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.
Borrowing it
Nothing to install: this file belongs to Azure/gpt-rag-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Azure/gpt-rag-mcp/main/.github/instructions/mcp-contracts.instructions.mdgit clone --depth 1 https://github.com/Azure/gpt-rag-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/azure/gpt-rag-mcp/mcp-contracts)<a href="https://agentmods.dev/instructions/azure/gpt-rag-mcp/mcp-contracts"><img src="https://agentmods.dev/badge/instructions/azure/gpt-rag-mcp/mcp-contracts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/azure/gpt-rag-mcp/mcp-contracts"><img src="https://agentmods.dev/badge/instructions/azure/gpt-rag-mcp/mcp-contracts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00303 | $0.00303 |
| Opus 5 | $0.00151 | $0.00151 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
gpt-rag-mcp mcp-contracts.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
MCP runtime contracts and safety
- Runtime MCP capabilities are product code. They are distinct from GitHub
Copilot engineering agents and skills under
.github/. - Treat capability names, descriptions, argument names and types, defaults, result shapes, resource URIs, prompt parameters, mounts, and error behavior as orchestrator-facing contracts.
- Prefer additive compatible evolution. Document and coordinate any rename, removal, required parameter, semantic change, or return-shape change with the GPT-RAG orchestrator and platform repository.
- Keep each tool focused and register it in
src/server.py; do not inline unrelated provider or business logic into server wiring. - Validate and bound untrusted inputs and outputs. Never interpolate arbitrary input into commands, paths, queries, URLs, or privileged Azure operations.
- Enforce authorization and least privilege in code or the provider boundary; descriptions and prompts are not controls.
- Bound external work with timeouts, response-size or item limits, and deliberate retry behavior.
- Avoid leaking secrets, credentials, personal data, or sensitive upstream responses through errors or tool results.
- Load
mcp-capability-developmentfor any capability or registration change. - Exercise changed capabilities with the MCP Inspector and, when relevant,
end to end through the orchestrator
mcpstrategy.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 28 lines · 303 tokens per session scan A 03f9ba82a15a
gpt-rag-mcp mcp-contracts.instructions.md is an instructions file published in the GitHub repository Azure/gpt-rag-mcp (22 stars, last pushed 7d ago), licensed MIT. It adds 303 tokens to every session, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.