅

❌

Optional SerpAPI/Tavily

✅

✅

Async + caching

✅

varies

Install in 10 seconds

✅

varies

Related MCP server: Web Search MCP Server

🚀 Quick Start

Option 1: Claude Desktop / Cursor

Add to your MCP config:

{
  "mcpServers": {
    "web-search": {
      "command": "uvx",
      "args": ["heventure-search-mcp"]
    }
  }
}

Option 2: Command Line

pip install heventure-search-mcp
heventure-search-mcp

Option 3: Docker

docker run -p 8080:8080 heventure-search-mcp

🔧 Available Tools

web_search

Search the web with multiple engines simultaneously.

Parameter

Type

Default

Description

query

string

required

Search query

max_results

int

10

Number of results (1-20)

search_engine

string

"both"

duckduckgo, bing, google, or both

get_page_content

Extract readable text from any webpage.

Parameter

Type

Default

Description

url

string

required

Page URL to fetch

🔑 Optional: Enhanced Search

The free engines work great for most use cases. For higher quality results, you can optionally add paid API keys:

# SerpAPI — 100 free searches/month
export SERPAPI_KEY="your_key"

# Tavily — 1,000 free searches/month  
export TAVILY_API_KEY="your_key"

🏗️ Architecture

  • Engines: DuckDuckGo, Bing, Google, SerpAPI, Tavily

  • Caching: LRU cache with 300s TTL (100 entries max)

  • Protocol: MCP (Model Context Protocol)

  • Runtime: Python 3.10+ with asyncio

🤝 Contributing

Issues and Pull Requests are welcome! See CONTRIBUTING.md for guidelines.

📄 License

MIT License — use it however you want.

Available Tools

2 tools
get_webpage_contentA

Extract readable text content from a specific webpage URL. Use this tool after web_search when you need the full text of a page found in search results. The tool strips scripts, styles, and navigation elements, returning only the meaningful text content. Output is truncated to 2000 characters to stay within context limits. Returns an empty string if the page cannot be fetched or parsed.

Inputs: url (required).

web_searchA

Search the web using multiple search engines. Use this tool when you need to find current information, articles, or references from the internet. Supports DuckDuckGo, Google, and Bing as free engines, with optional SerpAPI (requires SERPAPI_KEY env var) and Tavily (requires TAVILY_API_KEY env var) for higher-quality, more stable results. By default ('both'), queries DuckDuckGo and Bing concurrently and merges results, providing good coverage without any API keys. Each result includes title, URL, and description snippet. Rate limiting and caching are applied automatically.

Inputs: query (required), max_results, search_engine.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    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

    TDQS

    A4.6/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one searches the web, the other retrieves content from a specific URL. There is no overlap in functionality, and their descriptions make the differentiation explicit.

    Naming Consistency5/5

    Both tool names follow a consistent verb_noun pattern: 'web_search' and 'get_webpage_content'. The naming is clear, predictable, and uses underscores consistently.

    Tool Count4/5

    With only two tools, the server is minimal but well-scoped for a search-and-retrieve workflow. While more tools could be added (e.g., for advanced filtering or caching), the current count fits the server's stated purpose without being too thin.

    Completeness5/5

    The tool set covers the basic search workflow: find pages via web_search, then extract content via get_webpage_content. There are no obvious gaps for the intended use case of retrieving text from web pages.

    Maintenance

    ActivityInactive
    ResponsivenessLimited data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • MCP Fetch

      matiasngf
      A
      license
      A
      quality
      D
      maintenance
      Enables browser automation using Puppeteer through the MCP interface. Allows launching browsers, creating pages, and executing arbitrary JavaScript for web scraping, testing, and debugging tasks.
      5
      132 npm
      2
      MIT

    • Web Search MCP Server

      vishalkg
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables web search across multiple search engines (DuckDuckGo, Bing, Startpage) with parallel execution and result deduplication. Also provides web page content extraction capabilities.
      2
      MIT

    • Web Search MCP

      pranavms13
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables web searching through Google, DuckDuckGo, and Bing using a headless Chrome browser, returning structured results with titles, URLs, and snippets. Also supports fetching and extracting text content from any webpage.
      16
      MIT