"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.

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.

Enables auditing the AI models and SDKs in a repository, drafting evaluation examples, ranking candidates by cost per passing answer, and generating cheapest-first routing configurations, all through read-only local tools that never make network calls. Also estimates monthly token spend and local weights/KV-cache memory so users can pick and size the cheapest model that passes their own tests.

Enables AI agents to navigate JS/TS, HTML, and CSS code — symbol info, outlines, callers, implementations, definitions, references, hover, and diagnostics — through bundled Node language servers. It also builds a cross-file index answering where CSS custom properties and #id/.class selectors are defined and used across stylesheets, markup, and scripts.

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.

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

Lets AI coding agents read an outline of a large file or a digest of noisy command output instead of the full text, while every hidden line stays retrievable on disk through a run handle. Agents can request only the line ranges, slices, or grep matches they need and list recent runs, cutting token spend without losing information.

A git-native merge gate. mergelock check compares two branches before they meet and reports the conflicts git itself won't tell you about: a function whose signature changed on one branch while the other branch added calls to the old signature, a symbol deleted on one side but still used on the other, the same function written twice.

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.

Enables AI agents to parse Rockwell/Allen-Bradley L5X project exports and query PLC tags, UDTs, routines, AOIs, and I/O modules, including cross-reference search across logic to trace where a symbol is used. Ladder logic is returned as compact NeutralText with rung comments, keeping context windows small.

Exposes tools that let AI coding agents browse a repo's schema snapshot of tables and columns and validate their SQL against it before running or writing it, so queries referencing invented or stale table and column names get caught and corrected up front. Provides list_tables, describe_table, search_columns, and check_sql over the same snapshot used by the CLI, hook, and CI check.

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.

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

Enables models to reach all 170 reverse-engineering tools through four meta-tools for searching, schema lookup, calling, and bundle switching, so only a tiny fraction of the tool context is loaded by default. Function bundles can be activated or deactivated at runtime without restarting the host.

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.

A server-side implementation that handles context processing between GitHub repositories and AI models, enabling seamless integration of AI capabilities with codebases through the Model Context Protocol.

Enables agents to run static heuristic scans over a repository path via stdio, surfacing review candidates with file:line evidence for web3 auth and payment vulnerability patterns. Results can be used as CI-style gates or triage input without any dataflow analysis or external dependencies.