Bugsy

Bugsy

Automatic security vulnerability remediation for code using SAST and MCP integration.

60
Stars
13
Forks
60
Watchers
1
Issues
Bugsy provides a command-line interface for automatic remediation of security vulnerabilities in codebases. It integrates with popular SAST tools such as Checkmarx, Snyk, CodeQL, and Fortify to identify issues and generate fixes. Bugsy supports both direct scanning and analysis of pre-generated SAST reports, and also operates as a Model Context Protocol (MCP) server for AI assistant integrations. The tool enables developers to streamline the vulnerability fixing process and improve code security efficiently.

Key Features

Automatic vulnerability scanning using SAST tools
Generates code fixes for detected security issues
Supports both direct scanning and analysis of SAST reports
Integration with Checkmarx, Snyk, CodeQL, and Fortify
Command-line interface for ease of use
Operates as a Model Context Protocol (MCP) server
Redirects users to fix report pages for review
Handles public GitHub repositories and limited private repo analysis
Supports local git repositories with uncommitted changes
Mobb platform integration for API key usage

Use Cases

Automated remediation of security vulnerabilities in codebases
Integrating security fixes into developer workflows
Scanning open source repositories for vulnerabilities and fixes
Analyzing SAST scan results to generate fixes
Using AI assistants to perform vulnerability remediation via MCP server
Securing code in continuous integration pipelines
Improving security compliance for open-source and enterprise projects
Facilitating security reviews for code contributions
Assisting developers in quickly identifying and patching vulnerabilities
Enhancing team productivity by automating repetitive security tasks

README

Bugsy

Bugsy is a command-line interface (CLI) tool that provides automatic security vulnerability remediation for your code. It is the community edition version of Mobb, the first vendor-agnostic automated security vulnerability remediation tool. Bugsy is designed to help developers quickly identify and fix security vulnerabilities in their code.

What is Mobb?

Mobb is the first vendor-agnostic automatic security vulnerability remediation tool. It ingests SAST results from Checkmarx, CodeQL (GitHub Advanced Security), OpenText Fortify, and Snyk and produces code fixes for developers to review and commit to their code.

What does Bugsy do?

Bugsy has two modes - Scan (no SAST report needed) & Analyze (the user needs to provide a pre-generated SAST report from one of the supported SAST tools).

Scan

  • Uses Checkmarx or Snyk CLI tools to run a SAST scan on a given open-source GitHub/GitLab/ADO repo
  • Analyzes the vulnerability report to identify issues that can be remediated automatically
  • Produces the code fixes and redirects the user to the fix report page on the Mobb platform

Analyze

  • Analyzes the a Checkmarx/CodeQL/Fortify/Snyk vulnerability report to identify issues that can be remediated automatically
  • Produces the code fixes and redirects the user to the fix report page on the Mobb platform

Disclaimer

This is a community edition version that only analyzes public GitHub repositories. Analyzing private repositories is allowed for a limited amount of time. Bugsy does not detect any vulnerabilities in your code, it uses findings detected by the SAST tools mentioned above.

Usage

Command Line Interface

You can simply run Bugsy from the command line, using npx:

shell
npx mobbdev

This will show you Bugsy's usage help:

shell
Bugsy - Trusted, Automatic Vulnerability Fixer 🕵️‍♂️

Usage:
mobbdev <command> [options]


Commands:
  mobbdev scan     Scan your code for vulnerabilities, get automated fixes right away.
  mobbdev analyze  Provide a vulnerability report and relevant code repository, get automated fixes right away.

Options:
  -h, --help  Show help                                                                                        [boolean]

Examples:
  mobbdev scan -r https://github.com/WebGoat/WebGoat  Scan an existing repository

Made with ❤️ by Mobb

To run a new SAST scan on a repo and get fixes, run the Bugsy Scan command. Example:

shell
npx mobbdev scan --repo https://github.com/mobb-dev/simple-vulnerable-java-project

To get fixes for a pre-generated SAST report, run the Bugsy Analyze command. Example: npx mobbdev analyze --scan-file sast_results.json --repo https://github.com/mobb-dev/simple-vulnerable-java-project

Bugsy will automatically generate a fix for each supported vulnerability identified in the results, and refer the developer to review and commit the fixes to their code.

