Power Automate Debugging with FlowStudio MCP

Source of Truth

Always call tools/list first to confirm available tool names and their parameter schemas. Tool names and parameters may change between server versions. This skill covers response shapes, behavioral notes, and diagnostic patterns — things tools/list cannot tell you. If this document disagrees with tools/list or a real API response, the API wins.

Python Helper

import json, urllib.request

MCP_URL   = "https://mcp.flowstudio.app/mcp"
MCP_TOKEN = "<YOUR_JWT_TOKEN>"

def mcp(tool, **kwargs):
    payload = json.dumps({"jsonrpc": "2.0", "id": 1, "method": "tools/call",
                          "params": {"name": tool, "arguments": kwargs}}).encode()
    req = urllib.request.Request(MCP_URL, data=payload,
        headers={"x-api-key": MCP_TOKEN, "Content-Type": "application/json",
                 "User-Agent": "FlowStudio-MCP/1.0"})
    try:
        resp = urllib.request.urlopen(req, timeout=120)
    except urllib.error.HTTPError as e:
        body = e.read().decode("utf-8", errors="replace")
        raise RuntimeError(f"MCP HTTP {e.code}: {body[:200]}") from e
    raw = json.loads(resp.read())
    if "error" in raw:
        raise RuntimeError(f"MCP error: {json.dumps(raw['error'])}")
    return json.loads(raw["result"]["content"][0]["text"])

ENV = "<environment-id>"   # e.g. Default-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx

Step 1 — Locate the Flow

result = mcp("list_live_flows", environmentName=ENV)
# Returns a wrapper object: {mode, flows, totalCount, error}
target = next(f for f in result["flows"] if "My Flow Name" in f["displayName"])
FLOW_ID = target["id"]   # plain UUID — use directly as flowName
print(FLOW_ID)

Step 2 — Find the Failing Run

runs = mcp("get_live_flow_runs", environmentName=ENV, flowName=FLOW_ID, top=5)
# Returns direct array (newest first):
# [{"name": "08584296068667933411438594643CU15",
#   "status": "Failed",
#   "startTime": "2026-02-25T06:13:38.6910688Z",
#   "endTime": "2026-02-25T06:15:24.1995008Z",
#   "triggerName": "manual",
#   "error": {"code": "ActionFailed", "message": "An action failed..."}},
#  {"name": "...", "status": "Succeeded", "error": null, ...}]

for r in runs:
    print(r["name"], r["status"], r["startTime"])

RUN_ID = next(r["name"] for r in runs if r["status"] == "Failed")

Step 3 — Get the Top-Level Error

CRITICAL: get_live_flow_run_error tells you which action failed. get_live_flow_run_action_outputs tells you why. You must call BOTH. Never stop at the error alone — error codes like ActionFailed, NotSpecified, and InternalServerError are generic wrappers. The actual root cause (wrong field, null value, HTTP 500 body, stack trace) is only visible in the action's inputs and outputs.

err = mcp("get_live_flow_run_error",
    environmentName=ENV, flowName=FLOW_ID, runName=RUN_ID)
# Returns:
# {
#   "runName": "08584296068667933411438594643CU15",
#   "failedActions": [
#     {"actionName": "Apply_to_each_prepare_workers", "status": "Failed",
#      "error": {"code": "ActionFailed", "message": "An action failed..."},
#      "startTime": "...", "endTime": "..."},
#     {"actionName": "HTTP_find_AD_User_by_Name", "status": "Failed",
#      "code": "NotSpecified", "startTime": "...", "endTime": "..."}
#   ],
#   "allActions": [
#     {"actionName": "Apply_to_each", "status": "Skipped"},
#     {"actionName": "Compose_WeekEnd", "status": "Succeeded"},
#     ...
#   ]
# }

# failedActions is ordered outer-to-inner. The ROOT cause is the LAST entry:
root = err["failedActions"][-1]
print(f"Root action: {root['actionName']} → code: {root.get('code')}")

# allActions shows every action's status — useful for spotting what was Skipped
# See common-errors.md to decode the error code.

