dynatrace-mcp: Instructions file for GitHub Copilot

.github/instructions/mcp-tools.instructions.md

dynatrace-mcp mcp-tools.instructions.md is an instructions file for GitHub Copilot from dynatrace-oss/dynatrace-mcp. It costs 315 tokens per session, scanned A, original, MIT.

Project instructions for building tools that follow the Model Context Protocol, a standard way for an AI assistant to call software tools. They require using the project's helper function and documenting each tool's behaviour and safety properties.

In plain words
What is it for?
Use them when adding Dynatrace MCP tools, defining input schemas, setting read-only or destructive-operation hints, authenticating clients, and returning tool results.
Why use it?
They keep tool registration consistent and make important details—such as whether a tool changes data or needs approval—clear to users and the assistant.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

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

Reuse

Borrowing it

Nothing to install: this file belongs to dynatrace-oss/dynatrace-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/dynatrace-oss/dynatrace-mcp/main/.github/instructions/mcp-tools.instructions.md
Clone the repo
git clone --depth 1 https://github.com/dynatrace-oss/dynatrace-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 dynatrace-mcp mcp-tools.instructions.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dynatrace-oss/dynatrace-mcp/mcp-tools"><img src="https://agentmods.dev/badge/instructions/dynatrace-oss/dynatrace-mcp/mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 315 This file is loaded in full into every session.
When invoked 315 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 $0.00315 $0.00315
Opus 5 $0.00158 $0.00158
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00032 $0.00032

Measured 10d ago against content hash 5f878c78710c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

dynatrace-mcp mcp-tools.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 10d 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/mcp-tools.instructions.md · 36 lines

What it actually says

Implementing MCP Tools

Always use the tool() helper function (see src/index.ts) instead of calling server.registerTool() directly.

tool(
  'my_tool_name', // snake_case name, used as MCP tool identifier
  'My Tool Title', // human-readable title
  'What this tool does.', // description shown to the agent
  {
    // Zod parameter schema (ZodRawShape)
    entityId: z.string().describe('The entity ID to look up'),
  },
  // Tool Annotations
  {
    readOnlyHint: true, // only reads data, never modifies it
    destructiveHint: true, // may perform irreversible actions, requires human approval
    idempotentHint: true, // repeated calls with the same arguments produce the same result with no additional side-effects
    openWorldHint: true, // interacts with external or live data sources
  },
  // Tool Implementation
  async ({ entityId }) => {
    const dtClient = await createAuthenticatedHttpClient(['storage:entities:read']);
    // ... call Dynatrace SDK or capability function
    // And return the result
    return `Result: ${entityId}`;
  },
);

The callback must return either a string or { text: string; _meta?: Record<string, unknown> }. Errors thrown inside are caught and returned as isError: true responses automatically.

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. 10d ago First seen · 36 lines · 315 tokens per session scan A 5f878c78710c

Subscribe to this mod's changes

dynatrace-mcp mcp-tools.instructions.md is an instructions file published in the GitHub repository dynatrace-oss/dynatrace-mcp (136 stars, last pushed 15d ago), licensed MIT. It adds 315 tokens to every session, about $0.0016 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.

Related

Other instructions, from other repositories