mcp: Instructions file for GitHub Copilot

.github/copilot-instructions.md

mcp copilot-instructions.md is an instructions file for GitHub Copilot from microsoft/mcp. It costs 1,186 tokens per session, scanned A, original, MIT.

A set of coding and review rules for contributing to the microsoft/mcp repository, including C# style, testing, documentation, and pull-request practices.

In plain words
What is it for?
Use it while writing or reviewing C# and PowerShell changes, updating tests or documentation, and preparing pull requests for this repository.
Why use it?
It gives coding agents consistent project-specific instructions and helps changes meet the repository's build, security, and review requirements.

Instructions file for GitHub Copilot ✓ vendor

Written for GitHub Copilot: a Copilot instructions file.

This is microsoft/mcp's own configuration. It tells GitHub Copilot how to work on mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp configures →

About the project

microsoft/mcp is a repository of Microsoft’s Model Context Protocol server implementations, which let AI applications connect to data sources and tools through a shared client-server interface. It supports Microsoft MCP server contributors and the catalogue entries are add-ons for working with these servers.

microsoft/mcp · 3,800 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/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.

Copy the file
curl -O https://raw.githubusercontent.com/microsoft/mcp/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/microsoft/mcp

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/microsoft/mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/microsoft/mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/microsoft/mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/mcp/copilot-instructions/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.

agentmods 80×15 button for mcp copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/microsoft/mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,186 This file is loaded in full into every session.
When invoked 1,186 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01186 $0.01186
Opus 5.5 $0.00474 $0.00474
Sonnet 5.5 $0.00237 $0.00237
Haiku 4.5 $0.00119 $0.00119

Measured 17d ago against content hash e6428f45cdd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp copilot-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 17d 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/copilot-instructions.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Instructions for GitHub Copilot

  • Always use primary constructors in C#
  • Always run dotnet build after making a change
  • Always use System.Text.Json over Newtonsoft
  • Always put new classes and interfaces in separate files
  • Always make members static if they can be
  • All generated code needs to be AOT safe
  • Never expose RetryPolicyOptions through tool options or service contracts; use Azure SDK retry defaults
  • Always review your own code for consistency, maintainability, and testability
  • Always ask for clarifications if the request is ambiguous or lacks sufficient context.

Engineering System

  • Use ./eng/scripts/Build-Local.ps1 -VerifyNpx to verify changes to powershell, c# project files and npm packages
  • Don't run local builds to check pipeline YAML files (e.g., files in eng/pipelines/ with .yml extension)

Pull Request Guidelines

  • Ensure all tests pass
  • Follow the contribution guidelines
  • Include appropriate documentation
  • Include tests that cover your changes
  • Update CHANGELOG.md with your changes
  • Run .\eng\common\spelling\Invoke-Cspell.ps1
  • Create the auto-generated PR body as normal, but copilot should add an additional section after all of its regular PR body content. The contents should be:
    ## Invoking Livetests
    
    Copilot submitted PRs are not trustworthy by default. Users with `write` access to the repo need to validate the contents of this PR before leaving a comment with the text `/azp run mcp - pullrequest - live`. This will trigger the necessary livetest workflows to complete required validation.
    

Transitioning Live Tests to Recorded Tests

  • Always convert tool services to inject IHttpClientFactory into its clients and use IHttpClientFactory.CreateClient method to instantiate the HttpClient for usage in the tool classes' methods.
    • If IHttpClientFactory is already injected into the client, ensure that IHttpClientFactory.CreateClient is used to instantiate the HttpClient. If this is done, then no further action is needed.
  • Always re-parent test classes parented by CommandTestsBase to RecordedCommandTestsBase. This will require minor fixture adjustments.
  • In test classes extending RecordedCommandTestsBase, every test for a LocalRequired = true tool must call AssertLocalToolIsUnavailableInHttpMode(toolName) and return early when it returns true. This verifies that remote HTTP mode does not expose the local-only tool.
  • Always generate a new assets.json file alongside the livetest csproj file if one does not exist. This file should contain the following content:
    {
      "AssetsRepo": "Azure/azure-sdk-assets",
      "AssetsRepoPrefixPath": "",
      "TagPrefix": "<TestCsProjFileNameWithoutExtension>", // e.g., "Azure.Mcp.Tools.KeyVault.Tests"
      "Tag": ""
    }
    
  • Copilot should utilize the recorded test documentation in docs/recorded-tests.md for more details on how to convert and validate recorded tests.

Read the full file on GitHub · 62 lines

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. 17d ago Changed · +5 tokens per session e6428f45cdd3
  2. 1mo ago Changed · +1 lines · +59 tokens per session 748dd4e28504
  3. 1mo ago First seen · 61 lines · 1,122 tokens per session scan A 8457e627cf9a

Subscribe to this mod's changes

mcp copilot-instructions.md is an instructions file published in the GitHub repository microsoft/mcp (3,800 stars, last pushed yesterday), licensed MIT. It adds 1,186 tokens to every session, about $0.0047 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens