mcp-rquest MCP Server

What does “mcp-rquest” MCP Server do?

The mcp-rquest MCP Server is a Model Context Protocol (MCP) server designed to provide advanced, realistic browser-like HTTP request capabilities for AI assistants, including Claude and other large language models. Built atop the rquest engine, it enables models to interact with websites using accurate TLS, JA3/JA4, and HTTP/2 browser fingerprints, which helps bypass common anti-bot measures and simulate human browsing. Additionally, the server supports conversion of PDF and HTML documents to Markdown, facilitating easier ingestion and processing of web and document content by LLMs. It also features secure response storage, token-aware handling of large responses, and supports a variety of authentication and request customization options, making it a powerful tool for enhancing AI-driven development workflows involving web and document data.

List of Prompts

No specific prompt templates are mentioned in the repository.

List of Resources

No explicit resources are documented in the available files or README.

List of Tools

• http_get: Perform GET HTTP requests with customizable parameters.
• http_post: Submit data using POST requests to web resources.
• http_put: Update resources via PUT requests.
• http_delete: Remove resources from servers with DELETE requests.
• http_patch: Apply partial updates to resources.
• http_head: Retrieve only the headers from a web resource.
• http_options: Get supported HTTP methods for a resource.
• http_trace: Execute diagnostic tracing of HTTP requests.
• get_stored_response: Retrieve large, previously stored HTTP responses, with optional line range selection.

Use Cases of this MCP Server

• Web Scraping & Browsing: Safely scrape data from websites, including those with anti-bot protections, by emulating realistic browser fingerprints.
• Automated API Testing: Use the complete suite of HTTP methods to test REST APIs, including authentication and custom payloads.
• Document Conversion for LLMs: Convert both HTML and PDF documents into Markdown, making ingestion and processing by LLMs more efficient.
• Data Extraction from Secure Sites: Access and extract content from sites requiring authentication, cookies, or custom headers.
• Handling Large Web Responses: Store and retrieve large responses for incremental or token-limited LLM processing.

How to set it up

Windsurf

1. Ensure prerequisites like Node.js and Python are installed.
2. Open your Windsurf configuration file (e.g., windsurf.config.json).
3. Add the mcp-rquest MCP server to the mcpServers section:

   {
     "mcpServers": {
       "mcp-rquest": {
         "command": "mcp-rquest",
         "args": ["server"]
       }
     }
   }
   

4. Save changes and restart Windsurf.
5. Verify that mcp-rquest appears in your available MCP servers.

Claude

1. Open your Claude configuration file.
2. Insert the following JSON snippet into the MCP servers section:

   {
     "mcpServers": {
       "mcp-rquest": {
         "command": "mcp-rquest",
         "args": ["server"]
       }
     }
   }
   

3. Save changes and restart Claude.
4. Confirm that the server is running and accessible.

Cursor

1. Install prerequisites (Node.js, Python).
2. Edit Cursor’s configuration file.
3. Add:

   {
     "mcpServers": {
       "mcp-rquest": {
         "command": "mcp-rquest",
         "args": ["server"]
       }
     }
   }
   

4. Restart Cursor.
5. Test MCP server connectivity.

Cline

1. Make sure dependencies are installed.
2. Update the configuration file for Cline.
3. Insert:

   {
     "mcpServers": {
       "mcp-rquest": {
         "command": "mcp-rquest",
         "args": ["server"]
       }
     }
   }
   

4. Save and restart Cline.
5. Ensure mcp-rquest MCP server is operational.

Securing API Keys

To securely provide API keys, use environment variables and reference them in your configuration:

{
  "mcpServers": {
    "mcp-rquest": {
      "command": "mcp-rquest",
      "args": ["server"],
      "env": {
        "MY_API_KEY": "${MY_API_KEY_ENV_VAR}"
      },
      "inputs": {
        "api_key": "${MY_API_KEY_ENV_VAR}"
      }
    }
  }
}

Replace MY_API_KEY_ENV_VAR with your actual environment variable name holding the API key.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcp-rquest": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change "mcp-rquest" to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the tables above, mcp-rquest is a focused and robust HTTP request MCP server with excellent tool coverage (all HTTP verbs, document conversion, large response handling), good documentation, and practical setup examples. However, it lacks documented prompt templates, explicit resources, and information about sampling or roots support. Overall, it’s a practical, well-scoped utility for AI devs, but not a full ecosystem server.

MCP Score

Overall Rating: 6/10
A technically solid, well-documented MCP server for HTTP requests and document conversion, but missing higher-level MCP features like prompt templates, resource exposure, and sampling/roots support.