Skip to main content
Glama
deenesjakoruzh
cyberchitta

Scrapling Fetch MCP

by cyberchitta
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

scrapling-fetch-mcp

License PyPI version

Helps AI assistants fetch content from bot-protected websites. Uses Scrapling (patchright + curl-cffi) to bypass anti-automation measures, returning clean HTML or Markdown.

Optimized for low-volume retrieval of documentation and reference materials. Not designed for high-volume scraping or data harvesting.

Requirements: Python 3.10+, uv

Claude Code Skill

The easiest way to use this is as a Claude Code skill. Once installed, Claude will automatically fetch bot-protected URLs when you ask — no manual commands needed.

Install into your project (recommended — only loads in this project's context):

git clone --depth=1 https://github.com/cyberchitta/scrapling-fetch-mcp /tmp/scrapling-fetch-mcp
cp -r /tmp/scrapling-fetch-mcp/skills/s-fetch .claude/skills/
rm -rf /tmp/scrapling-fetch-mcp

Or install for all projects (loads into context everywhere):

git clone --depth=1 https://github.com/cyberchitta/scrapling-fetch-mcp /tmp/scrapling-fetch-mcp
cp -r /tmp/scrapling-fetch-mcp/skills/s-fetch ~/.claude/skills/
rm -rf /tmp/scrapling-fetch-mcp

The first time you invoke /s-fetch, Claude will read skills/s-fetch/references/install.md and run the one-time setup (installs the tool and downloads browser binaries). After that, just ask naturally:

"Fetch the docs at https://example.com/api"
"Find all mentions of 'authentication' on that page"
"Get me the installation instructions from their homepage"

Related MCP server: mult-fetch-mcp-server

Claude Desktop (MCP Server)

If the /s-fetch skill has already installed the tool, skip to the config below.

Otherwise install first:

uv tool install git+https://github.com/cyberchitta/scrapling-fetch-mcp
uvx --from git+https://github.com/cyberchitta/scrapling-fetch-mcp scrapling install

Note: Browser installation downloads hundreds of MB and must complete before first use. If the server times out initially, wait a few minutes and try again.

Add this to your Claude Desktop MCP settings and restart:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "scrapling-fetch": {
      "command": "uvx",
      "args": ["scrapling-fetch-mcp"]
    }
  }
}

How It Works

Two tools, used automatically by Claude:

  • Page fetching — retrieves complete pages with pagination support

  • Pattern extraction — finds content matching a regex

Three protection levels, escalated automatically:

  • basic — fast (1-2s), works for most sites

  • stealth — moderate (3-8s), headless Chromium

  • max-stealth — thorough (10s+), full browser fingerprint

Limitations

  • Text content only (documentation, articles, references)

  • Not for high-volume scraping or sites requiring authentication

  • Performance varies by site complexity and protection level

License

Apache 2.0

Available Tools

2 tools
s_fetch_pageA

Fetches a complete web page with pagination support. Retrieves content from websites with bot-detection avoidance. For best performance, start with 'basic' mode (fastest), then only escalate to 'stealth' or 'max-stealth' modes if basic mode fails. Content is returned as 'METADATA: {json}\n\n[content]' where metadata includes length information and truncation status.

Args:
    url: URL to fetch
    mode: Fetching mode (basic, stealth, or max-stealth)
    format: Output format (html or markdown)
    max_length: Maximum number of characters to return.
    start_index: On return output starting at this character index, useful if a previous fetch was truncated and more content is required.
ParametersJSON Schema
NameRequiredDescriptionDefault
urlYes
modeNobasic
formatNomarkdown
max_lengthNo
start_indexNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.2/5.0
Behavior4/5

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 effectively describes key behaviors: bot-detection avoidance, performance characteristics of modes, pagination support, output format structure ('METADATA: {json}\n\n[content]'), and truncation handling. It doesn't mention rate limits, authentication needs, or error conditions, but covers most essential operational aspects.

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 well-structured and appropriately sized. It starts with the core purpose, adds usage guidelines, describes output format, then details parameters in a clear 'Args:' section. Every sentence adds value, though the parameter explanations could be slightly more concise.

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 5 parameters with 0% schema coverage and no annotations, the description does an excellent job covering the tool's functionality. It explains purpose, usage, behavior, parameters, and output structure. The presence of an output schema means return values don't need explanation. The main gap is lack of error handling or edge case information.

