"DNS Doctor" matching MCP servers:

Finds slow pandas code (iterrows loops, row-wise apply, concat in a loop), runs a rewrite on the same data to check the result is identical, and measures the speedup. Tools: check_code, verify_rewrite, list_rules.

Enables AI assistants to diagnose and fix iOS app issues that cause App Store rejections, such as missing privacy manifests, permission strings, and test credentials, before submission.

CI health reports for GitHub Actions: flaky tests named from logs, wasted compute priced in dollars, zombie crons, PR feedback time, plus 21 lint rules with safe auto-fixes. Read-only MCP tools wrap the same Go binary.

Evidence-backed, read-only codebase diagnostics for coding agents: secrets, dependency, RLS, and source-impact audits with a verify loop and PR review verdicts. Never writes files or uses the network by default.

Read-only npm dependency diagnostics: inventory, audit and health checks from package-lock.json, no account needed.

Offline PostgreSQL diagnostics: reviews SQL, risky migrations, candidate indexes and EXPLAIN JSON plans without database credentials or executing statements.

Enables an MCP client to inspect a local Python project directory, reporting its package-manager signals, local Python environment, and available tooling. It also runs Ruff lint and formatting checks and returns the outcomes as structured results, without modifying the project or installing dependencies into it.

MCP server that produces scored, evidence-cited audits of public GitHub repos via tools for fetching metadata, reading files, scanning git history, and checking hygiene.

Enables agents to lint exported n8n workflow JSON for security, structure, reliability, and Code node issues, outline workflow paths and branches, review safe auto-fixes, and triage failed executions through MCP tools.

Provides AI coding agents with structured, deterministic repository intelligence—file tree, dependencies, hotspots, and git history—via Model Context Protocol, enabling them to understand codebases without reconstructing architecture from scratch.

Enables reading agent-made changes in context by capturing Git diffs with verified task context, ordering every change into reading blocks, and recording versioned feedback so corrections can be steered with a short instruction. Exposes these capabilities as MCP tools alongside an optional loopback-only web review viewer.

Tracks the complete lineage and DNA of every line of code, enabling impact analysis, bug risk prediction, and code archaeology through deterministic analysis of git history and AST.

Analyzes a codebase to extract its coding conventions and exposes tools via MCP for AI agents to retrieve live style rules, ensuring generated code matches the project's unwritten style.

MCP server for Apple HIG compliance auditing, providing tools to list skills, search/lookup HIG references, audit files/projects, and explain findings.

Enables agents to analyze OpenAPI contracts for deterministic integration risks, plan auth, sync, action, and webhook candidates, and diff contract versions for likely breaking changes through read-only tools.

A secure local MCP server that allows AI assistants to inspect and diagnose Expo-based React Native projects, offering read-only tools for project summary, doctor checks, dependency validation, and public config retrieval.

Analyzes Godot GDScript files for code quality and provides refactoring plans. Includes tools for script analysis, refactoring planning, and service code generation.

PCI DSS v4.0.1 compliance scanner for Go payment services, delivered as an MCP server. Every finding maps to a specific PCI DSS requirement ID. Taint-aware cardholder data flow analysis with PCI SSC FAQ semantics, designed to complement broad SAST tools like Semgrep and CodeQL - not replace them.

Enables LLM agents to search, resolve and audit DTCG design tokens — finding the token behind an intent or a hard-coded color/size, checking naming grammar, auditing CSS for hard-coded or unknown tokens, arbitrating semver, and previewing token additions as JSON Patch diffs. Writes are gated behind explicit confirmation plus an opt-in flag, so every change arrives as a reviewable proposal rather than an edit.

Analyzes repositories to extract engineering culture and conventions, generating executable skill scripts and rule documents for AI coding agents.

Get your research artifact ready for Artifact Evaluation before the deadline: scan the repo, scaffold the easy fixes, verify the run path, and generate the appendix.

Enables external AI coding agents to use a running VS Code instance for IDE-aware file operations, project-wide symbol renames, file moves that update imports, code analysis, diagnostics, and formatting through a local MCP endpoint. Provides configurable tool categories, optional bearer-token authentication, and protections against DNS rebinding and cross-origin browser requests.

Exposes code search and file reading tools over the Model Context Protocol, enabling any MCP-compatible client to query a codebase with natural language.