Skip to main content
Glama

Power Automate MCP Server by Flow Studio

by io.github.ninihen1
OverviewDiscussionsAdmin

get_live_flow_run_action_outputs

Read-only

Read the recorded inputs and outputs of actions in one flow run. Without actionName: the top-level actions (optionally filtered by name). With actionName: every execution of that action across foreach iterations, each with repetitionIndexes, status, error, and resolved inputs/outputs. Use iterationIndex to pin one iteration; omit it for all. TRIGGER PAYLOADS: set trigger=true with a runName to get that run's trigger inputs and outputs. No Compose workaround is needed. TRIGGER CHECKS: pass checkId (from get_live_flow_runs -> triggerChecks.recent[].checkId) to read a trigger evaluation that never became a run — that is how you see WHY a trigger is failing. Do not supply runName with a checkId.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNoMax actions or repetitions to return. Paginates automatically. Omit for all.
checkIdNoTrigger check id (checkId from get_live_flow_runs -> triggerChecks). Returns that check's inputs/outputs, including the failure reason. Not a run id — the two are different, which is why a check id returns WorkflowRunNotFound from the run tools.
runNameNoRun identifier (name field from get_live_flow_runs). Required unless checkId is given.
triggerNoReturn the RUN's trigger inputs/outputs instead of its actions. Requires runName.
flowNameYesName (ID) of the flow.
actionNameNoAction name. Without iterationIndex: returns all repetitions of this action across every foreach iteration. With iterationIndex: returns the single repetition matching that iteration. Omit entirely for top-level action list.
iterationIndexNoZero-based foreach iteration index. Matched against the innermost repetitionIndexes[].itemIndex in the PA repetition record. Only meaningful when actionName is also set.
environmentNameYesName of the Power Platform environment.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / checkId
      Added value: +{
+  "description": "Trigger check id (checkId from get_live_flow_runs -> triggerChecks). Returns that check's inputs/outputs, including the failure reason. Not a run id — the two are different, which is why a check id returns WorkflowRunNotFound from the run tools.",
+  "type": "string"
+}
    • changedInput schema / properties / runName / description
      Previous value: -"Run identifier (name field from get_live_flow_runs)."New value: +"Run identifier (name field from get_live_flow_runs). Required unless checkId is given."
    • addedInput schema / properties / trigger
      Added value: +{
+  "description": "Return the RUN's trigger inputs/outputs instead of its actions. Requires runName.",
+  "type": "boolean"
+}
    • changedInput schema / required
      Previous value: -[
-  "environmentName",
-  "flowName",
-  "runName"
-]New value: +[
+  "environmentName",
+  "flowName"
+]
  2. First observed

TDQS

A5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag this as read-only and non-destructive, and the description adds meaningful behavioral detail beyond that: it explains that a checkId is not a run id and would otherwise return WorkflowRunNotFound, how repetitions are surfaced, and how trigger evaluations that never became runs can be inspected. It also clarifies the return contents such as status, error, and resolved inputs/outputs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-organized, with clear mode labels and front-loaded purpose. Despite the length, each sentence contributes necessary usage detail; the structured breaks for trigger payloads and trigger checks make the complexity navigable rather than overwhelming.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the burden of explaining return behavior. It does so well: it names the per-repetition fields, explains trigger input/output returns, describes how to retrieve failed trigger checks, and connects to get_live_flow_runs for obtaining checkId and runName. Given the tool's complexity, this is unusually complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the input schema already documents all 8 parameters at 100% coverage, the description adds crucial cross-parameter semantics: actionName and iterationIndex interaction, runName required unless checkId is supplied, trigger requiring runName, and the checkId provenance. These relationships are not obvious from the schema alone and materially improve correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Read the recorded inputs and outputs of actions in one flow run.' It then clearly distinguishes the main modes (top-level actions, per-action repetitions, trigger payloads, trigger checks), making it easy for an agent to tell this from siblings like get_live_flow_runs or get_live_flow_run_error.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit conditional guidance: when to omit actionName, when to provide iterationIndex, when to use trigger=true, and when to pass checkId instead of runName. It even states the exclusion directly: 'Do not supply runName with a checkId.' This is strong when-to-use versus when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Power Automate MCP Server by Flow Studio toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources