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.
npx skills add prasadgd9022/power-automate-mcp --skill local-power-automate-mcpgit clone --depth 1 https://github.com/prasadgd9022/power-automate-mcpWrote 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.
[](https://agentmods.dev/skills/prasadgd9022/power-automate-mcp/local-power-automate-mcp)<a href="https://agentmods.dev/skills/prasadgd9022/power-automate-mcp/local-power-automate-mcp"><img src="https://agentmods.dev/badge/skills/prasadgd9022/power-automate-mcp/local-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.
<a href="https://agentmods.dev/skills/prasadgd9022/power-automate-mcp/local-power-automate-mcp"><img src="https://agentmods.dev/badge/skills/prasadgd9022/power-automate-mcp/local-power-automate-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00171 | $0.02718 |
| Opus 5 | $0.00086 | $0.01359 |
| Sonnet 5 | $0.00034 | $0.00544 |
| Haiku 4.5 | $0.00017 | $0.00272 |
Grade A, and why
local-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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Power Automate MCP — Privacy-First Foundation
This skill is the self-hosted counterpart to hosted Power Automate MCP offerings. It connects an agent to a local stdio MCP server that talks directly to Microsoft's own APIs using the operator's existing Azure identity, so tenant flow data never transits a third-party cloud.
When to prefer this over a hosted MCP: regulated tenants, data-residency or data-sovereignty requirements, air-gapped/BYO-identity policies, or anyone who simply does not want an external vendor brokering their Power Platform traffic. If a hosted MCP is acceptable, the
flowstudio-power-automate-*skills cover that path.
Requires:
- Python 3.10+ on
PATH- Azure CLI installed and signed in (
az login)- The reference server (
server.py) cloned locally —git clone https://github.com/prasadgd9022/power-automate-mcp- Python packages:
mcp,azure-identity,requests
Why This Is Different (Trust & Data-Flow Model)
| Dimension | Hosted MCP (e.g. FlowStudio) | This local server |
|---|---|---|
| Where it runs | Vendor cloud, remote HTTP endpoint | Your machine, stdio subprocess of the host |
| Auth | Portal-issued JWT via x-api-key header |
Your az login session (Azure CLI credential) |
| Identity used | Service/API-key identity | The signed-in user's own identity + RBAC |
| Data path | Tenant data traverses the vendor's cloud | Direct to api.flow.microsoft.com + Dataverse over HTTPS |
| Subscription | Paid tiers | None — open source (MIT) |
| Write safety | (host-defined) | confirm=True dry-run guard on Dataverse writes |
Design rule: nothing runs at import time. The server starts instantly and
only acquires a token on the first tool call — so registration succeeds even
before az login, and an auth failure is always a sign-in issue, never a setup
issue.
Auth Model — az login, Not API Keys
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.
- 11d ago First seen · 259 lines · 171 tokens per session scan A e4702489aad1
local-power-automate-mcp is a skill published in the GitHub repository prasadgd9022/power-automate-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 171 tokens to every session and 2,718 once invoked, about $0.0009 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.