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

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

Git-driven MCP server that manages and provides prompt templates with Handlebars support, enabling teams to collaborate on and version-control reusable, dynamic prompts across AI editors like Cursor and Claude Desktop.

MCP server for managing a project backlog as Markdown files in Git, enabling AI agents to read, create, and update tasks programmatically.

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.

Read-only MCP server for querying official dental professional registry data from the Regional Council of Dentistry of Maranhão, Brazil. Enables natural-language lookups via a single consult tool.

Scan codebases for LLM API calls and estimate monthly costs. Compare costs between git refs to catch cost regressions during code review.

Combines GitHub releases from multiple repositories into a single product release note, with context sources for LLM synthesis.

Wraps portfolio-drift-agent as MCP tools, letting LLM clients audit a portfolio of projects against GitHub conversationally.

Analyzes codebases using Repomix and LLMs to provide structured code reviews with specific issues and recommendations, supporting multiple LLM providers including OpenAI, Anthropic, and Gemini.

Deterministic code review MCP server that provides tools for file selection, rule matching, comment positioning, and reflection, ensuring stable review quality without LLM calls.

Enables version-controlled golden dataset management and semantic evaluation for RAG/LLM pipelines using TF-IDF cosine similarity, without requiring an LLM API key.

GitHub MCP server for Claude Code, Cursor, Cline, Windsurf, and any MCP-compatible client. Exposes GitHub tools (issues, pull requests, code search, file content) to your LLM via the Model Context Protocol.

MCP server that decomposes tasks into plans with disjoint file boundaries, validates overlaps, and creates git worktrees with a ready prompt per plan.

Espacio compartido y persistente por repositorio para sesiones de Claude Code: cada sesión registra su actividad vía hooks, ves qué hicieron/hacen las demás, te avisa si vas a pisar trabajo ajeno, y podés dejar notas. Sin daemon.

Enables LLM agents to query Patchwork kernel patches, series, CI checks, and comments via natural language through a read-only MCP server.

Enables LLM clients to list, read, review, and comment on GitHub pull requests, turning an AI assistant into a fully capable code reviewer.

Enables local-first document versioning with content-addressable storage, word-level AST diffs, and AI-compliance auditing for LLM agents.

MCP server for the Bitbucket Cloud REST API v2.0, providing 32 tools across 5 toolsets for repository management, pull requests, issues, pipelines, and more with safety controls and LLM-optimized output.

An MCP server for the GitHub API that provides repo summaries, recent commit messages, raw README resources, and a prompt template for evaluating repos as portfolio pieces.

Integrates with GitHub REST API to allow LLM agents to list and create repository issues.