agentmods.dev

PowerAutomate_MCP: Instructions file for Claude Code

CLAUDE.md

PowerAutomate_MCP CLAUDE.md is an instructions file for Claude Code from karenrebecag/PowerAutomate_MCP. It costs 666 tokens per session, scanned A, original, MIT.

A set of project instructions for building a local Microsoft Power Automate server. Power Automate is Microsoft's service for running cloud workflows, and MCP is a way for an agent to call tools.

In plain words
What is it for?
Use it when developing or extending this Power Automate MCP server, especially when handling login tokens, API routes, or project conventions.
Why use it?
It documents authentication, security rules, and the need to check Microsoft's undocumented API responses before adding support for an endpoint.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is karenrebecag/PowerAutomate_MCP's own configuration. It tells Claude Code how to work on PowerAutomate_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 PowerAutomate_MCP configures →

not rated 1repo 2d ago A scan 666 tokens original MIT
View source ↗ karenrebecag/PowerAutomate_MCP
Reuse

Borrowing it

Nothing to install: this file belongs to karenrebecag/PowerAutomate_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/karenrebecag/PowerAutomate_MCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/karenrebecag/PowerAutomate_MCP

Made for: Claude Code.

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 PowerAutomate_MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/karenrebecag/powerautomate_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/karenrebecag/powerautomate_mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/karenrebecag/powerautomate_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/karenrebecag/powerautomate_mcp/claude-md/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 PowerAutomate_MCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/karenrebecag/powerautomate_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/karenrebecag/powerautomate_mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 666 This file is loaded in full into every session.
When invoked 666 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 $0.00666 $0.00666
Opus 5 $0.00333 $0.00333
Sonnet 5 $0.00133 $0.00133
Haiku 4.5 $0.00067 $0.00067

Measured 10d ago against content hash 56b258398e6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

PowerAutomate_MCP CLAUDE.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.

CLAUDE.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Power Automate MCP

Local stdio MCP server for personal Power Automate cloud flows. Personal reverse-engineering project. Read README.md for the product story, docs/DEVELOPMENT.md for how to extend it, and docs/SECURITY.md for tokens.

The one thing to never forget

This rides api.flow.microsoft.com — undocumented and unsupported. Route templates are not in Microsoft's reference docs; they come from observed behaviour. Therefore: never write a tool against a guessed endpoint shape. Run pnpm probe first, read the real response from scratch/, then type the tool against that. A route that 404s in the probe is dropped, not shipped.

Auth model

  • Public first-party client 51f81489-12ee-4a9e-aaae-a2591f45987d, device-code delegated grant. No app registration, no admin consent (when the tenant allows this path).
  • Scope audience has a deliberate double slash: https://service.flow.microsoft.com//user_impersonation. Do not "fix" it.
  • Refresh token in .pa-token (0600, gitignored). Access tokens minted on demand, cached in-process, refreshed 60s early.
  • pnpm login re-runs the device flow (new machine / expired token / switch account).

Two-API design

src/client/flow-api.ts holds both FLOW_SERVICE_BASE (used) and POWER_PLATFORM_BASE (dormant, official). Personal flows are invisible to the official API — it needs Dataverse solution flows. Keep tool request shapes routed through flowRequest so retargeting is a base-URL change.

Conventions

  • ESM (NodeNext), strict, single quotes, semicolons, printWidth 100.
  • One tool per file in src/tools/, exporting xSchema (zod) + handleX.
  • Read tools set readOnlyHint. Write tools (create_or_update_flow, set_flow_state) require an explicit preview path first (dryRun default true / confirm required).
  • pnpm verify = check + lint + format:check + test. Run before calling done.

Scope (v1)

In: list environments, list/get flows, run history, run actions (debug), create/update flow definition, start/stop.

Read the full file on GitHub · 59 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. 10d ago First seen · 59 lines · 666 tokens per session scan A 56b258398e6d

Subscribe to this mod's changes

PowerAutomate_MCP CLAUDE.md is an instructions file published in the GitHub repository karenrebecag/PowerAutomate_MCP (1 stars, last pushed 2d ago), licensed MIT. It adds 666 tokens to every session, about $0.0033 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 2026-08-31.

Microsoft-Graphai-toolsclaudemcpmodel-context-protocoloauth2
Related

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens