"Créer des systèmes de prompt pour les modèles de langage (LLM)" matching MCP servers:

Enables coding agents to inspect Python applications, research source and target models, and produce reviewable migration plans with evidence gates and evaluation before production code changes.

Enables cleaning and sanitizing prompts through an LLM-powered tool that removes sensitive information, provides structured feedback with notes and risks, and normalizes prompt formatting. Supports configurable local or remote OpenAI-compatible APIs with automatic secret redaction.

Fix your vibe coding prompts before they reach the AI. Scores and rewrites across 4 dimensions — no API key, no server, just npx. Now with codebase-aware context injection for design, database, API, auth, testing, and state management.

MCP server for reviewing code changes using LLMs, supporting Copilot, Ollama, and OpenAI-compatible endpoints.

MCP server connecting Claude Code to LM Studio, delegating token-expensive tasks to a local model while keeping the cloud model in control. It reduces cloud context usage by reading files locally and returning only the processed results.

Rewrites coding prompts for optimal results with AI IDEs like Cursor by using Claude to add structure, context, and language-specific considerations to user prompts.

Provides AI coding agents with pre-edit situational awareness by combining structural call graphs and co-change history to prevent incomplete edits. It surfaces files that historically change together, reducing missed coupled modules.

MCP server that exposes an AI decompiler via an OpenAI-compatible API, enabling decompilation, explanation, and variable renaming of disassembly for binary analysis.

A demonstration MCP server for exploring MCP prompts with 10 reusable development prompts.

Bridges local LLMs running in LM Studio with MCP clients like Claude Desktop to perform reasoning and analysis tasks while keeping sensitive data private. It features a suite of tools for local code review, privacy scanning, and content transformation using auto-discovered local models.

MCP server exposing a shared pr-review skill with tools to list, get, run, and evaluate skills, enabling AI assistants to perform code review tasks.

Processes large files, error logs, and codebase searches locally via Ollama to reduce token consumption in Cursor by up to 80%.

MCP server that guides LLM security reviews step-by-step, tracking progress and ensuring all assigned source code is read before completing each plan step.

Intelligently engineers and optimizes prompts for Claude Code with automatic language detection, task type recognition, and interactive refinement capabilities. Works entirely offline without external API dependencies to transform natural language requests into structured, Claude Code-optimized prompts.

A privacy-first MCP server that provides local LLM-enhanced tools for code analysis, security scanning, and automated task execution using backends like Ollama and LM Studio. It enables symbol-aware code reviews and workspace exploration while ensuring that all code and analysis remain strictly on your local machine.

Integrates local language models (like Qwen3-8B) with MCP clients, providing tools for chat, code analysis, text generation, translation, and content summarization using your own hardware.

Provides Cursor-like code intelligence using tools like ripgrep, ctags, and tree-sitter to help LLMs explore and understand entire codebases. It implements a structured, phase-gated workflow to ensure high-confidence code modifications and eliminate hallucinations.

Provides coding agents with visibility into test health through tools for flaky test detection, test quality linting, and LLM evaluation harness, enabling them to triage failures, review test quality, and check prompt changes for regressions.

Enables AI agents to scan MCP servers and AI packages for vulnerabilities, prompt injection, and supply chain attacks.

Bug-report triage and fix-dispatch MCP for vibe coders. Ask your AI coding agent for a plain-English diagnosis of any user-reported bug — with evidence, blast radius, and a paste-ready fix prompt — then dispatch an automated GitHub fix PR without a second LLM key. 71 tools, Supabase-backed, MIT SDK. npx @mushi-mushi/mcp