Skip to main content
Glama
deenesjakoruzh
HughesCuit

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesThe full URL of the webpage to extract content from (e.g., 'https://example.com/article'). Must be a valid HTTP or HTTPS URL. Supports most standard web pages; JavaScript-rendered content may not be fully captured.

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, but description discloses stripping of non-content elements, truncation to 2000 characters, and empty string on failure. Provides adequate behavioral insight.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five concise sentences front-load the purpose. No redundant information; every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given low complexity and no output schema, description fully covers return behavior, truncation, and failure modes. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single URL parameter; description adds context about JavaScript-rendered content limitations, which enhances understanding beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool extracts readable text from a URL, specifying it strips scripts/styles/navigation. Distinguishes from sibling 'web_search' by indicating usage after search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly describes when to use: after web_search when full text of a search result page is needed. Does not explicitly state when not to use, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 2 tool updates
    • Changedget_webpage_content1 field changed
      • changedInput schema / properties / url / description
        Previous value: -"要获取内容的网页URL"New value: +"The full URL of the webpage to extract content from (e.g., 'https://example.com/article'). Must be a valid HTTP or HTTPS URL. Supports most standard web pages; JavaScript-rendered content may not be fully captured."
    • Changedweb_search3 fields changed
      • changedInput schema / properties / max_results / description
        Previous value: -"最大结果数量"New value: +"Maximum number of results to return per search engine. Default is 10. Range: 1-20. Higher values increase latency. Actual count may be lower if the engine returns fewer matches."
      • changedInput schema / properties / query / description
        Previous value: -"搜索查询字符串"New value: +"The search query string. Use specific keywords for best results. Supports natural language queries (e.g., 'best practices for Python async') as well as keyword-style queries (e.g., 'Python async await tutorial')."
      • changedInput schema / properties / search_engine / description
        Previous value: -"搜索引擎选择：duckduckgo / bing / google / serpapi / tavily / both"New value: +"Which search engine(s) to query. Options: 'duckduckgo' (free, no API key needed), 'bing' (free), 'google' (free), 'serpapi' (requires SERPAPI_KEY), 'tavily' (requires TAVILY_API_KEY), 'both' (default — uses DuckDuckGo + Bing concurrently for broader coverage without API keys). Use 'serpapi' or 'tavily' when you need higher-quality results and have the API key configured."
  2. 2 tool updatesv0.1.0
    • First observedget_webpage_content
    • First observedweb_search
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
ResponsivenessResponsive

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Fetch

    matiasngf
    A
    license
    A
    quality
    F
    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
    149 npm
    2
    MIT

  • Web Search MCP Server

    vishalkg
    F
    license
    Not graded
    quality
    C
    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
    -

  • 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.
    13
    MIT