Microsoft Copilot Studio MCP vs Microsoft Power Automate

Microsoft Copilot Studio MCP

Entra sign-in with per-resource scopes, tokens kept only in memory, and a plan-then-confirm step before connector writes. The package is a day old, the linked MIT repository holds no source, no changelog or support channel exists, the five cloud tools' schemas are visible only after sign-in, and workflow tests run live workflows billed in Copilot Credits.

Microsoft Power Automate

Cloud flows in a solution are rows an agent can read and write through the Dataverse Web API under Entra ID OAuth and security roles, with published limits and a 99.9 per cent SLA. Flows under My flows can't be managed in code, a flow's body is one hand-built JSON string, and setup needs a tenant administrator.

Microsoft Copilot Studio MCP

1. Call copilot_studio_status first and reuse a ready session. Don't reconnect or reselect an environment to start a new task
2. Read an action's contract with discover_resources and action=describe_actions before building unfamiliar parameters
3. Ask the person before testing a workflow. Tests run published, enabled workflows and can have real effects
4. Never retry an uncertain write. Inspect the agent, workflow or connection first, as the error text says
5. Expect a browser sign-in after every restart. Tell the person a window is opening and never ask for credentials in chat

Microsoft Power Automate

1. Filter workflows on category eq 5 for cloud flows, and add $select, because clientdata holds the whole definition
2. Flows created through the API start with statecode 0 (off). The docs say to turn the flow on before use
3. Put the flow in a solution first. Flows that sit only under My flows are outside the supported API
4. On 429 wait the Retry-After seconds. Reads of flowruns count against the daily Power Platform request allowance
5. Treat an HTTP trigger URL with sig= as a secret, and prefer the tenant or named-user trigger modes with a bearer token for https://service.flow.microsoft.com/