MCP server installation

Last updated: May 22, 2026


This guide explains how to install the Fluid Attacks MCP server in Claude Desktop, Claude Code, Cursor, VS Code, and Windsurf. Pick your AI assistant in the tabs below to see the matching configuration steps and a usage example. Besides, you can learn how to integrate Fluid Attacks security scanners into your software development lifecycle (SDLC) using AI agents.

Prerequisites

  • To use the Fluid Attacks MCP Server, you need an AI assistant that supports MCP, such as Claude (via Cursor, Claude Desktop, VS Code, etc.).
  • All MCP tools require authentication. Claude Desktop, Claude Code, VS Code, and Windsurf handle this through an OAuth flow with the Fluid Attacks platform. For Cursor, you need to provide a Fluid Attacks API token.
  • Do you want to run security scans? If so, you need to have Docker installed. Also, it is recommended to configure an AGENTS.md file in the project root directory.

Configure your MCP client

Select your AI assistant in the tab list below. Each tab contains the configuration steps and a usage example specific to that client.

Install the runtime environment

Follow these steps to install Node.js, which is required for using Fluid Attacks' MCP server. If you already have Node.js v22 installed, simply skip to the next section according to your needs.

  1. It is recommended that you install Node Version Manager (nvm), as it allows you to have different versions of Node.js and switch between them according to your current needs. To install nvm, open your terminal and run the following:
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.2/install.sh | bash

Close and reopen your terminal or run the following command to load nvm into your current session:

\. "$HOME/.nvm/nvm.sh"
  1. Install the Node.js version 22 with the following command (v18 or higher is required):
nvm install 22

Set up in Claude

Set up Fluid Attacks' MCP server in Claude following these instructions:

  1. Go to the menu bar, click on Claude and then Settings.
Open Claude settings
  1. Switch to the Developer tab and click the Edit Config button.
Find Edit Config in Claude
  1. You are presented with a folder that contains the file claude_desktop_config.json. Open this file with a text editor.

  2. Paste the following into the configuration file:

    {
      "mcpServers": {
        "fluidattacks-mcp": {
          "command": "npx",
          "args": [
            "--cache",
            "/tmp/fluidattacks-mcp",
            "mcp-remote",
            "https://app.fluidattacks.com/mcp/messages/"
          ]
        }
      }
    }
  3. Save the file and close both it and Claude.

  4. Reopen Claude Desktop. On startup, mcp-remote opens your default browser and redirects you to the Fluid Attacks sign-in page, where you grant Claude Desktop access to the information stored in your Fluid Attacks platform account. After you authorize the request, the browser returns to Claude Desktop and the fluidattacks-mcp server appears as connected.

You can now start chatting with the platform.

Configuration

Use Fluid Attacks' remote MCP server in Claude Code, following these instructions:

  1. From your project root, add the server using the Claude Code CLI:

    claude mcp add --transport http fluidattacks-mcp https://app.fluidattacks.com/mcp/messages/

    To make the server available across all your projects, use the --scope user flag instead:

    claude mcp add --scope user --transport http fluidattacks-mcp https://app.fluidattacks.com/mcp/messages/
  2. Alternatively, create a .mcp.json file in your project root and declare the server:

    {
      "mcpServers": {
        "fluidattacks-mcp": {
          "type": "http",
          "url": "https://app.fluidattacks.com/mcp/messages/"
        }
      }
    }
  3. Start an interactive Claude Code session and run the /mcp command. Select fluidattacks-mcp from the list and choose the Authenticate option to start the OAuth flow in your browser. After authorizing, the server status should change to connected.

  4. You can now use the Fluid Attacks MCP server in Claude Code.

Configuration

Use Fluid Attacks' remote MCP server in Cursor, following these instructions:

  1. Go to Cursor's MCP Directory and search for the Fluid Attacks server.
  2. Click on the Add to Cursor button:
Fluid Attacks server on Cursor MCP Directory
  1. Once you see this warning message in your browser, click the Open Link or Open Cursor.app button:
Open Cursor link
  1. Add the Fluid Attacks API token in the configuration field. Authentication is required to use any of the MCP tools.
Installing Fluid Attacks MCP server on Cursor
  1. Click on the Install button.

