azure-devops-mcp: Command for GitHub Copilot

.github/prompts/toolset.prompt.md

toolset is a command for GitHub Copilot from microsoft/azure-devops-mcp. It costs 7 tokens per session (263 once invoked), scanned A, original, MIT.

A command that creates or updates TOOLSET.md, a Markdown document describing the tools available in an Azure DevOps MCP server and how to use them.

In plain words
What is it for?
Use it to document tool purposes, required inputs, optional inputs, and functional groupings in the repository's TOOLSET.md file.
Why use it?
It keeps the tool reference aligned with the available tools, parameters, and removals instead of relying on an outdated manual list.

Command for GitHub Copilot ✓ vendor

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: model in frontmatter.

This is microsoft/azure-devops-mcp's own configuration. It tells GitHub Copilot how to work on azure-devops-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 azure-devops-mcp configures →

About the project

microsoft/azure-devops-mcp is an MCP server that lets AI agents access Azure DevOps projects, repositories, builds, work items, test plans, teams, iterations, and wikis. It is intended for agents that need to read or manage Azure DevOps data through a remote or local server. The catalogue MCP entry operates Azure DevOps through this server.

microsoft/azure-devops-mcp · 2,005 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/azure-devops-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/azure-devops-mcp/main/.github/prompts/toolset.prompt.md
Clone the repo
git clone --depth 1 https://github.com/microsoft/azure-devops-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 toolset

README.md
[![agentmods](https://agentmods.dev/badge/commands/microsoft/azure-devops-mcp/toolset.svg)](https://agentmods.dev/commands/microsoft/azure-devops-mcp/toolset)
Your own site
<a href="https://agentmods.dev/commands/microsoft/azure-devops-mcp/toolset"><img src="https://agentmods.dev/badge/commands/microsoft/azure-devops-mcp/toolset.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 263 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00007 $0.00263
Opus 5 $0.00003 $0.00131
Sonnet 5 $0.00001 $0.00053
Haiku 4.5 $0.00001 $0.00026

Measured yesterday against content hash 8b101735d29e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

toolset 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 yesterday.

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/prompts/toolset.prompt.md · 25 lines

What it actually says

[🪪] Role

Act as a documentation specialist, who carefully examines tools available to you to document their purpose and usage. You never optimize tool selection, always examine all available tools. You never call any of the ado tools, just document them.

[🛠️] Toolset file

The toolset is a Markdown file located at #file:../../docs/TOOLSET.md It provides a meaningful yet concise summary of all tools available in the Azure DevOps MCP server. It lists all tools, grouped by their functional area, and for each tool it describes its purpose and usage (including all required and optional parameters).

[📋] Instructions

Carefully examine the contents of the current [🛠️] and then update it to match the tools you have available. If a tool previously listed is now unavailable or its parameters were removed or renamed, warn the user before proceeding. Avoid updates that are cosmetic only; add missing tools, remove obsolete tools, update argument lists and purposes as needed.

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. yesterday First seen · 25 lines · 7 tokens per session scan A 8b101735d29e

Subscribe to this mod's changes

toolset is a command published in the GitHub repository microsoft/azure-devops-mcp (2,005 stars, last pushed yesterday), licensed MIT. It adds 7 tokens to every session and 263 once invoked, about $0.0000 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 2026-09-07.