To see all the options Bugsy allows, use the Scan or Analyze commands with the -h option:

shell
npx mobbdev scan -h
npx mobbdev analyze -h

Model Context Protocol (MCP) Server

Bugsy can also be used as an MCP server, allowing AI assistants like Claude to automatically scan and fix vulnerabilities in your code repositories.

Prerequisites

  1. API Key: You need a Mobb API key to use the MCP server functionality

    • Sign up at mobb.ai to get your API key
    • Set the API_KEY environment variable: export API_KEY=your_api_key_here
  2. Local Git Repository: The MCP server analyzes git repositories with uncommitted changes

    • Make sure your code is in a local git repository
    • Have some modified, added, or staged files to analyze

Installation

Run mobb-mcp from command line:

shell
npx mobbdev mcp

Configuration

Add Mobb MCP to your Cursor MCP client configuration: API_URL is only required if you are not using https://app.mobb.ai

json
{
  "mcpServers": {
    "mobb-mcp": {
      "command": "npx",
      "args": ["mobbdev", "mcp"],
      "env": {
        "API_KEY": "your_mobb_api_key_here",
        "API_URL": "optional__your_mobb_api_url_here",
        "MVS_AUTO_FIX": "true"
      }
    }
  }
}

Environment Variables:

  • API_KEY: Your Mobb API key (required)
  • API_URL: Custom Mobb API URL (optional, defaults to https://app.mobb.ai)
  • MVS_AUTO_FIX: Override auto-fix setting - set to "true" or "false" to force enable/disable automatic fix application regardless of user's database setting (optional)

Usage

Once configured, you can use the MCP server through your AI assistant:

  1. Ask Claude to scan for vulnerabilities:

    run a scan with mobb-mcp
    

    or

    run fix-vulnerabilities mcp tool
    
  2. The MCP server will:

    • Validate the repository path
    • Check for git changes (modified, added, or staged files)
    • Upload the changed files for analysis
    • Generate automated fixes for detected vulnerabilities
    • Return detailed fix recommendations

Available MCP Tools

  • fix_vulnerabilities: Scans the current code changes and returns fixes for potential vulnerabilities
    • Parameter: path (string) - The path to the local git repository
    • Returns: Detailed vulnerability fixes with code patches and explanations

Example MCP Workflow

  1. Make changes to your code
  2. Stage or modify files in git
  3. Ask your AI assistant: "Can you check my code for security vulnerabilities?"
  4. The assistant will use the MCP server to analyze your changes
  5. Receive detailed fix recommendations with code patches

Troubleshooting

  • "API_KEY environment variable is not set": Make sure you've set your Mobb API key
  • "Path is not a valid git repository": Ensure you're pointing to a valid git repository
  • "No changed files found": Make sure you have modified, added, or staged files in your repository

Using Bugsy as part of a CI/CD pipeline

If you utilize SAST scans as part of the CI/CD pipeline, Bugsy can be easiy added and provide immediate fix for every issue detected. Here is a simple example of a command line that will run Bugsy in your pipeline:

shell
npx mobbdev analyze --ci --scan-file $SAST_RESULTS_FILENAME --repo $CI_PROJECT_URL --ref $CI_COMMIT_REF_NAME --api-key $MOBB_API_KEY

Contribution

Install the dependencies and run the tests:

shell
pnpm install

# or use npm run build:dev to watch for changes
pnpm run build

# or use npm test:watch to watch for changes
pnpm run test

Debugging

If you're using VSCode, you can use the launch.json file to debug the code. Run the CLI tests configuration to continuously run and debug the tests.

