by mobb-dev
Provides automatic security vulnerability remediation for code via a command‑line interface, supporting both live scans and analysis of pre‑generated SAST reports to generate fix patches and guide developers to review them.
Bugsy enables developers to quickly identify and automatically fix security vulnerabilities in their source code. It works in two modes: Scan, which runs a SAST scan using Checkmarx or Snyk on a public GitHub/GitLab/ADO repository, and Analyze, which consumes an existing SAST report from supported tools (Checkmarx, CodeQL, Fortify, Snyk).
npx mobbdev <command> [options]
mobbdev scan --repo <repo-url>
– runs a fresh SAST scan and returns automated fixes.mobbdev analyze --scan-file <report.json> --repo <repo-url>
– processes an existing report.API_KEY
environment variable with your Mobb API key.npx mobbdev mcp
.fix_vulnerabilities
tool.bugsy scan
on a repository to instantly get fix suggestions while coding.fix_vulnerabilities
tool, letting the assistant scan local changes and suggest patches.API_KEY
and run npx mobbdev mcp
. Then add the server configuration to your AI client.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.
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.
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
Analyze
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.
You can simply run Bugsy from the command line, using npx:
npx mobbdev
This will show you Bugsy's usage help:
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:
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:
npx mobbdev scan -h
npx mobbdev analyze -h
Bugsy can also be used as an MCP server, allowing AI assistants like Claude to automatically scan and fix vulnerabilities in your code repositories.
API Key: You need a Mobb API key to use the MCP server functionality
API_KEY
environment variable: export API_KEY=your_api_key_here
Local Git Repository: The MCP server analyzes git repositories with uncommitted changes
Run mobb-mcp from command line:
npx mobbdev mcp
Add Mobb MCP to your Cursor MCP client configuration:
API_URL
is only required if you are not using https://app.mobb.ai
{
"mcpServers": {
"mobb-mcp": {
"command": "npx",
"args": ["mobbdev", "mcp"],
"env": {
"API_KEY": "your_mobb_api_key_here",
"API_URL": "optional__your_mobb_api_url_here"
}
}
}
}
Once configured, you can use the MCP server through your AI assistant:
Ask Claude to scan for vulnerabilities:
run a scan with mobb-mcp
or
run fix-vulnerabilities mcp tool
The MCP server will:
fix_vulnerabilities
: Scans the current code changes and returns fixes for potential vulnerabilities
path
(string) - The path to the local git repositoryIf 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:
npx mobbdev analyze --ci --scan-file $SAST_RESULTS_FILENAME --repo $CI_PROJECT_URL --ref $CI_COMMIT_REF_NAME --api-key $MOBB_API_KEY
Install the dependencies and run the tests:
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
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.
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
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "bugsy-mcp": { "command": "npx", "args": [ "mobbdev", "mcp" ], "env": { "API_KEY": "<YOUR_API_KEY>", "API_URL": "optional__your_mobb_api_url_here" } } } }
Discover more MCP servers with similar functionality and use cases
by zed-industries
Provides real-time collaborative editing powered by Rust, enabling developers to edit code instantly across machines with a responsive, GPU-accelerated UI.
by cline
Provides autonomous coding assistance directly in the IDE, enabling file creation, editing, terminal command execution, browser interactions, and tool extension with user approval at each step.
by continuedev
Provides continuous AI assistance across IDEs, terminals, and CI pipelines, offering agents, chat, inline editing, and autocomplete to accelerate software development.
by github
Enables AI agents, assistants, and chatbots to interact with GitHub via natural‑language commands, providing read‑write access to repositories, issues, pull requests, workflows, security data and team activity.
by block
Automates engineering tasks by installing, executing, editing, and testing code using any large language model, providing end‑to‑end project building, debugging, workflow orchestration, and external API interaction.
by RooCodeInc
An autonomous coding agent that lives inside VS Code, capable of generating, refactoring, debugging code, managing files, running terminal commands, controlling a browser, and adapting its behavior through custom modes and instructions.
by lastmile-ai
A lightweight, composable framework for building AI agents using Model Context Protocol and simple workflow patterns.
by firebase
Provides a command‑line interface to manage, test, and deploy Firebase projects, covering hosting, databases, authentication, cloud functions, extensions, and CI/CD workflows.
by gptme
Empowers large language models to act as personal AI assistants directly inside the terminal, providing capabilities such as code execution, file manipulation, web browsing, vision, and interactive tool usage.