Skip to main content
Glama
enesjakozh
tatn

MCP Server Fetch Python

by tatn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

mcp-server-fetch-python

웹 콘텐츠를 다양한 형식으로 가져오고 변환하는 MCP 서버입니다. 이 서버는 JavaScript로 렌더링된 콘텐츠 및 미디어 파일 지원을 포함하여 웹 페이지에서 콘텐츠를 추출하는 데 필요한 포괄적인 도구를 제공합니다.

특징

도구

서버는 4가지 전문 도구를 제공합니다.

  • get-raw-text : 브라우저 렌더링 없이 URL에서 직접 원시 텍스트 콘텐츠를 추출합니다.

    • 인수:

      • url : 대상 웹 페이지의 URL(text, JSON, XML, csv, tsv 등)(필수)

    • 구조화된 데이터 형식이나 빠르고 직접적인 액세스가 필요할 때 가장 잘 사용됩니다.

  • get-rendered-html : 헤드리스 브라우저를 사용하여 완전히 렌더링된 HTML 콘텐츠를 가져옵니다.

    • 인수:

      • url : 대상 웹페이지의 URL (필수)

    • JavaScript 렌더링이 필요한 최신 웹 애플리케이션 및 SPA에 필수적입니다.

  • get-markdown : 웹 페이지 콘텐츠를 잘 포맷된 마크다운으로 변환합니다.

    • 인수:

      • url : 대상 웹페이지의 URL (필수)

    • 구조적 요소를 보존하면서 깔끔하고 읽기 쉬운 텍스트 출력을 제공합니다.

  • get-markdown-from-media : 미디어 파일에서 AI 기반 콘텐츠 추출을 수행합니다.

    • 인수:

      • url : 대상 미디어 파일(이미지, 비디오)의 URL(필수)

    • 시각적 콘텐츠 분석을 위해 컴퓨터 비전과 OCR을 활용합니다.

    • 환경 변수에 유효한 OPENAI_API_KEY가 설정되어 있어야 합니다.

    • API 키가 설정되지 않았거나 미디어 파일을 처리하는 데 문제가 있는 경우 오류 메시지가 반환됩니다.

Related MCP server: Fetch MCP

용법

클로드 데스크탑

Claude Desktop과 함께 사용하려면 서버 구성을 추가하세요.

MacOS의 경우: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows의 경우: %APPDATA%/Claude/claude_desktop_config.json

지엑스피1

환경 변수

다음 환경 변수를 구성할 수 있습니다.

  • OPENAI_API_KEY : get-markdown-from-media 도구를 사용하는 데 필요합니다. 이 키는 AI 기반 이미지 분석 및 콘텐츠 추출에 필요합니다.

  • PYTHONIOENCODING : 출력에서 문자 인코딩 문제가 발생하면 "utf-8"로 설정합니다.

  • MODEL_NAME : 사용할 모델 이름을 지정합니다. 기본값은 "gpt-4o"입니다.

"mcpServers": {
  "mcp-server-fetch-python": {
    "command": "uvx",
    "args": [
      "mcp-server-fetch-python"
    ],
    "env": {
        "OPENAI_API_KEY": "sk-****",
        "PYTHONIOENCODING": "utf-8",
        "MODEL_NAME": "gpt-4o",        
    }
  }
}

로컬 설치

또는 서버를 로컬로 설치하고 실행할 수 있습니다.

git clone https://github.com/tatn/mcp-server-fetch-python.git
cd mcp-server-fetch-python
uv sync
uv build

그런 다음 Claude Desktop 구성 파일에 다음 구성을 추가합니다.

"mcpServers": {
  "mcp-server-fetch-python": {
    "command": "uv",
    "args": [
      "--directory",
      "path\\to\\mcp-server-fetch-python",  # Replace with actual path to the cloned repository
      "run",
      "mcp-server-fetch-python"
    ]
  }
}

개발

디버깅

다음 명령을 사용하여 npx를 사용하여 MCP Inspector를 시작할 수 있습니다.

npx @modelcontextprotocol/inspector uvx mcp-server-fetch-python
npx @modelcontextprotocol/inspector uv --directory path\\to\\mcp-server-fetch-python run mcp-server-fetch-python

Available Tools

4 tools
get-markdownA

Converts web page content to well-formatted Markdown, preserving structural elements like tables and definition lists. Recommended as the default tool for web content extraction when a clean, readable text format is needed while maintaining document structure.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL of the target web page (ordinary HTML, etc.).