  2. Verify that the server is active before using it to request vulnerability scans or reports containing information about your groups.

    fluidattacks-mcp is enabled for Cursor
  3. You can now use the Fluid Attacks MCP server in Cursor.

    Use Fluid Attacks MCP on Cursor

Configuration

Use Fluid Attacks' remote MCP server in VS Code, following these instructions:

  1. Open VS Code's search bar (cmd + P) and type "> MCP: Open User Configuration".

  2. Select the option shown in the image below:

    Start MCP configuration on VS Code
  3. Add Fluid Attacks' MCP Server in the servers section of the configuration:

    {
      "servers": {
        "fluidattacks-mcp": {
          "type": "http",
          "url": "https://app.fluidattacks.com/mcp/messages/"
        }
      }
    }
  4. Save the file.

  5. As shown in the image below, click on Start.

    Start using MCP on VS Code
  6. Authenticate

    • click on allow
    Allow auth flow to start
    • Click on open
    Allow auth flow to start
    • Select the account you use to access the Fluid Attacks platform and accept
    Allow auth flow to start
    • Click on the link or accept opening the app
    Allow auth flow to start
  7. Once again on VS Code, the number of tools and prompts should be shown.

  8. To enable the AI Agent to use our MCP tools, click on the Configure tools option.

    Enable the AI Agent on VS Code
  9. On the opened window, search for "fluidattacks-mcp", enable the tools you want to use, and click the OK button:

    Selecting fluidattacks-mcp on VS Code
  10. You can now use the Fluid Attacks MCP server in VS Code.

    Using Fluid Attacks MCP on VS Code

Configuration

Use Fluid Attacks' remote MCP server in Windsurf, following these instructions:

  1. Open the ~/.codeium/windsurf/mcp_config.json file in your home directory. If the file does not exist, create it.

  2. Add Fluid Attacks' MCP server under the mcpServers section:

    {
      "mcpServers": {
        "fluidattacks-mcp": {
          "serverUrl": "https://app.fluidattacks.com/mcp/messages/"
        }
      }
    }

    Alternatively, you can manage the server from the UI: open the Cascade panel, click the MCPs icon in the top-right menu, then open Windsurf Settings > Cascade > MCP Servers and add the server entry above.

  3. Save the file and refresh the MCP servers list in Cascade. Windsurf opens your default browser to start the OAuth flow. After you authorize the request, the browser returns to Windsurf and the fluidattacks-mcp server appears as connected.

  4. You can now use the Fluid Attacks MCP server in Windsurf.

Usage example

Once the Fluid Attacks MCP server is connected to your AI assistant, you can request vulnerability information or security scans using natural language. The same prompts work across Claude Desktop, Claude Code, Cursor, VS Code, and Windsurf.

For example, to generate a vulnerability report for a specific group in a specific organization, use the following prompt:

Using Fluid Attacks' API, please generate a one-page report of the vulnerabilities found in the Narrabri group of the Imamura organization.

Or, to query the highest severity vulnerability in a specific file:

From the Fluid Attacks API, what is the highest severity (CVSS) vulnerability in the basketitems.ts file of the Clickable group within the Imamura organization?

Your AI assistant asks for permission before running each tool exposed by the MCP server (for example, fetch_group_vulnerabilities, which retrieves vulnerability information such as status and severity). After approval, it returns the requested information and can help you remediate findings directly in your codebase.

Sandbox configuration

If you need to skip the interactive OAuth flow (for example, when running the MCP server in a sandbox or headless environment, invoking it from CI, or scripting integration tests), you can authenticate by passing a Fluid Attacks API token in the Authorization header.

Add the headers field to the server entry in your client configuration and set Authorization to Bearer <YOUR_API_TOKEN>.

The example below uses the .mcp.json format shared by Claude Code and VS Code:

{
  "mcpServers": {
    "fluidattacks-mcp": {
      "type": "http",
      "url": "https://app.fluidattacks.com/mcp/messages/",
      "headers": {
        "Authorization": "Bearer <YOUR_API_TOKEN>"
      }
    }
  }
}

For Windsurf, use the serverUrl field together with headers in ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "fluidattacks-mcp": {
      "serverUrl": "https://app.fluidattacks.com/mcp/messages/",
      "headers": {
        "Authorization": "Bearer <YOUR_API_TOKEN>"
      }
    }
  }
}

Security considerations

  • Data sensitivity: Be cautious when sharing vulnerability data.

Integrate our scanners into your SDLC using AI

When using AI-powered development tools, such as Cursor, GitHub Copilot, or similar AI coding assistants, you can configure them to automatically execute Fluid Attacks security scanners at appropriate points in your SDLC. This integration helps you ensure that security vulnerabilities are detected and addressed early.

Before integrating our security scanners with AI agents, ensure that you have Docker installed in your system, that Fluid Attacks' MCP server is configured in your AI development environment, and that you have write access to your project directory for configuration files and scan results.

Add AGENTS.md to your project using Fluid Attacks' MCP server

On the chat of your AI agent, start by typing /fluidattacks-mcp/ and then select the following command:

/fluidattacks-mcp/config_agents_md

Add AGENTS.md to your project manually

1. Create the AGENTS.md file

Add an AGENTS.md file to your project root directory. This file contains instructions that AI agents will follow to determine when and how to execute security scanners.

The AGENTS.md file should be placed at the root of your project:

your-project/
├── AGENTS.md     # Add this file
├── src/
├── package.json
└── ...

2. Add the AGENTS.md content

# Project Instructions

## Execute Security Scanners

### Execute SCA Scanner When:

- New dependencies are added to the project
- Dependencies are updated to new versions
- Lock files are modified (e.g.,`package-lock.json`, `uv.lock`)
- User explicitly requests a dependency security scan
- Setting up a new project for the first time
- Before deploying to production
- Before pushing to the repository

### Execute SAST Scanner When:

- Source code changes are made to application files
- New features or modules are added
- Security-sensitive code is modified (authentication, authorization)
- User explicitly requests a code security scan
- Before committing significant code changes
- During code reviews
- Before deploying to production
- Before pushing to the repository

### Execute Both Scanners When:

- A complete security audit is needed
- Major project updates involving both code and dependencies
- Pre-deployment security check
- User requests a full security scan

## Prerequisites

- Docker installed on the system
- No Dockerfile creation needed - only download the Docker images
- Write access to the project directory for configuration files and results

## Fluid Attacks Scanner

### Purpose

Scan the project for vulnerabilities using the Fluid Attacks MCP tools.

### Step-by-Step Instructions

#### 1. Use Fluid Attacks MCP tools to configure and run the scanner

#### 2. Add the output file to .gitignore

#### 3. Remediate vulnerabilities

- Review the output file
- If there are vulnerabilities, remediate them

## Best Practices for Agents

### 1. Configuration File Management

- Always verify the correct paths for include/exclude before running
- Adjust configuration based on project structure
- Use `.gitignore` as a reference for exclude patterns
- Store configuration files in the project root and add them to .gitignore

## When to Run What

| Scenario                      | Scanner | Priority |
| ----------------------------- | ------- | -------- |
| New dependency added          | SCA     | High     |
| Code changes in auth/security | SAST    | Critical |
| Weekly security audit         | Both    | Medium   |
| Pre-deployment check          | Both    | Critical |
| Dependency version update     | SCA     | High     |
| New feature development       | SAST    | Medium   |
| Third-party library added     | SCA     | High     |
| API endpoint changes          | SAST    | High     |

## Integration with Development Workflow

- On Code Changes: Run SAST if source files modified
- On Dependency Changes: Run SCA if dependency files modified
- On User Request: Run appropriate scanner(s)
- Help with remediation: Always create/update security reports
- Re-scan: After fixes to verify remediation

Troubleshooting

If the scanners are not being executed automatically:

  • Verify that AGENTS.md exists in your project root
  • Ensure the Fluid Attacks MCP server is properly configured
  • Check that Docker is installed and running
  • Verify that the AI agent has read access to AGENTS.md
  • You can ask the AI agent to execute the scanners: "Run fluid attacks scanners."

If the scanners report false positives:

  • Review the specific vulnerability details
  • Adjust scanner configuration if needed
  • Document acceptable exceptions in your project documentation
  • Consider reaching out to Fluid Attacks support for clarification

On this page