gpt-rag-mcp
Azure/gpt-rag-mcp is a Python server that exposes GPT-RAG capabilities through the Model Context Protocol. It is deployed with Azure resources and consumed by GPT-RAG through its MCP strategy, while the catalogue provides instructions, skills, and agents for operating it.
Latest release v0.3.8 · 28 May 2026
16 files for Claude Code, GitHub Copilot, Codex and OpenCode: architecture, implementation, release, gpt-rag-mcp copilot-instructions.md and 12 more — 3,909 tokens loaded in every session.
.github/copilot-instructions.md A 635 tok .github/instructions/agentic-assets.instructions.md A 189 tok .github/instructions/deployment.instructions.md A 242 tok .github/instructions/documentation.instructions.md A 230 tok .github/instructions/mcp-contracts.instructions.md A 303 tok .github/instructions/python-mcp.instructions.md A 226 tok .github/instructions/release.instructions.md A 222 tok AGENTS.md A 1,862 tok .github/skills/architecture-decision/SKILL.md A 42 tok .github/skills/component-release/SKILL.md A 39 tok .github/skills/documentation-consistency/SKILL.md A 39 tok .github/skills/engineering-principles/SKILL.md A 37 tok .github/skills/mcp-capability-development/SKILL.md A 38 tok .github/agents/architecture.agent.md A 41 tok .github/agents/implementation.agent.md A 31 tok .github/agents/release.agent.md A 43 tok These files are Azure/gpt-rag-mcp's own configuration — they tell Claude Code, GitHub Copilot, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.