Getting support

If you need support using Bugsy or just want to share your thoughts and learn more, you are more than welcome to join our discord server

Star History

Star History Chart

Repository Owner

mobb-dev
mobb-dev

Organization

Repository Details

Language TypeScript
Default Branch main
Size 4,337 KB
Contributors 2
License MIT License
MCP Verified Nov 12, 2025

Programming Languages

TypeScript
97.48%
JavaScript
2.15%
Java
0.22%
Shell
0.15%
Go
0.01%

Tags

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • mcp-security-audit

    mcp-security-audit

    MCP server for automated npm package security auditing.

    mcp-security-audit is an MCP (Model Context Protocol) server designed to audit npm package dependencies for security vulnerabilities. It supports real-time vulnerability scanning, integrates directly with remote npm registries, and generates detailed reports with severity, CVSS scores, and CVE information. Compatible with npm, pnpm, and yarn, it also provides automatic fix recommendations and supports standardized MCP integration for tools like Cursor and Cline.

    • 46
    • MCP
    • qianniuspace/mcp-security-audit
  • RAD Security MCP Server

    RAD Security MCP Server

    AI-powered security insights for Kubernetes and cloud environments via the Model Context Protocol.

    RAD Security MCP Server is an implementation of the Model Context Protocol designed to deliver AI-powered security insights and operations for Kubernetes and cloud platforms. It serves as an MCP server for RAD Security, providing a range of toolkits for container, cluster, identity, audit, and threat management. The server is easily configurable via environment variables, allowing for flexible toolkit activation and authentication options. Multiple deployment options are supported, including Node.js, Docker, and integration with development environments like Cursor IDE and Claude Desktop.

    • 5
    • MCP
    • rad-security/mcp-server
  • Semgrep MCP Server

    Semgrep MCP Server

    A Model Context Protocol server powered by Semgrep for seamless code analysis integration.

    Semgrep MCP Server implements the Model Context Protocol (MCP) to enable efficient and standardized communication for code analysis tasks. It facilitates integration with platforms like LM Studio, Cursor, and Visual Studio Code, providing both Docker and Python (PyPI) deployment options. The tool is now maintained in the main Semgrep repository with continued updates, enhancing compatibility and support across developer tools.

    • 611
    • MCP
    • semgrep/mcp
  • GitHub MCP Server

    GitHub MCP Server

    Connect AI tools directly to GitHub for repository, issue, and workflow management via natural language.

    GitHub MCP Server enables AI tools such as agents, assistants, and chatbots to interact natively with the GitHub platform. It allows these tools to access repositories, analyze code, manage issues and pull requests, and automate workflows using the Model Context Protocol (MCP). The server supports integration with multiple hosts, including VS Code and other popular IDEs, and can operate both remotely and locally. Built for developers seeking to enhance AI-powered development workflows through seamless GitHub context access.

    • 24,418
    • MCP
    • github/github-mcp-server
  • CVE-Search MCP Server

    CVE-Search MCP Server

    MCP server for querying and managing CVE-Search vulnerability data.

    CVE-Search MCP Server implements the Model Context Protocol to provide structured access to the CVE-Search API. It enables querying vendors, products, and vulnerabilities, as well as retrieving detailed information for specific CVEs. The server facilitates model context integration via MCP client tools, supporting seamless interactions for vulnerability data management.

    • 67
    • MCP
    • roadwy/cve-search_mcp
  • CipherTrust Manager MCP Server

    CipherTrust Manager MCP Server

    Enables AI assistants to access CipherTrust Manager securely via the Model Context Protocol.

    CipherTrust Manager MCP Server provides an implementation of the Model Context Protocol (MCP), offering AI assistants such as Claude and Cursor a unified interface to interact with CipherTrust Manager resources. Communication is facilitated through JSON-RPC over stdin/stdout, enabling key management, CTE client management, user management, and connection management functionalities. The tool is configurable via environment variables and integrates with existing CipherTrust Manager instances using the ksctl CLI for secure resource access.

    • 7
    • MCP
    • sanyambassi/ciphertrust-manager-mcp-server
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results