Step 4 — Inspect the Failing Action's Inputs and Outputs

This is the most important step. get_live_flow_run_error only gives you a generic error code. The actual error detail — HTTP status codes, response bodies, stack traces, null values — lives in the action's runtime inputs and outputs. Always inspect the failing action immediately after identifying it.

# Get the root failing action's full inputs and outputs
root_action = err["failedActions"][-1]["actionName"]
detail = mcp("get_live_flow_run_action_outputs",
    environmentName=ENV,
    flowName=FLOW_ID,
    runName=RUN_ID,
    actionName=root_action)

out = detail[0] if detail else {}
print(f"Action: {out.get('actionName')}")
print(f"Status: {out.get('status')}")

# For HTTP actions, the real error is in outputs.body
if isinstance(out.get("outputs"), dict):
    status_code = out["outputs"].get("statusCode")
    body = out["outputs"].get("body", {})
    print(f"HTTP {status_code}")
    print(json.dumps(body, indent=2)[:500])

    # Error bodies are often nested JSON strings — parse them
    if isinstance(body, dict) and "error" in body:
        err_detail = body["error"]
        if isinstance(err_detail, str):
            err_detail = json.loads(err_detail)
        print(f"Error: {err_detail.get('message', err_detail)}")

# For expression errors, the error is in the error field
if out.get("error"):
    print(f"Error: {out['error']}")

# Also check inputs — they show what expression/URL/body was used
if out.get("inputs"):
    print(f"Inputs: {json.dumps(out['inputs'], indent=2)[:500]}")

What the action outputs reveal (that error codes don't)

Example: HTTP action returning 500

Error code: "InternalServerError" ← this tells you nothing

Action outputs reveal:
  HTTP 500
  body: {"error": "Cannot read properties of undefined (reading 'toLowerCase')
    at getClientParamsFromConnectionString (storage.js:20)"}
  ← THIS tells you the Azure Function crashed because a connection string is undefined

Example: Expression error on null

Error code: "BadRequest" ← generic

Action outputs reveal:
  inputs: "body('HTTP_GetTokenFromStore')?['token']?['access_token']"
  outputs: ""   ← empty string, the path resolved to null
  ← THIS tells you the response shape changed — token is at body.access_token, not body.token.access_token

Step 5 — Read the Flow Definition

defn = mcp("get_live_flow", environmentName=ENV, flowName=FLOW_ID)
actions = defn["properties"]["definition"]["actions"]
print(list(actions.keys()))

Find the failing action in the definition. Inspect its inputs expression to understand what data it expects.

Step 6 — Walk Back from the Failure

When the failing action's inputs reference upstream actions, inspect those too. Walk backward through the chain until you find the source of the bad data:

# Inspect multiple actions leading up to the failure
for action_name in [root_action, "Compose_WeekEnd", "HTTP_Get_Data"]:
    result = mcp("get_live_flow_run_action_outputs",
        environmentName=ENV,
        flowName=FLOW_ID,
        runName=RUN_ID,
        actionName=action_name)
    out = result[0] if result else {}
    print(f"\n--- {action_name} ({out.get('status')}) ---")
    print(f"Inputs:  {json.dumps(out.get('inputs', ''), indent=2)[:300]}")
    print(f"Outputs: {json.dumps(out.get('outputs', ''), indent=2)[:300]}")

⚠️ Output payloads from array-processing actions can be very large. Always slice (e.g. [:500]) before printing.

Tip: Omit actionName to get ALL actions in a single call. This returns every action's inputs/outputs — useful when you're not sure which upstream action produced the bad data. But use 120s+ timeout as the response can be very large.

Step 7 — Pinpoint the Root Cause

Expression Errors (e.g. split on null)

If the error mentions InvalidTemplate or a function name:

1. Find the action in the definition
2. Check what upstream action/expression it reads
3. Inspect that upstream action's output for null / missing fields

# Example: action uses split(item()?['Name'], ' ')
# → null Name in the source data
result = mcp("get_live_flow_run_action_outputs", ..., actionName="Compose_Names")
if not result:
    print("No outputs returned for Compose_Names")
    names = []