"The most widely used models" matching MCP servers:

Enables Claude Code to request independent code reviews and second opinions from other AI models (like Gemini, GPT-OSS) via the Antigravity CLI, directly from the chat.

An MCP server that turns any public GitHub repository into a PDF report containing a codebase summary, the most recent commits, and suggested improvements — generated locally by an Ollama model.

Enables adversarial code review by connecting Claude Code to OpenAI Codex, iterating until consensus is reached between the two AI models.

AI access to SAP ECC and on-premise S/4HANA: natural-language table queries, ABAP source reads, where-used lookups, syntax checks, dumps and background jobs — served by an in-system ABAP add-on behind a single ICF node, with no BTP, ADT or RISE dependency. Every call runs under the calling user's own SAP authorizations and is audit-logged inside the customer's system; the connector is MIT-licensed

Enables querying Odoo's model registry (fields, inheritance, methods) without a database connection by loading the registry in-memory.

Enables AI models to run Stylelint on CSS files and fix linting warnings directly through the Model Context Protocol.

Routes narrow text-processing tools (classification, extraction, summarization, etc.) to budget models to reduce token consumption on the main model.

An MCP server for React Native Upgrade Helper diffs. It fetches the same generated template diffs used by React Native Upgrade Helper, backed by react-native-community/rn-diff-purge, and exposes them as MCP tools that agents can call directly.

The server facilitates natural language interactions for exploring and understanding codebases, providing insights into data models and system architecture using a cost-effective, simple setup with support for existing Claude Pro subscriptions.

An MCP server that lets AI models run code in 31 languages, evaluate symbolic math and logic problems, and measure complexity—exposed as 48 tools for execution, session management, translation, optimization, and more.

Enterprise-grade code intelligence server for AI assistants that analyzes codebases for due diligence, tech debt, security vulnerabilities, and code quality.

Enables AI agents to analyze large codebases and document collections by consulting large context window models (up to 2M tokens) via OpenRouter when files exceed the current agent's context limits.

Code-search engine that parses TypeScript and JavaScript with a real AST, stores the symbol graph in SQLite, and serves AI assistants exact matching declarations (functions, classes, types) via BM25 fused with declaration-exact ranking — saving tokens by returning only the relevant code instead of whole files.

Enables coding agents to audit a Next.js codebase read-only, checking routes, Prisma models, environment variables, and locale consistency via MCP tools.

Enables AI agents to fetch and pack the most relevant files from any GitHub repository for a given query, within token limits. Works with Claude Desktop, Cursor, Windsurf, and VS Code Copilot.

MCP server that helps AI models understand Vite/Nuxt applications better, available as both a Nuxt module and Vite plugin.

Enables Claude-powered pre-push code review, blocking bad commits by analyzing diffs with Anthropic's models.

A Python MCP server that decompiles Android APK/XAPK/JAR/AAR files and extracts HTTP APIs used by the app.

CodeGuard MCP is a real-time AI code security scanning tool used to detect vulnerabilities, keys, and compliance issues in AI-generated code, and is suitable for code security reviews in development environments

Provides AI coding agents with ground truth about a Rails app via 45 read-only tools covering schema, models, routes, controllers, views, jobs, and conventions, working over MCP or CLI and functioning even when the app cannot boot.