Skip to main content
Glama
evanlouie

Fetch MCP Server

by evanlouie

Fetch MCP Server (Browser Impersonation Fork)

A Model Context Protocol server that provides web content fetching capabilities with browser impersonation. This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.

This is a fork of the original MCP fetch server that utilizes curl_cffi for browser impersonation, allowing it to bypass basic bot detection and access websites that might block standard HTTP requests.

Key Features

  • Browser Impersonation: Uses curl_cffi to mimic real browser requests, helping bypass basic bot detection

  • Content Extraction: Converts HTML to markdown for easier LLM consumption

  • Chunked Reading: Support for reading large webpages in chunks using start_index

  • Browser Headers: Uses realistic Chrome browser headers for better compatibility

CAUTION

This server can access local/internal IP addresses and may represent a security risk. Exercise caution when using this MCP server to ensure this does not expose any sensitive data.

The fetch tool will truncate the response, but by using the start_index argument, you can specify where to start the content extraction. This lets models read a webpage in chunks, until they find the information they need.

Available Tools

  • fetch - Fetches a URL from the internet and extracts its contents as markdown.

    • url (string, required): URL to fetch

    • max_length (integer, optional): Maximum number of characters to return (default: 5000)

    • start_index (integer, optional): Start content from this character index (default: 0)

    • raw (boolean, optional): Get raw content without markdown conversion (default: false)

Prompts

  • fetch

    • Fetch a URL and extract its contents as markdown

    • Arguments:

      • url (string, required): URL to fetch

Related MCP server: Fetch MCP Server

Installation

Using uv

When using uv no specific installation is needed. We will use uvx to directly run from the git repository:

uvx --from git+https://github.com/evanlouie/mcp-fetch.git mcp-server-fetch

Configuration

Configure for Claude.app

Add to your Claude settings:

{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/evanlouie/mcp-fetch.git",
        "mcp-server-fetch"
      ],
      "env": {
        "PYTHONWARNINGS": "ignore",
        "npm_config_audit": "false",
        "npm_config_fund": "false"
      }
    }
  }
}

Configure for VS Code

For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).

Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.

Note that the mcp key is needed when using the mcp.json file.

{
  "mcp": {
    "servers": {
      "fetch": {
        "command": "uvx",
        "args": [
          "--from",
          "git+https://github.com/evanlouie/mcp-fetch.git",
          "mcp-server-fetch"
        ],
        "env": {
          "PYTHONWARNINGS": "ignore",
          "npm_config_audit": "false",
          "npm_config_fund": "false"
        }
      }
    }
  }
}

Customization - Proxy

The server can be configured to use a proxy by using the --proxy-url argument.

Troubleshooting

JSON Parsing Errors

If you encounter JSON parsing errors like:

Unexpected token 'o', "found 0 vul"... is not valid JSON

This is caused by security scanners or audit tools outputting non-JSON content to stdout during package installation. The MCP protocol requires pure JSON-RPC messages on stdout, but vulnerability scanners (like npm audit) can contaminate this output.

Solution: The environment variables in the configuration examples above suppress these outputs:

  • PYTHONWARNINGS=ignore - Suppresses Python warning messages

  • npm_config_audit=false - Disables npm security audits

  • npm_config_fund=false - Disables npm funding messages

Alternative Solution: If you continue to experience issues, you can create a wrapper script:

#!/bin/bash
uvx --from git+https://github.com/evanlouie/mcp-fetch.git mcp-server-fetch 2>/dev/null

Then use the wrapper script path as your command instead of uvx.

Debugging

You can use the MCP inspector to debug the server. For uvx installations:

npx @modelcontextprotocol/inspector uvx --from git+https://github.com/evanlouie/mcp-fetch.git mcp-server-fetch

Or if you've installed the package in a specific directory or are developing on it:

cd path/to/mcp-fetch
npx @modelcontextprotocol/inspector uv run src/mcp_fetch

Contributing

We encourage contributions to help expand and improve mcp-fetch. Whether you want to add new tools, enhance existing functionality, or improve documentation, your input is valuable.

This project is a fork of the original MCP fetch server. For the original implementation and other MCP servers, see: https://github.com/modelcontextprotocol/servers

Pull requests are welcome! Feel free to contribute new ideas, bug fixes, or enhancements to make mcp-fetch even more powerful and useful.

Acknowledgments

This project is based on the original MCP fetch server from the Model Context Protocol team. The browser impersonation capabilities are powered by curl_cffi.

License

mcp-fetch is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Available Tools

1 tool
fetchA

Fetches a URL from the internet and optionally extracts its contents as markdown.

This tool uses Chrome browser impersonation to access websites that might otherwise block automated requests, making it more reliable for fetching content from various sources.

ParametersJSON Schema
NameRequiredDescriptionDefault
rawNoGet the actual HTML content of the requested page, without simplification.
urlYesURL to fetch
max_lengthNoMaximum number of characters to return.
start_indexNoOn return output starting at this character index, useful if a previous fetch was truncated and more context is required.

TDQS

A4.1/5.0
Behavior3/5

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

The description discloses the use of Chrome impersonation and markdown extraction, adding value beyond the schema. However, with no annotations, it does not address potential issues like rate limits, errors, or return format details.

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 two sentences—concise and front-loaded. Every sentence provides useful information without unnecessary detail.

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 no output schema, the description does not specify the return format or structure beyond markdown/HTML. It is adequate for a simple tool but lacks completeness for advanced usage.

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 input schema already describes all 4 parameters, and the tool description adds context about markdown extraction and the role of the 'raw' parameter, enhancing understanding beyond the schema alone.

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 fetches a URL from the internet and extracts contents as markdown, which is specific and easy to understand. No sibling tools require differentiation.

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 explains that the tool uses Chrome browser impersonation to handle blocked sites, providing context for when to use it. However, it lacks explicit guidance on when not to use it or alternatives.

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. 1 tool updatev0.7.0
    • First observedfetch

TDQS

A4.2/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity. The single tool 'fetch' has a clearly defined purpose of fetching URLs.

Naming Consistency5/5

Only one tool exists, so naming is trivially consistent. The name 'fetch' is a clear verb describing its action.

Tool Count3/5

A single tool for a very narrow domain (fetching URLs) is borderline. While it covers the core functionality, the server feels minimal and could benefit from additional tools for common variations.

Completeness4/5

For its stated purpose of fetching a URL and optionally extracting markdown, the tool is complete. No essential features are missing, though advanced options like authentication or batch fetching are absent.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    D
    maintenance
    Enables LLMs to retrieve and process web content by fetching URLs and converting HTML to markdown format. Supports chunked reading of large pages and can access both public websites and local networks.
    1
    MIT
  • A
    license
    C
    quality
    D
    maintenance
    Enables LLMs to retrieve and process web content by fetching URLs and converting HTML to markdown, with support for chunked reading and customizable user-agents.
    1
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    Enables fetching and converting web content to markdown with built-in prompt injection safeguards that detect and block malicious content attempting to manipulate the LLM.
    1
    2
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables LLMs to fetch and process web content by converting HTML into markdown for easier consumption. It supports chunked reading via pagination and provides configuration options for robots.txt compliance and proxy usage.
    1
    MIT