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It describes the tool's behavior ('preserving structural elements like tables and definition lists') and output format ('well-formatted Markdown'), but lacks details on error handling, rate limits, or authentication needs. It's adequate but has gaps in behavioral disclosure.

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?

Two sentences, zero waste: the first states the purpose and key features, the second provides usage guidance. It's front-loaded with the core functionality and efficiently structured without redundancy.

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 (single parameter, no output schema, no annotations), the description is mostly complete: it covers purpose, usage, and behavioral traits. However, it lacks details on output format specifics or error cases, leaving some gaps in context.

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?

Schema description coverage is 100%, so the schema already documents the 'url' parameter. The description adds context by specifying the type of web page ('ordinary HTML, etc.') and the goal of conversion, but doesn't provide additional syntax or format details beyond what the schema implies. Baseline 3 is appropriate as the schema does the heavy lifting.

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 specific action ('Converts web page content to well-formatted Markdown') and resource ('web page'), and distinguishes it from siblings by mentioning it's 'Recommended as the default tool for web content extraction' and preserves structural elements like tables and definition lists, unlike get-raw-text which likely doesn't preserve structure.

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

Usage Guidelines5/5

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

It explicitly provides when to use ('Recommended as the default tool for web content extraction when a clean, readable text format is needed while maintaining document structure') and implies alternatives (siblings like get-raw-text for less structured extraction or get-rendered-html for HTML output), giving clear context for selection.

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

get-markdown-from-mediaB

Performs AI-powered content extraction from media files (images and videos) and converts the results to Markdown format. Specialized tool for visual content analysis that utilizes computer vision and OCR capabilities to generate descriptive text from media sources.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL of the target web page (images, videos, etc.).

TDQS

B3.4/5.0
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 AI-powered extraction and computer vision/OCR capabilities, which adds some context about the tool's approach. However, it does not disclose critical behavioral traits such as rate limits, authentication needs, error handling, or whether the operation is read-only or has side effects, which is a significant gap for a tool with no annotation coverage.

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

Conciseness4/5

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

The description is appropriately sized with two sentences that are front-loaded with the core purpose. The first sentence clearly states the tool's function, and the second adds specialized context. There is minimal redundancy, though the second sentence could be slightly more concise.

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

Completeness3/5

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

Given the tool's complexity (AI-powered media analysis) and lack of annotations or output schema, the description is moderately complete. It explains the tool's purpose and specialization but omits details on output format, error conditions, and behavioral constraints. This leaves gaps for an agent to understand full usage, though the core functionality is adequately described.

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 input schema has 100% description coverage, with the 'url' parameter documented as 'URL of the target web page (images, videos, etc.)'. The description does not add meaning beyond this, as it does not elaborate on parameter usage, format, or constraints. The baseline score of 3 is appropriate since the schema adequately covers the single parameter.

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: 'Performs AI-powered content extraction from media files (images and videos) and converts the results to Markdown format.' It specifies the action (extraction and conversion), resources (media files), and distinguishes from siblings by focusing on visual content analysis with computer vision/OCR rather than text or HTML processing.

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 ('Specialized tool for visual content analysis') but does not explicitly state when to use this tool versus alternatives like 'get-markdown' or 'get-raw-text'. It suggests media files as input but lacks guidance on exclusions or prerequisites, leaving some ambiguity for the agent.

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

get-raw-textA

Extracts raw text content directly from URLs without browser rendering. Ideal for structured data formats like JSON, XML, CSV, TSV, or plain text files. Best used when fast, direct access to the source content is needed without processing dynamic elements.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL of the target web page (text, JSON, XML, csv, tsv, etc.).

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits such as operating 'without browser rendering' and handling 'structured data formats', but lacks details on error handling, rate limits, authentication needs, or output format specifics, which are important for a tool interacting with external URLs.

