MCP Power Automate
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| POWER_AUTOMATE_BRIDGE_PORT | No | The port for the local HTTP bridge | 17373 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_contextB | Return the current Power Automate context, capabilities, selection, and cached summaries. |
| doctorA | Return bridge identity, diagnostics, public command names, and current Power Automate readiness. |
| connect_flowC | Connect the MCP to a flow using flowId, tabId, or nameQuery. Returns candidates if the request is ambiguous. |
| list_flowsC | List flows from live catalog plus browser-captured flows in the current environment. |
| list_solutionsB | List visible Dataverse solutions in the current or provided environment without changing them. |
| list_solution_componentsB | List Dataverse solution components for a solution unique name without changing them. |
| list_environment_variablesC | List Dataverse environment variable definitions and current values without changing them. |
| add_flow_to_solutionC | Add an existing cloud flow to an unmanaged Dataverse solution. |
| get_flowC | Fetch the selected Power Automate flow target and return a normalized editable payload. |
| preview_flow_updateA | Preview a flow edit without saving it, returning the proposed review diff and summary. |
| validate_flowC | Validate a flow definition using the flow service validation API when available. |
| apply_flow_updateC | Apply a flow edit and return the saved flow plus the persisted review diff. |
| get_last_updateA | Return the last successful flow update recorded by the local bridge. |
| revert_last_updateC | Revert the selected flow target to the last recorded before-state. |
| list_runsC | List recent runs for the selected flow target. |
| get_latest_runC | Return the most recent run for the selected flow target. |
| get_runA | Return details for a specific run of the selected flow target. |
| get_run_actionsC | Return action-level statuses for a specific run of the selected flow target. |
| wait_for_runB | Poll the latest run or a specific run until it reaches a terminal status or timeout. |
| get_trigger_callback_urlC | Return the callback URL for the selected flow trigger when it supports manual invocation. |
| invoke_triggerC | Invoke the selected flow trigger using its callback URL when it supports manual execution. |
| create_flowC | Create a new blank flow in the current environment and connect it as the active target. |
| create_flow_in_solutionB | Create a new blank flow in the current environment, add it to an unmanaged solution, and connect it as the active target. |
| clone_flowC | Clone an existing flow inside the current environment and optionally connect the clone. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| power-automate-context | Current Power Automate context, capabilities, and cached summaries. |
| power-automate-last-run | Last cached run summary for the connected flow. |
| power-automate-last-update | Last cached update summary for the connected flow. |
TDQS
Scored across 24 tools
All tools have distinct purposes. Even similar tools like preview_flow_update and apply_flow_update are clearly differentiated by their descriptions (preview vs. apply). No ambiguity.
Every tool follows a consistent verb_noun pattern in snake_case (e.g., add_flow_to_solution, list_flows, invoke_trigger). No mixed conventions or vague naming.
With 24 tools, the server is on the heavy side of the acceptable range. While each tool serves a specific function, the count feels slightly high for a single domain, though still workable.
The tool set covers flow creation, editing, validation, runs, triggers, solutions, and environment variables. A notable gap is the absence of a delete or remove flow tool, which agents may need.