power-automate-mcp-server: Instructions file for Claude Code

CLAUDE.md

power-automate-mcp-server CLAUDE.md is an instructions file for Claude Code from sapientsai/power-automate-mcp-server. It costs 1,831 tokens per session, scanned A, original, MIT.

A set of instructions for Claude Code while working on an MCP server that manages Microsoft Power Automate cloud flows. Power Automate is Microsoft's service for automating tasks and business processes.

In plain words
What is it for?
Use it when managing, inspecting, debugging, enabling, disabling, or cautiously creating and updating Power Automate flows through the server.
Why use it?
It records the project's architecture, fixed design decisions, and limits so code changes follow the intended setup.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is sapientsai/power-automate-mcp-server's own configuration. It tells Claude Code how to work on power-automate-mcp-server 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 power-automate-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sapientsai/power-automate-mcp-server. 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/sapientsai/power-automate-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sapientsai/power-automate-mcp-server

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 power-automate-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sapientsai/power-automate-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/sapientsai/power-automate-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sapientsai/power-automate-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sapientsai/power-automate-mcp-server/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 power-automate-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sapientsai/power-automate-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sapientsai/power-automate-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,831 This file is loaded in full into every session.
When invoked 1,831 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 $0.01831 $0.01831
Opus 5 $0.00915 $0.00915
Sonnet 5 $0.00366 $0.00366
Haiku 4.5 $0.00183 $0.00183

Measured 10d ago against content hash a0086508b059, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

power-automate-mcp-server 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 · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository.

What this is

power-automate-mcp-server — an MCP server to manage and (lightly) author Microsoft Power Automate cloud flows from an agent context. Built on SomaMCP (over FastMCP), TypeScript, pnpm, tsdown, vitest, functype, zod v4.

Primary surface is management (list/inspect/debug/enable-disable/owners). Flow authoring (create_flow/update_flow/delete_flow) was originally a v2 non-goal but is now implemented and verified — gated behind ENABLE_WRITE_OPS, with delete_flow requiring confirm=true. The visual designer is still the better authoring surface for complex definitions; these tools emit the raw workflow-definition JSON, so prefer get_flow-as-template + targeted edits.

  • Spec: the build spec lives in the project history / Civala memory (~/.claude/projects/-Users-jordanburke-IdeaProjects-Civala/memory/project_power_automate_mcp.md).
  • Design references: ../somamcp (framework), ../microsoft-mcp-server (sibling patterns — but note its auth is app-only/FastMCP-OAuth, not device-code).

Key decisions (locked)

  • Backend: v1 targets api.flow.microsoft.com (unofficial, full reach incl. personal flows, no Premium needed). Dataverse backend is stubbed (src/backend/dataverse/README.md). The FlowBackend interface (src/backend/index.ts) is the seam — renamed from "BackendAdapter" to avoid colliding with SomaMCP's own BackendAdapter.
  • Auth: net-new MSAL device-code token manager behind a getToken seam (src/auth/token-manager.ts). v1 = interactive (device-code, stdio) primary + clientCredentials (app-only) secondary. v2 = FastMCP AzureProvider HTTP per-user OAuth (FastMCP exposes the upstream token on the session; reachable via SomaMCP backendOptions passthrough — no fork). The Flow API client depends only on getToken, so v2 is a drop-in.
  • No default client idAZURE_CLIENT_ID is required (README documents registration).
  • Tenant default: common. Package: public, unscoped power-automate-mcp-server.
  • functype ^1.2.0, somamcp ^1.0.9, @azure/msal-node ^5.2.2, zod ^4.4.3.
  • Node 24 in .nvmrc + CI (OIDC trusted publishing needs npm 11.5.1+, which ships with Node 24). The npm@latest workaround was removed from publish.yml.

Read the full file on GitHub · 113 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 · 113 lines · 1,831 tokens per session scan A a0086508b059

Subscribe to this mod's changes

power-automate-mcp-server CLAUDE.md is an instructions file published in the GitHub repository sapientsai/power-automate-mcp-server (2 stars, last pushed 25d ago), licensed MIT. It adds 1,831 tokens to every session, about $0.0092 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.

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

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

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