"A tool or method for editing code using diffs" matching MCP servers:

Enables real-time AI editing assistance in the WordPress block editor, allowing Claude to proofread, review, edit, translate, compose, and prepare posts for publishing.

Enables AI agents to perform exact-match, transactional multi-file edits with atomic writes, dry-run diffs, and self-correcting error diagnostics that reduce token usage.

Enables LLMs to perform addition calculations through a stdio-based MCP server with an add_numbers tool and type-safe validation.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Bridges Claude Code CLI with Cursor IDE to use your existing Claude subscription without separate API costs.

A custom MCP tool that integrates Perplexity AI's API with Claude Desktop, allowing Claude to perform web-based research and provide answers with citations.

AI-powered video editing toolkit: scene splitting, subtitle generation, thumbnail planning, color grading, and aspect ratio conversion.

A Model Context Protocol (MCP) server that learns from your video editing behavior and provides intelligent assistance for film and television post-production workflows.

Enables fetching weather forecasts for the USA via NWS API and for Israel via browser automation using Playwright.

A Model Context Protocol server that provides a scratchpad tool for LLMs to organize thoughts, take notes, and plan approaches to complex problems.

MCP router that fronts your other MCP servers behind a few small generic tools, so their tool definitions stay out of the context window and are discovered on demand.

A simple MCP server implementation in TypeScript that communicates over stdio, allowing users to ask questions that end with 'yes or no' to trigger the MCP tool in Cursor.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Enables AI assistants to read, search, draft, and send email with attachments over IMAP/SMTP, keeping passwords in the OS keyring and gating outgoing mail on user approval for CMMC Level 2 environments.

Enables LLM clients to access crop yield predictions from RGB imagery, topic-based PDF literature, and soil lab/moisture CSV data.

Enables Claude Code CLI to interact with Obsidian by reading selections, opening files, showing diffs, and running an embedded terminal.

MCP server that routes natural language requests to structured tool calls using a LoRA-tuned small language model, with built-in validation, retry, and fallback recovery.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Provides agents with tools to score a page's AI readiness, check which AI crawlers robots.txt blocks, and assess passage citability—all performed locally.

Provides a unified MCP server to interact with multiple middleware (Loki, MySQL, Redis, RocketMQ, Elasticsearch, MongoDB) through a desktop application for connection management and configuration export.

Enables converting documents between formats over MCP: any supported input (docx, odt, xlsx, ods, pptx, odp, pdf) to structured Markdown, Markdown to docx, odt or pdf, direct cross-format pairs, and Markdown to sanitised HTML. Fidelity losses are reported rather than failing the conversion.

Enables AI coding agents to submit code, files, or diffs for deterministic checks and optional re-verified LLM repair, returning cleaned code, structured findings, and a pass/fixed/reject verdict.

A Zsh execution tool for Claude Code providing yield-based command execution, PTY mode for interactive programs, circuit breaker for timeout protection, and adaptive learning (A.L.A.N.) for retry detection and proactive insights.

Local MCP server for A-share stock trading via Tonghuashun, offering account/position queries, buy/sell/cancel orders with risk controls and forced user confirmation; currently simulated with a reserved interface for real broker channels.

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

Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tradeoff analysis without allowing Claude to edit files or run commands.

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

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

Zero-trust PII & secret airlock for coding agents (reversible <TOKEN_N> file read/write sanitization, safe subprocess runner with stdout scrubbing, and 0.2ms Git pre-commit scanning via pure-ONNX GLiNER + regex).

Enables semantic search over codebases using natural language queries, returning relevant code snippets with source locations. Integrates with Claude Code for automatic codebase exploration.

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.

Turns your PDFs into locally stored flashcards and quizzes, grades your answers, and schedules spaced-repetition reviews entirely on your machine.

Gemini-powered MCP server for automated code review, analysis, and documentation.

An MCP server for searching and downloading books from Library Genesis, supporting EPUB, MOBI, PDF, and more through natural language queries.

Provides a no-op 'think' tool that enables Claude to decompose complex problems and enhance reasoning by pausing to organize thoughts.

Renders source code as beautiful SVG or PNG images with syntax highlighting, line numbers, and diff support. Ideal for AI agents to present code visually to humans or for sharing snippets.

Enables agents to run semantic search across one or more local project directories by automatically maintaining a LAN-local Qdrant index with Ollama embeddings. Indexing, staleness checks, and incremental updates happen transparently, so users can query code by meaning without managing collections, chunks, or hashes.

Checks a code repository without running it: Safe, Works and Complete scores with an A-F grade, catching leaked keys, dangerous calls, invented or lookalike packages, broken imports and missing project files. Standard-library Python; MCP tools scan, orphans and explain.

Central registry for AI tools with vector search and knowledge graph, enabling intelligent tool discovery, chaining, and execution via MCP.

Provides structural, queryable understanding of a Python codebase via MCP tools, enabling direct lookups for callers, dependencies, and class hierarchies without repeated grep/read cycles.