Skip to main content
Glama
Sign In
mcp-fetch-ya

mcp-fetch-ya

by xiaocang
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

mcp-fetch-ya

A Model Context Protocol (MCP) server for fetching web content and converting HTML to markdown.

Features

  • HTML to Markdown - Automatically extracts main content using Readability and converts to clean markdown

  • robots.txt Compliance - Respects robots.txt by default (configurable)

  • Custom User-Agent - Configurable User-Agent string

  • Proxy Support - Optional HTTP/HTTPS proxy configuration

Related MCP server: escalator

Installation

npm install -g mcp-fetch-ya@latest

Or use directly with npx:

npx mcp-fetch-ya@latest

Usage with Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": ["mcp-fetch-ya@latest"]
    }
  }
}

With options

{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": [
        "mcp-fetch-ya@latest",
        "--ignore-robots-txt",
        "--user-agent", "MyBot/1.0"
      ]
    }
  }
}

With proxy

{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": [
        "mcp-fetch-ya@latest",
        "--proxy-url", "http://proxy.example.com:8080"
      ]
    }
  }
}

Tool: fetch_ya

If the built-in web fetch tool fails, you can retry with this MCP tool as a fallback. Fetches a URL and returns the content. HTML pages are converted to markdown for easier reading.

Parameters

Parameter

Type

Required

Default

Description

url

string

Yes

-

The URL to fetch

raw

boolean

No

false

Return raw content without markdown conversion

CLI Options

Option

Description

--user-agent <agent>

Custom User-Agent string

--proxy-url <url>

Proxy URL for requests

--ignore-robots-txt

Ignore robots.txt restrictions

License

MIT

Available Tools

1 tool
fetch_yaFetch URLA

If the built-in web fetch tool fails, you can retry with this MCP tool as a fallback. Fetches a URL and returns the content. HTML pages are converted to markdown for easier reading.

Inputs: url (required), raw.

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

    A4.4/5.0

    Scored across 1 tool

    Disambiguation5/5

    Only one tool exists, so no possible confusion between tools. The purpose is clear: it fetches a URL as a fallback.

    Naming Consistency5/5

    With a single tool, there is no inconsistency in naming. 'fetch_ya' follows a simple verb-based convention and is recognizable.

    Tool Count3/5

    One tool is extremely minimal and may feel thin, but it exactly matches the narrow fallback-fetch scope. It sits in the borderline range for tool count.

    Completeness5/5

    For its stated purpose of acting as a fallback URL fetcher, the tool fully covers the operation: fetch, convert to markdown, and return content. No obvious gaps exist for this narrow domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • fetch

      RMRanjit
      A
      license
      Not graded
      quality
      D
      maintenance
      Fetches web pages and converts them to markdown for LLM consumption, supporting chunked reading and raw content extraction.
      MIT

    • escalator

      ruslanstarikov
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables fetching web pages as clean Markdown with automatic escalation from direct requests to residential proxies and headless browsers to overcome blocks, plus built-in politeness handling like robots.txt and rate limiting.
      -

    • read-website-fast

      fcoigvozst
      F
      license
      Not graded
      quality
      A
      maintenance
      Fetches webpages locally, extracts readable content, and converts it to clean Markdown with preserved links, optional multi-page crawling, caching, and robots.txt support for token-efficient use by AI agents and LLM pipelines.
      -

    • read-website-fast

      DieterErdogan61
      A
      license
      Not graded
      quality
      A
      maintenance
      Fetches webpages and converts them into clean, token-efficient Markdown, optionally crawling multiple linked pages while respecting robots.txt and caching results for AI agents and LLM pipelines.
      MIT