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/python-mcp.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/python-mcp)<a href="https://agentmods.dev/instructions/azure/gpt-rag-mcp/python-mcp"><img src="https://agentmods.dev/badge/instructions/azure/gpt-rag-mcp/python-mcp/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/python-mcp"><img src="https://agentmods.dev/badge/instructions/azure/gpt-rag-mcp/python-mcp.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 | $0.00226 | $0.00226 |
| Opus 5.5 | $0.00090 | $0.00090 |
| Sonnet 5.5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
gpt-rag-mcp python-mcp.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 2mo 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
Python MCP implementation
- Python 3.12 and
pyproject.tomlare authoritative. - Prefer explicit types, intent-revealing names, small cohesive functions, and public docstrings that explain behavior and contract.
- Keep
src/server.pyfocused on application composition and registration. Put capability logic in the appropriatesrc/tools/,src/resources/, orsrc/prompts/module. - Reuse existing helpers before adding dependencies or abstractions.
- Preserve async correctness. Do not perform blocking network, disk, process, or provider I/O on an async request path.
- Preserve the original cause when translating exceptions and use configured logging for runtime diagnostics.
- Do not add broad catches, silent defaults, success-shaped fallbacks, or mutable global request state.
- Keep imports package-correct for both local
uvexecution and the container entry point. - Restore with
uv sync; run the narrowest available checks and an import or startup check for changed runtime modules.
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.
- 2mo ago First seen · 24 lines · 226 tokens per session scan A 49b2a02394c5
gpt-rag-mcp python-mcp.instructions.md is an instructions file published in the GitHub repository Azure/gpt-rag-mcp (22 stars, last pushed 10d ago), licensed MIT. It adds 226 tokens to every session, about $0.0009 per session on Opus 5.5. 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.
gpt-rag-mcp python-mcp.instructions.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gpt-rag-mcp python-mcp.instructions.mdAzure/gpt-rag-mcp | Instructions file | 22 | 10d ago | MIT | A | 226 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |