MCP Overview

ByteHide is available as an MCP (Model Context Protocol) server, allowing AI coding agents like Claude, Cursor, and VS Code Copilot to scan your code for vulnerabilities, audit dependencies, and detect secrets — all directly from your AI workflow.

What Is MCP

The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources. Instead of copying and pasting code into a security scanner, the AI agent calls ByteHide directly and gets results in real time as part of the conversation.

With the ByteHide MCP integration, your AI assistant becomes a security-aware coding partner that can:

• Scan code for vulnerabilities (SAST) and hardcoded secrets as you write it
• Check dependencies before you install them to catch known CVEs
• Audit manifest files (package.json, requirements.txt, go.mod, etc.) for vulnerable packages
• Review AI configurations for prompt injection risks, credential exposure, and overpermissioning
• List and manage your ByteHide projects directly from the AI conversation

See It in Action

Checking a dependency before installing

Ask your AI agent if a package is safe. ByteHide checks it against known vulnerabilities and tells you whether to upgrade.

Click to expand

The response includes the specific vulnerability found, the affected version, and the exact command to upgrade:

Click to expand

Scanning code for vulnerabilities

Paste or share code with your AI agent and ask if it's safe. ByteHide runs a SAST scan and returns findings with severity, CWE references, and fix recommendations.

Click to expand

The scan returns detailed results including the vulnerability type, affected file, and a clear explanation of the issue:

Click to expand

Claude then explains the vulnerability in context, highlighting the dangerous line and showing how an attacker could exploit it:

Click to expand

Auditing all dependencies at once

In Claude Code (CLI), you can audit your entire package.json in a single request. ByteHide scans all dependencies and returns a prioritized vulnerability report.

Click to expand

The report includes prioritized recommended actions, telling you exactly which packages to upgrade first and the effort involved for each change.

Available Tools by Product

The MCP server exposes tools organized by ByteHide product. Each product section in the documentation covers its specific MCP tools in detail.

Radar

For detailed parameters and usage examples, see Radar MCP Tools.

Supported Languages & Ecosystems

Code Scanning (SAST + Secrets)

General Availability: C, C++, C#, Go, Java, JavaScript, JSX, TypeScript, TSX, Kotlin, PHP, Python, Ruby, Rust, Scala, Swift.

Also supported: Apex, Bash, Dart, Dockerfile, Elixir, HTML, JSON, Lua, OCaml, R, Solidity, Terraform, XML, YAML, and more.

Dependency Scanning (SCA)

How It Works

1. Connect your AI agent to the ByteHide MCP server (one-time setup)
2. Authenticate via OAuth — a browser window opens to log in to your ByteHide account
3. Use it — ask your AI assistant to scan code, check a package, or audit dependencies. The agent calls the right tool automatically

Projects are created automatically in your ByteHide dashboard when you scan for the first time. All findings sync to the cloud panel so you can track them alongside your regular scans.

Next Steps