agentmods.dev

power-automate-mcp

power-automate-mcp is a skill for Claude Code, Codex from kaael1/mcp-power-automate. It costs 46 tokens per session (1,188 once invoked), scanned A, original, MIT.

A guide for using a local connection to Microsoft Power Automate, a service for building automated workflows. It covers inspecting, checking, changing, running, and undoing changes to flows.

In plain words
What is it for?
Connecting to Power Automate flows, reading their setup, previewing and applying small edits, testing them, checking results, and reverting the latest change.
Why use it?
It provides a defined process for working safely with flows, including reviewing changes and validating them before and after saving.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 28repo +1 5mo ago A scan 46 tokens original MIT

Good fit Connecting to Power Automate flows, reading their setup, previewing and applying small edits, testing them, checking results, and reverting the latest change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kaael1/mcp-power-automate/power-automate-mcp
View source ↗ kaael1/mcp-power-automate
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kaael1/mcp-power-automate --skill power-automate-mcp
Clone the repo
git clone --depth 1 https://github.com/kaael1/mcp-power-automate

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/kaael1/mcp-power-automate/power-automate-mcp/github.svg)](https://agentmods.dev/skills/kaael1/mcp-power-automate/power-automate-mcp)
Your own site
<a href="https://agentmods.dev/skills/kaael1/mcp-power-automate/power-automate-mcp"><img src="https://agentmods.dev/badge/skills/kaael1/mcp-power-automate/power-automate-mcp/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kaael1/mcp-power-automate/power-automate-mcp"><img src="https://agentmods.dev/badge/skills/kaael1/mcp-power-automate/power-automate-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,188 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 $0.00046 $0.01188
Opus 5.5 $0.00018 $0.00475
Sonnet 5.5 $0.00009 $0.00238
Haiku 4.5 $0.00005 $0.00119

Measured 2mo ago against content hash 31a6ebce2e9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

power-automate-mcp 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 2mo 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.

skills/power-automate-mcp/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power Automate MCP

Use this skill when the user wants AI help with Microsoft Power Automate flows through the local MCP server and Chromium extension from this repository.

The extension is a passive capture and status surface. Do not ask the user to click extension buttons to make normal MCP work proceed. The AI should operate through MCP tools.

Provider notes live in references/providers.md.

Operating Rules

  1. Start with doctor or get_context.
  2. Use connect_flow when the target is not already explicit.
  3. Prefer browser-captured flows, explicit flowId, or a narrow nameQuery; if connect_flow returns candidates, choose by flowId or ask the user which flow is intended.
  4. Call get_flow before edits.
  5. Call preview_flow_update before saving.
  6. Call validate_flow before and after save when available.
  7. Call apply_flow_update only for the smallest intended change.
  8. Call get_last_update after save and summarize the review diff.
  9. Use revert_last_update if the saved result is wrong.
  10. Prefer test or staging flows before production flows.

Inspection

  1. doctor
  2. get_context
  3. connect_flow if needed
  4. get_flow
  5. list_runs or get_latest_run if run history matters
  6. get_run_actions when a run needs action-level triage

Solution Work

Use solution write tools only for unmanaged solutions and only when adding cloud flows is the intended change.

  1. doctor
  2. get_context
  3. Confirm canManageSolutions.available is true, or follow its reason before retrying.
  4. list_solutions
  5. list_solution_components when a specific solution needs component inventory.
  6. list_environment_variables when environment variable definitions or current values matter.
  7. add_flow_to_solution for an existing flow, or create_flow_in_solution when a new blank flow should be created and added.

Safe Edit

  1. doctor
  2. connect_flow
  3. get_flow
  4. Build the smallest candidate flow change.
  5. preview_flow_update
  6. validate_flow
  7. apply_flow_update
  8. get_last_update
  9. validate_flow again when available

Read the full file on GitHub · 123 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 123 lines · 46 tokens per session scan A 31a6ebce2e9a

Subscribe to this mod's changes

power-automate-mcp is a skill published in the GitHub repository kaael1/mcp-power-automate (28 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 1,188 once invoked, about $0.0002 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.

Productivityautomationbrowser-extensioncodexmcpmodel-context-protocolpower-automate
Related

Other skills, from other repositories

automation-strategy

Use when deciding whether a process is worth automating, sizing ROI and build-vs-buy, choosing an automation platform, or diagnosing why a fleet of automations keeps breaking — the decision layer before anyone builds. NOT building the flow (that is automation-flows, or n8n / make / zapier / power-automate to drive a…

ericrisco/rsc-harness · 86 tokens

harness-design-fuzzing

Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…

provos/ironcurtain · 147 tokens

disk-cleanup

Use when the Mac is low on disk or before a build/release/large-media job, to find where space went and reclaim it safely in tiers. Triggers on "disk is full", "free up space", "out of disk", low-free-space warnings, or at session start before heavy work. Measures first, then deletes only regenerable/settled pools…

mtarcure/claude-vibe-squad · 92 tokens

email-formatting

Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.

provos/ironcurtain · 53 tokens

compact-now

Operator-triggered proactive compaction — Chrono externalizes load-bearing state (active decisions, open tasks, next action) to a snapshot + a durable Vault learning note before invoking Claude Code's native /compact, then resumes from the snapshot. Use when the operator says "/compact-now" / "compact now" or when…

mtarcure/claude-vibe-squad · 82 tokens

json-schema-emails

Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.

provos/ironcurtain · 62 tokens