gpt-rag-mcp python-mcp.instructions.md

A set of coding rules for a Python 3.12 project that implements an MCP server, a program that lets an AI agent use defined tools and resources.

In plain words
What is it for?
Use it when adding or changing MCP tools, resources, prompts, logging, exception handling, dependencies, or startup checks in the project.
Why use it?
It keeps server setup separate from capability code and helps prevent broken asynchronous code, hidden errors, and incorrect imports.

Instructions file for GitHub Copilot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/azure/gpt-rag-mcp/python-mcp
Clone the repo
git clone --depth 1 https://github.com/Azure/gpt-rag-mcp

Made for: GitHub Copilot.

Per session 226 This file is loaded in full into every session.
When invoked 226 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00226 $0.00226
Opus 5 $0.00113 $0.00113
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00023 $0.00023

Measured 2d ago against content hash 49b2a02394c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.github/instructions/python-mcp.instructions.md · 24 lines

What it actually says

Python MCP implementation

  • Python 3.12 and pyproject.toml are authoritative.
  • Prefer explicit types, intent-revealing names, small cohesive functions, and public docstrings that explain behavior and contract.
  • Keep src/server.py focused on application composition and registration. Put capability logic in the appropriate src/tools/, src/resources/, or src/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 uv execution and the container entry point.
  • Restore with uv sync; run the narrowest available checks and an import or startup check for changed runtime modules.
Changes

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.

  1. 2d ago First seen · 24 lines · 226 tokens per session scan A 49b2a02394c5

Subscribe to this mod's changes

gpt-rag-mcp python-mcp.instructions.md is an instructions file published in the GitHub repository Azure/gpt-rag-mcp (22 stars, last pushed 27d ago), licensed MIT. It adds 226 tokens to every session, about $0.0011 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.