Introduction to the MCP server

Last updated: Oct 28, 2026


What is MCP?

MCP (Model Context Protocol) is a communication standard. With this standard, AI assistants (for example, Claude, ChatGPT, and Gemini) can connect to external tools and services.

What is the Fluid Attacks MCP server?

The MCP server of Fluid Attacks is a software component. With it, AI systems can connect to the Fluid Attacks platform and work with it through the Internet. Thus, you can send natural language queries to the Fluid Attacks platform directly from your AI tool. These are examples of what you can do with it:

  • Monitor your security posture: Get real-time information about the vulnerabilities in your applications
  • Run security scans: Run automated security tests on your code
  • Investigate vulnerabilities: Examine security problems in detail to understand them better
  • Get remediation guidance: Get step-by-step instructions to fix security problems
  • Access documentation: Search the security documentation of Fluid Attacks
  • Manage your projects: See and organize your security testing projects

Key terms

  • Group: A security testing project (for example, "MobileApp" or "WebPortal")
  • Weakness: A type of vulnerability (for example, SQL injection)
  • Vulnerability: A security problem at one location in your code
  • Root: What you test (code repository, website, or IP address)
  • SAST: Analysis of source code to find security problems
  • SCA: Analysis of dependencies to find known vulnerabilities
  • Forces: Automated security checks in your CI/CD pipeline
  • Treatment: What you do with a vulnerability (for example, fix it or accept it)

Key features

  • Read-only access: Reads data from the Fluid Attacks platform and does not change it
  • Multi-language support: Answers in the language of the user
  • Conversation memory: Keeps the context from one interaction to the next
  • Streaming responses: Sends answers in real time
  • Observability: Uses Logfire for traces and Datadog for error monitoring
  • Security: Uses token authentication and validates the user

Key capabilities of our MCP

You can ask the AI Agent of Fluid Attacks or configure the MCP server of Fluid Attacks to do these actions. Each capability shows example prompts that you can use:

  • Analytics: See security trends and metrics
    • "Show risk over time for the organization ORGANIZATION_NAME."
    • "Show me today's security summary for the organization ORGANIZATION_NAME."
    • "Show remediation metrics for this sprint for the group GROUP_NAME."
  • Vulnerabilities: Find and monitor security problems
    • "List all XSS-related vulnerabilities in the group GROUP_NAME."
    • "List all untreated vulnerabilities by priority for the group GROUP_NAME."
    • "Generate a vulnerability report by severity for the group GROUP_NAME."
    • "Get details for vulnerability VULNERABILITY_UUID/NAME in the group GROUP_NAME."
  • Projects: Manage security testing projects
    • "What is the configuration of each group in the organization ORGANIZATION_NAME?"
    • "Show me all information for the group GROUP_NAME."
  • Assets: See the applications and code that Fluid Attacks tests
    • "List Git repositories of the group GROUP_NAME that are being scanned for security issues."
  • Scanning: Run automated security tests
    • "Scan my dependencies."
    • "Run a complete security scan."
    • "Scan my packages for vulnerabilities."
  • DevSecOps: Monitor pipeline security checks
    • "Show the latest scan results for the group GROUP_NAME."
    • "Show latest CI/CD security scan results in the group GROUP_NAME."
  • Knowledge: Search the security documentation
    • "How to fix SQLi reported in the group GROUP_NAME?"
    • "Explain [vulnerability type] reported in the group GROUP_NAME."

Further reading

On this page