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 appropriately sized and front-loaded, with three concise sentences that each add value: the first states the core purpose, the second specifies ideal use cases, and the third provides usage context. There is no wasted text.

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

Completeness3/5

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

Given the tool's complexity (interacting with external URLs) and lack of annotations and output schema, the description is somewhat complete but has gaps. It covers purpose and usage well, but omits behavioral details like error responses, performance characteristics, or output structure, which are important for an agent to use it effectively.

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 input schema has 100% description coverage, so the schema already documents the 'url' parameter adequately. The description adds marginal value by implying the types of URLs supported ('text, JSON, XML, csv, tsv, etc.'), but does not provide additional syntax or format details beyond what the schema states.

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 a specific verb ('Extracts') and resource ('raw text content directly from URLs'), and distinguishes it from siblings by emphasizing 'without browser rendering' and 'structured data formats', contrasting with tools like get-rendered-html that likely involve rendering.

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?

The description provides clear context on when to use this tool ('Ideal for structured data formats', 'Best used when fast, direct access to the source content is needed without processing dynamic elements'), but does not explicitly mention when not to use it or name specific alternatives among siblings like get-markdown.

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

get-rendered-htmlB

Fetches fully rendered HTML content using a headless browser, including JavaScript-generated content. Essential for modern web applications, single-page applications (SPAs), or any content that requires client-side rendering to be complete.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL of the target web page (ordinary HTML including JavaScript, etc.).

TDQS

B3.4/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that the tool uses a headless browser and fetches JavaScript-generated content, which adds some context beyond the basic 'fetch' operation. However, it lacks details on performance characteristics (e.g., speed, timeouts), error handling, or output format, leaving significant gaps in understanding how the tool behaves in practice.

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

Conciseness4/5

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

The description is appropriately sized with two sentences that are front-loaded with key information (purpose and method). Every sentence contributes meaningfully, though the second sentence could be slightly more concise by combining the examples of use cases.

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

Completeness3/5

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

Given the tool's moderate complexity (involving headless browsers and dynamic content) and the absence of both annotations and an output schema, the description is incomplete. It explains what the tool does and when to use it but lacks details on behavioral traits (e.g., performance, errors) and output format, which are critical for effective use. However, it covers the core purpose adequately for a basic understanding.

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 schema description coverage is 100%, with the single parameter 'url' clearly documented in the schema. The description doesn't add any parameter-specific information beyond what's in the schema (e.g., no examples, constraints, or format details), so it meets the baseline for high schema coverage without compensating with extra value.

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 with specific verbs ('fetches fully rendered HTML content') and resources ('using a headless browser'), and distinguishes it from likely siblings by emphasizing JavaScript-generated content and client-side rendering. However, it doesn't explicitly name or differentiate from the actual sibling tools (get-markdown, get-markdown-from-media, get-raw-text).

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?

The description provides clear context for when to use this tool ('modern web applications, single-page applications (SPAs), or any content that requires client-side rendering'), which implicitly suggests alternatives for static content. It doesn't explicitly state when not to use it or name specific alternative tools, but the context is sufficiently detailed to guide usage decisions.

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. 4 tool updatesv1.0.0
    • First observedget-markdown
    • First observedget-markdown-from-media
    • First observedget-raw-text
    • First observedget-rendered-html
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

A4/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: get-markdown for general web content conversion, get-markdown-from-media for AI-powered media extraction, get-raw-text for direct access to structured data, and get-rendered-html for JavaScript-rendered content. The descriptions explicitly differentiate use cases, preventing misselection.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with 'get-' prefix and descriptive suffixes (e.g., get-markdown, get-raw-text). This uniformity makes the tool set predictable and easy to navigate, with no deviations in naming style.

Tool Count5/5

With 4 tools, the server is well-scoped for web content extraction, covering key scenarios like general conversion, media analysis, raw data access, and rendered content. Each tool earns its place without redundancy, and the count is appropriate for the domain.

Completeness5/5

The tool set provides complete coverage for web content extraction, addressing diverse needs from structured data to dynamic pages and media files. There are no obvious gaps; agents can handle various extraction workflows without dead ends.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches