"Papers With Code" matching MCP servers:

Enables Codex CLI to perform code reviews on uncommitted changes via an MCP tool, keeping review context separate from the main session.

Enables users to read code with selection-based floating explanations, file-purpose summaries, interactive code mind maps, and source navigation, available as an independent web app or Codex plugin. It supports local-only reading workflows, model selection, caching, and project context without sending chat messages.

Validates AI-generated Python: syntax, lint, security scan and deterministic repair.

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

Enables Claude Code agents and subagents to get an independent read-only review of their changes from OpenAI Codex and to continue that same Codex conversation later for re-checks. Runs each request in an isolated CODEX_HOME so those threads stay separate from the Codex desktop app, supporting parallel callers and per-call model, effort, sandbox, and timeout settings.

Indexes codebases cut at function and class boundaries into Oracle AI Database 26ai, letting AI coding tools search code by name or meaning, trace callers, callees and change impact, read per-module wiki pages, and recall facts from earlier sessions. All of it is served over the Model Context Protocol with embeddings computed in-database, so no source code leaves the machine and no API key is required.

Helps AI assistants optimize Linux workloads on Arm64 by parsing perf report output, recommending NEON SIMD intrinsics for hot loops, and auditing Python dependency manifests for arm64 wheel availability — all offline and structured.

Provides a code search service via MCP, allowing AI clients to perform fast, indexed searches across large codebases using Zoekt, with support for filters like repository, language, and path.

Lets MCP-compatible AI assistants have read-only conversations with OpenAI Codex CLI for code analysis, review, and Q&A.

Enables developers and AI agents to compress context, plan token budgets, rerank results, patch code, analyze ASTs and dependencies, isolate stack traces, compile polyglot types, solve deterministic math, schedule constraints, judge A/B tests, and diff agent memory checkpoints through 12 specialized tools.

A code review tool that generates detailed HTML review documents by comparing branches or commits, with author filtering and intelligent analysis.

A local MCP server that provides semantic code search for Python codebases using tree-sitter for chunking and LanceDB for vector storage. It enables natural language queries to find relevant code snippets based on meaning rather than just text matching.

embedded code search engine CLI -AST based that just works - improves speed and efficiency for coding agent

MCP server that provides a 216-rule, framework-aware Kotlin/JVM security analyzer, enabling AI coding agents to query real security findings while writing code.

Provides coding agents with file inventory, ranked search, location-aware reading, code packing, and note writing over the workspace folder through MCP, without involving a model.

Enables efficient analysis of large codebases using Claude Code and Kimi K2.5 through the Model Context Protocol, with session caching and parallel processing to reduce costs and time.

Enables fast, low-token code search for AI coding agents via a local BM25 engine built on SQLite FTS5, with support for camelCase, snake_case, and Japanese text. Provides a stateless MCP stdio server and a Hermes adapter for multi-agent environments.

Integrates Google's Gemini AI models into Claude Code and other MCP clients to provide second opinions, code comparisons, and token counting. It supports streaming responses and multi-turn conversations directly within your existing AI development workflow.

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

An MCP server that provides dynamic codebase context to Claude Code through tools like hybrid search, recent changes, and symbol definitions, enhancing AI-assisted coding with local RAG.