"Papers With Code" matching MCP servers:

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.

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.

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.

Cross-platform MCP server providing Claude Code-style plan mode via four tools (enter_plan_mode, get_plan_mode_standards, todo_write, exit_plan_mode) with soft guidance through SKILL.md.

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

An enhanced sequential thinking tool optimized for programming tasks that helps break down complex coding problems into structured, self-auditing thought steps with branching and revision capabilities.

An MCP server for downloading academic papers from multiple sources using intelligent routing and year-aware priority selection. It enables users to retrieve metadata and download single or batch PDFs by DOI or URL.

A server that allows LLMs to run Claude Code with all permissions bypassed automatically, enabling code execution and file editing without permission interruptions.

MCP server that provides read-only analysis of Claude Code session transcripts, enabling queries about project activity, session details, and tool usage.

Enables multi-agent council workflows for coding assistants, providing parallel independent reviews, plans, brainstorms, validation, and research with strict read-only boundaries.

Enables a model to write short Python programs that call a wrapped MCP server's tools as async functions, rather than invoking them one at a time. The program runs in a locked-down Docker sandbox, and every tool call passes through a host-side bridge that enforces an allowlist, schema-validated arguments, call budgets, timeouts and output caps.

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.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.

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.

An MCP server that lets Claude Code delegate coding tasks such as code generation, review, refactoring, and test writing to a local Ollama instance running a Qwen3 model.

An MCP server that provides local code quality analysis for AI coding assistants, supporting file analysis, git diff review, and full project scanning with quality scoring.

Enables AI agents to run untrusted, model-generated Python code in a locked-down throwaway Docker container with enforced isolation and resource limits. Supports starting, checking, and stopping asynchronous runs while returning structured status reports without exposing the host, network, or Docker controls.