Skip to main content
Glama
enesjakozh
kouui

DuckDuckGo Web Search MCP Server

by kouui
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Servidor MCP de búsqueda web de DuckDuckGo

Este proyecto proporciona un servidor MCP (Protocolo de contexto de modelo) que le permite buscar en la web utilizando el motor de búsqueda DuckDuckGo y, opcionalmente, obtener y resumir el contenido de las URL encontradas.

Características

  • Búsqueda web: busque en la web utilizando DuckDuckGo.

  • Extracción de resultados: extrae títulos, URL y fragmentos de los resultados de búsqueda.

  • Obtención de contenido (opcional): obtiene el contenido de las URL encontradas en los resultados de búsqueda y lo convierte a formato Markdown mediante la API de Jina.

  • Obtención paralela: obtiene varias URL simultáneamente para un procesamiento más rápido.

  • Manejo de errores: maneja con elegancia los tiempos de espera y otros errores potenciales durante la búsqueda y la obtención.

  • Configurable: le permite establecer el número máximo de resultados de búsqueda que se devolverán.

  • API de Jina : uso de la API de Jina para convertir HTML a Markdown.

  • Compatible con MCP : este servidor está diseñado para usarse con cualquier cliente compatible con MCP.

Related MCP server: DuckDuckGo MCP Server

Uso

  1. Prerrequisitos:

    • gestor de paquetes uvx

  2. Configuración del escritorio de Claude

    • Si está utilizando Claude Desktop, puede agregar el servidor al archivo claude_desktop_config.json .

    {
    "mcpServers": {
        "web-search-duckduckgo": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/kouui/web-search-duckduckgo.git@main",
                "main.py"
            ]
        }
    }
}

    La configuración anterior no funciona, es posible que deba clonar el repositorio en la PC local y usar la siguiente configuración

    {
    "mcpServers": {
        "web-search-duckduckgo": {
            "command": "uv",
            "args": [
                "--directory",
                "/path/to/web-search-duckduckgo",
                "run",
                "main.py"
            ]
        }
    }
}

  3. Herramienta

    • En su cliente MCP (por ejemplo, Claude), ahora puede utilizar las siguientes herramientas:

    • search_and_fetch : busca en la web y recupera el contenido de las URL.

      • query : La cadena de consulta de búsqueda.

      • limit : el número máximo de resultados a devolver (predeterminado: 3, máximo: 10).

    • fetch : obtiene el contenido de una URL específica.

      • url : La URL a buscar.

Licencia

Este proyecto está licenciado bajo la licencia MIT. (Agregue un archivo de licencia si desea especificar una licencia).

Available Tools

2 tools
fetchC
scrape the html content and return the markdown format using jina api.

Args:
    url: The search query string

Returns:
    text : html in markdown format
ParametersJSON Schema
NameRequiredDescriptionDefault
urlYes

TDQS

C2.8/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions using the Jina API and the transformation to markdown format, but doesn't disclose important behavioral traits: rate limits, authentication requirements, error handling, whether this makes external network calls, or what happens with invalid URLs. For a tool that performs web scraping with an external API, this is a significant gap.

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

Conciseness3/5

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

The description is brief but has structural issues. The first sentence is clear, but the 'Args:' and 'Returns:' sections use inconsistent formatting and terminology ('search query string' for a URL parameter). While concise, it could be more effectively structured with clearer separation of concerns.

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

Completeness2/5

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

Given no annotations, no output schema, and a tool that performs web scraping via an external API, the description is incomplete. It doesn't address important contextual aspects: error conditions, rate limits, authentication, what types of URLs are supported, or the structure/limitations of the returned markdown. For a tool with external dependencies and potential complexity, this is inadequate.

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

Parameters3/5

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

The description adds minimal parameter semantics beyond the schema. With 0% schema description coverage, the description states 'url: The search query string' which is somewhat confusing (calling it a 'search query string' when it's clearly a URL parameter). It doesn't explain URL format requirements, validation, or provide examples. The baseline would be lower given the coverage gap, but it does at least identify the parameter's purpose.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'scrape the html content and return the markdown format using jina api.' It specifies the verb (scrape/return), resource (html content), and transformation (to markdown format). However, it doesn't explicitly differentiate from its sibling tool 'search_and_fetch' - we can infer it's a direct fetch while the sibling might search first, but this isn't stated.

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

Usage Guidelines2/5

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

No guidance is provided about when to use this tool versus alternatives. The description doesn't mention the sibling tool 'search_and_fetch' or explain when direct fetching is appropriate versus searching and fetching. There's no context about prerequisites, limitations, or appropriate use cases.

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

search_and_fetchA
Search the web using DuckDuckGo and return results.

Args:
    query: The search query string
    limit: Maximum number of results to return (default: 3, maximum 10)

Returns:
    List of dictionaries containing 
    - title
    - url
    - snippet 
    - summary markdown (empty if not available)
ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
limitNo

TDQS

A4/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden. It discloses the search engine (DuckDuckGo) and return format, but doesn't mention rate limits, authentication needs, error conditions, or whether this is a read-only operation. The behavioral disclosure is adequate but incomplete.

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?

The description is well-structured with clear sections (Args, Returns) and front-loaded purpose. Every sentence earns its place - no redundant information. The formatting with bullet points enhances readability without unnecessary verbosity.

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

Completeness4/5

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

Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description provides good coverage of purpose, parameters, and return format. It could benefit from more behavioral context (like rate limits or error handling) but is largely complete for a search tool.

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?

The description adds significant value beyond the 0% schema coverage by explaining both parameters: 'query' as the search string and 'limit' with its default (3) and maximum (10) values. This compensates well for the lack of schema descriptions, though it doesn't cover all potential edge cases.

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?

The description clearly states the tool's purpose with specific verb ('Search the web using DuckDuckGo') and resource ('return results'). It distinguishes from the sibling 'fetch' tool by specifying it's a search operation rather than a direct fetch operation.

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

Usage Guidelines3/5

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

The description implies usage context (searching the web) but doesn't explicitly state when to use this tool versus the 'fetch' sibling. It provides basic parameter guidance but lacks explicit alternatives or exclusion criteria.

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
    • First observedfetch
    • First observedsearch_and_fetch
Deploy Server
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

TDQS

B3.3/5.0

Scored across 2 tools

Disambiguation4/5

The two tools have distinct primary purposes: 'search_and_fetch' performs web searches and returns results, while 'fetch' scrapes HTML content from a given URL. However, there is some potential for confusion because 'fetch' accepts a 'url' argument but its description mentions 'search query string' (likely a documentation error), which could blur the boundary between searching and fetching.

Naming Consistency4/5

The tool names follow a consistent verb-based pattern ('fetch' and 'search_and_fetch'), with clear action-oriented naming. The minor deviation is that 'search_and_fetch' uses an 'and' conjunction, but overall the naming is readable and predictable.

Tool Count3/5

With only 2 tools, the server feels thin for a web search and scraping domain. While it covers basic search and fetch operations, more tools (e.g., for advanced search filtering, caching, or handling different content types) would provide better scope. It's borderline but not severely lacking.

Completeness3/5

The server covers core web search and content fetching workflows, but there are notable gaps. For example, it lacks tools for managing search history, refining queries, handling pagination, or supporting different output formats beyond markdown. Agents can work around these, but the surface is not fully comprehensive.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • DuckDuckGo MCP Server

    988664li-star
    A
    license
    B
    quality
    D
    maintenance
    Enables web search through DuckDuckGo and webpage content fetching with intelligent text extraction. Features built-in rate limiting and LLM-optimized result formatting for seamless integration with language models.
    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

Appeared in Searches