| 42crunch-api-security-testing | 42Crunch integrates with Claude Code to automatically audit OpenAPI specifications, identify OWASP-aligned vulnerabilities like BOLA/BFLA, and apply AI-driven fixes within a continuous security validation cycle. | Security | 42Crunch |
| amd-skills | An AMD plugin bundling verified Agent Skills: routes image/audio processing to local AI on Ryzen AI, deploys LLMs via vLLM on AMD Instinct GPUs, boosts inference throughput using Hyperloom, and analyzes GPU kernel and PyTorch trace performance. | Development | AMD |
| browser-use | Enables Claude to control a real browser—local Chrome or a cloud-based instance—for web tasks like browsing, scraping, form filling, site testing, screenshot capture, and workflow automation. | Automation | Browser Use |
| chrome-devtools-mcp | This tool lets coding agents control and inspect a live Chrome browser, capturing performance traces, network requests, console logs with stack traces, and automating actions via Puppeteer. | Development | — |
| claude-security | Performs in-depth code vulnerability scanning within Claude Code sessions at adjustable effort levels, verifying findings via code-based tallying and generating agent-panel-checked patches for optional application. | Security | Anthropic |
| code-modernization | This tool guides legacy software modernization: running /modernize produces an assessment, interactive map, extracted business rules, and an approvable plan, followed by upgrading, rewriting, or rebuilding code with verified behavioral equivalence, security improvements, and reporting. | Development | Anthropic |
| code-review | This tool automates pull request code reviews by deploying multiple specialized agents that assign confidence scores to findings, reducing false positive results. | Productivity | Anthropic |
| code-simplifier | This tool refactors recently changed code to improve clarity, consistency, and maintainability without altering its original functionality. | Productivity | Anthropic |
| coderabbit | CodeRabbit is an AI-powered code review tool combining specialized architecture with 40+ static analyzers to detect bugs, vulnerabilities, and logic errors, using AST-based context analysis and project guidelines, offering actionable fixes at no cost. | Productivity | — |
| codspeed | CodSpeed is a performance testing toolkit offering benchmarking data, flamegraphs, and comparisons; its MCP server supplies Claude detailed profiling context to identify bottlenecks and independently refine performance. | Development | CodSpeed |
| datahub-skills | A DataHub-focused toolkit supporting connector design, pull request review, catalog search, metadata enhancement, lineage tracking, data quality checks, and connection configuration tasks. | Database | DataHub |
| deepeval | Provides capabilities for integrating DeepEval into AI applications, covering evaluation setup, tracing, dataset management, Confident AI reporting, and cycles of iterative refinement. | Development | Confident AI |
| feature-dev | This tool coordinates specialized agents to explore codebases, design architecture, and review quality throughout the software feature development process. | Development | Anthropic |
| fiftyone | A computer vision tool for building datasets and models, offering visualization, analysis, duplicate detection, inference, evaluation, and custom plugin development. | — | — |
| github | A GitHub MCP server enabling repository management—creating issues, handling pull requests, reviewing code, and searching repos via GitHub's API within Claude Code. | Productivity | — |
| greptile | An AI-powered code review integration for GitHub and GitLab, accessible within Claude Code. It lets users view and resolve Greptile's pull request comments, trigger reviews on active branches, and search organizational knowledge and coding pattern data. | Development | Greptile |
| mattpocock-skills | A collection of practical agent skills by Matt Pocock covering software engineering practices like requirement clarification, spec/ticket workflows, test-driven development, code review, and domain modeling, designed for ready-to-use application rather than improvised coding. | Development | Matt Pocock |
| mergify | A terminal-based skill set for the Mergify CLI, enabling management of merge queues, stacked pull requests, Test Insights (including flaky test detection and quarantine), merge protections, and Mergify configuration. | Development | Mergify |
| mlflow | A skillset for using MLflow to instrument, trace, evaluate, and iteratively refine AI agents, supporting a complete workflow from monitoring through validation. | Monitoring | MLflow Team |
| nightvision | Provides skills for configuring scan targets/authentication/scope, triaging scan results, extracting OpenAPI specs from source code, and integrating scanning into CI/CD pipelines; portable across agent tools like Claude Code, Codex, and Cursor. | — | — |
| pagerduty | Analyzes code changes by comparing them to historical incident data, generating PagerDuty-based risk scores to flag deployment risks before shipping. | Monitoring | — |
| playwright | This MCP server from Microsoft enables browser automation, letting Claude navigate web pages, capture screenshots, complete forms, and run automated testing tasks. | Testing | — |
| postman | An agent-oriented Postman integration enabling initialization of a repository's Postman configuration, mocking unbuilt APIs, executing collection and governance tests in CI pipelines, monitoring live endpoints, deploying and troubleshooting Flows, and publishing generated documentation. | Development | — |
| pr-review-toolkit | A suite of automated agents that perform thorough pull request reviews, covering comment quality, test coverage, error handling, type design, overall code quality, and simplification opportunities. | Productivity | Anthropic |
| pyright-lsp | Pyright is a Python language server that provides static type checking and enhances code intelligence features like autocompletion and navigation. | Development | Anthropic |
| qodo | Qodo integrates codebase intelligence, coding standards enforcement, and code review capabilities directly into a coding agent, helping ensure consistent, high-quality code development within that agent's workflow. | Development | Qodo |
| qodo-standards | Qodo offers configurable workflows for discovering optional coding rules and managing organizational standards, helping teams locate applicable guidelines and administer compliance practices within their development processes. | Development | Qodo |
| qt-development-skills | A skill set for Qt software engineering tasks, covering reviewing Qt C++/QML code, writing QML code, and producing documentation for Qt C++/QML codebases. | Development | Qt Group |
| security-guidance | This tool checks Claude-generated code for security issues, combining pattern-based edit warnings, LLM diff review, and commit analysis to detect injection, XSS, SSRF, hardcoded secrets, and other vulnerabilities. | Security | Anthropic |
| semgrep | Semgrep detects security vulnerabilities as code is written, helping guide Claude toward producing secure code from the outset. | Security | — |
| sentry | Sentry integration for retrieving error reports and stack traces, searching issues by fingerprint, enabling developers to debug production errors from within their development environment. | Monitoring | — |
| serena | An MCP server that uses language server protocol integration to analyze code semantically, offering intelligent code comprehension, refactoring recommendations, and navigation across a codebase. | Development | — |
| sonarqube | Integrates SonarQube into AI coding agents, automatically checking code quality, security, and secrets across 40+ languages using hooks, CLI, MCP server, and slash commands. | Security | SonarSource |
| sourcegraph | This tool enables searching, reading, and tracing code references across repositories, assessing refactoring impact, investigating incidents through commit/diff history, and conducting security-focused code scans. | Development | — |
| stackhawk-api | Interacts with the StackHawk platform API to retrieve security posture reports, vulnerability findings, and application management data, assisting agents with authentication, data retrieval, and presenting results. | Security | StackHawk |
| stackhawk-hawkscan | Integrates HawkScan DAST scanning into Claude Code by creating stackhawk.yml configuration files, executing scans through CLI or Docker, and converting security findings into prioritized remediation tasks for coding agents. | Security | StackHawk |
| superpowers | Superpowers is a training resource enabling Claude to brainstorm, use subagent-driven development with code review, debug systematically, apply red/green TDD, and create and test new skills. | Development | — |
| ui5 | A plugin that helps coding agents build UI5 projects by supporting creation and validation, API reference access, linting, and adherence to UI5 development best practices. | Development | SAP SE |