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 description coverage is 0%, so the description must compensate. It provides meaningful context for all 5 parameters: explains what 'url' is for, defines 'mode' options and their purpose, specifies 'format' choices, clarifies 'max_length' as character limit, and describes 'start_index' for handling truncation. This adds substantial value beyond the bare schema, though some details like default values are only in the schema.

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: 'Fetches a complete web page with pagination support. Retrieves content from websites with bot-detection avoidance.' This specifies the verb ('fetches'), resource ('web page'), and key capabilities ('pagination support', 'bot-detection avoidance'). It doesn't explicitly differentiate from sibling tool 's_fetch_pattern', but the purpose is well-defined.

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?

The description provides explicit guidance on when to use different modes: 'For best performance, start with 'basic' mode (fastest), then only escalate to 'stealth' or 'max-stealth' modes if basic mode fails.' This gives clear operational advice and distinguishes between modes based on performance and fallback scenarios.

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

s_fetch_patternA

Extracts content matching regex patterns from web pages. Retrieves specific content from websites with bot-detection avoidance. For best performance, start with 'basic' mode (fastest), then only escalate to 'stealth' or 'max-stealth' modes if basic mode fails. Returns matched content as 'METADATA: {json}\n\n[content]' where metadata includes match statistics and truncation information. Each matched content chunk is delimited with '॥๛॥' and prefixed with '[Position: start-end]' indicating its byte position in the original document, allowing targeted follow-up requests with s-fetch-page using specific start_index values.

Args:
    url: URL to fetch
    search_pattern: Regular expression pattern to search for in the content
    mode: Fetching mode (basic, stealth, or max-stealth)
    format: Output format (html or markdown)
    max_length: Maximum number of characters to return.
    context_chars: Number of characters to include before and after each match
ParametersJSON Schema
NameRequiredDescriptionDefault
urlYes
search_patternYes
modeNobasic
formatNomarkdown
max_lengthNo
context_charsNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.7/5.0
Behavior4/5

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 effectively describes key behaviors: bot-detection avoidance capabilities, performance characteristics of different modes, output format details including metadata structure and content delimiters, and how results enable follow-up requests with s_fetch_page. However, it doesn't mention error handling, rate limits, or authentication requirements.

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 well-structured with purpose first, usage guidance second, output format third, and parameters last. It's appropriately detailed for a complex tool but could be slightly more concise in the output format explanation. Every sentence serves a clear purpose.

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 the tool's complexity (6 parameters, regex matching, multiple modes), no annotations, but with an output schema present, the description provides excellent contextual completeness. It covers purpose, usage guidelines, behavioral details, parameter semantics, and output format - everything needed for effective tool use without needing to explain return values (handled by output schema).

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

Parameters5/5

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

With 0% schema description coverage, the description must fully compensate, which it does excellently. The Args section provides clear semantic explanations for all 6 parameters, including practical guidance for 'mode' selection and explaining what 'context_chars' and 'max_length' control. This adds substantial value beyond the bare 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?

The description clearly states the tool's purpose: 'Extracts content matching regex patterns from web pages.' It specifies the verb ('extracts'), resource ('content'), and method ('regex patterns'), distinguishing it from the sibling tool s_fetch_page which presumably fetches full pages rather than pattern-matched content.

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?

The description provides explicit usage guidance: 'For best performance, start with 'basic' mode (fastest), then only escalate to 'stealth' or 'max-stealth' modes if basic mode fails.' This gives clear when-to-use instructions for mode selection and implicitly suggests basic mode as the default approach.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0
Disambiguation5/5

The two tools have clearly distinct purposes: s_fetch_page retrieves entire web pages with pagination support, while s_fetch_pattern extracts specific content matching regex patterns. Their descriptions explicitly differentiate them, with no overlap in functionality that would cause confusion.

Naming Consistency5/5

Both tools follow a consistent 's_fetch_' prefix pattern with descriptive suffixes ('page' and 'pattern'), maintaining perfect naming consistency. The snake_case convention is applied uniformly across both tool names.

Tool Count3/5

With only 2 tools, the server feels somewhat thin for a web scraping domain that typically requires more operations like navigation, form handling, or session management. While the tools are well-designed, the limited count may restrict agent capabilities for complex scraping tasks.

Completeness4/5

The tools cover the core web scraping operations of fetching pages and extracting patterns with bot-detection avoidance. However, there are notable gaps for a complete scraping workflow, such as no tools for navigating between pages, handling authentication, managing sessions, or interacting with dynamic content beyond basic fetching.

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cyberchitta/scrapling-fetch-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server