"Tools and Systems for Math, AI, and Proof Verification with Bug Detection and Auto Fixing" matching MCP servers:

MCP server that provides six verification tools (Lean proof checking, axiom audit, bound, gridlock check, certificate verification, residency check) with honest status reporting (ok/failed/unavailable) to prevent agents from claiming unchecked proofs passed.

Turns a codebase into a persistent knowledge graph so AI coding agents can answer structural questions about functions, call chains, routes, and cross-service links through graph queries instead of reading files one by one.

AI-powered smart contract security analysis for AI agents and developers, enabling scanning of Solidity repos for vulnerabilities.

Bridges UI feedback captured by a browser extension on localhost apps into a Claude Code session, queueing picked elements, comments and rewrite requests as batches that the coding agent can claim and act on. It also lets Claude report progress and per-item results back to the extension, and can import batches exported as JSON.

Enables static analysis and code smell detection by connecting to an external analysis API.

Architectural Gatekeeper for AI coding. Prevents "tunnel vision" bugs by forcing the AI to verify dependencies (via AST parsing) before editing files. Supports JavaScript & TypeScript. Blocks unsafe edits until the AI proves it understands the impact

Analyzes git repository changes to generate conventional commit messages and summaries using OpenAI's GPT-4o-mini. It provides detailed tracking of modified, added, and deleted files to streamline the version control process.

A headless IDA Pro MCP server that enables AI agents to automatically open, analyze, and query multiple binary files simultaneously without manual GUI interaction. It provides 36 tools for tasks like decompilation, disassembly, and cross-reference analysis through IDA's idalib library.

MCP server providing npm registry search, package details, dependency auditing, bundle size estimation, and package comparison tools for AI agents.

An MCP server that provides a persistent sandbox for AI coding agents to explore codebases server-side, returning only compact summaries to reduce context consumption.

locidx

MCP server providing dependency and package management tools for AI agents. Analyze licenses, find outdated packages, visualize dependency trees, estimate bundle sizes, and audit security vulnerabilities.

Enables AI agents to explore, analyze, and search file systems, with tools for directory trees, file statistics, duplicate detection, code counting, and multi-criteria file search.

Provides AI-callable tools for modernizing legacy applications, including stack detection, API contract extraction, SQL to Flyway conversion, and migration effort estimation.

A Model Context Protocol server that helps programmers understand code by providing explanations, tech stack analysis, and best practice suggestions through prompt templates.

MCP server providing parser-backed validation, parsing, documentation, and editor assistance for AI agents working with _hyperscript.

Provides documentation generation and analysis tools for AI agents, including JSDoc generation, README analysis, changelog generation, API documentation, and code comment analysis.

MCP server providing code review, auto-fix, test running, linting, formatting, and refactor suggestions for Claude Code.

Local MCP servers that give Claude Code access to other tools mid-session.

Code linting and style checking tools for AI agents, exposed as an MCP server. Supports style checks, naming conventions, complexity analysis, dead code detection, and import analysis.