MCP server · Security

rqwstr MCP server

Lets your AI send and test web requests at a low level, for security checks and fuzzing.

rqwstr is a helper that connects your AI to a toolkit for testing how websites and web services respond to requests. It is made for security work, like checking how a site handles odd or repeated traffic. It is most useful if you already do web security testing and want your AI to drive the tools for you.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to a service. This one connects your AI to rqwstr, an HTTP security testing toolkit, so the AI can send requests, run fuzzing, and gather results when you ask. You stay in the chat, and the helper does the technical work behind the scenes.

What this MCP server does

You ask your AI to send a request or run a test against a web address. The AI passes that to rqwstr, which sends the raw request over HTTP/1.1 or HTTP/2 with fine control over how it is built. rqwstr collects the responses, filters them, and stores the results. Then your AI shows you the findings in the chat, such as which inputs caused unusual replies. It can also run repeated or racing requests and watch for out-of-band signals.

Flow diagram: you ask your AI “Send a test request to my site and show what comes back”, on your own computer the rqwstr MCP server works with rqwstr, and you get back findings shown in your chat.

Click to zoom

What you can do with it

Send a single HTTP/1.1 or HTTP/2 request and read the response
Run intruder-style fuzzing with different payload patterns
Race many requests at once to check for timing issues
Chain several requests together in one workflow
Watch for out-of-band callbacks from a target
Import traffic from Burp or HAR files and export as curl or Python
Save, search, and profile findings across a hunt

Try asking your AI

“Send a GET request to https://example.com and show me the headers”
“Run an intruder attack on the id parameter with these values”
“Race 20 requests to this login endpoint and tell me if any differ”
“Import this HAR file and list the unique endpoints”

What it gives back to you

You get answers in the chat: response headers and bodies, lists of requests and results, and summaries of what stood out. rqwstr also stores per-hunt state, so you can search past findings and pull them back later. For attacks, it reports which payloads or timings produced different responses. Exports come back as text you can copy, like curl commands or Python code.

Before you start

What you need

A license key from rqwstr.com (a free tier covers the core tools, Pro unlocks the heavier attack tools)
The rqwstr binary for your platform, or the Claude Desktop .mcpb bundle
An MCP client, such as the Claude desktop app

Good to know

This tool sends real requests to web addresses you choose, so only point it at systems you are allowed to test, and remember it can change or delete data on those systems.

Install it with your AI

Add rqwstr MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check rqwstr MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.