{
  "listings": [
    {
      "slug": "activepieces",
      "name": "Activepieces API + MCP",
      "company": "Activepieces Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "ap_list_runs and ap_get_run give per-step outputs, errors and durations, ap_list_connections shows ERROR status, and ap_retry_run FROM_FAILED_STEP keeps earlier outputs. No idempotency key, and docs don't say what a failed loop step repeats. Run data is kept 30 days.",
      "source": "https://www.activepieces.com/docs/mcp/tools.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/activepieces"
    },
    {
      "slug": "copilot-studio-mcp",
      "name": "Microsoft Copilot Studio MCP",
      "company": "Microsoft Corporation",
      "grade": "D",
      "fit": "caveat",
      "why": "list_runs, get_run, list_run_actions, get_run_action_content and inspect_run read per-action detail, but there is no resubmit or retry action, and the README says never to retry an uncertain write automatically.",
      "source": "https://registry.npmjs.org/@microsoft/copilot-studio-mcp/-/copilot-studio-mcp-1.0.4.tgz",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/copilot-studio-mcp"
    },
    {
      "slug": "gumloop",
      "name": "Gumloop",
      "company": "AgentHub Inc. (doing business as Gumloop)",
      "grade": "C",
      "fit": "caveat",
      "why": "Retrieve session returns messages and state, and get_run_history is an MCP tool, but no retry or resume endpoint is documented, so recovery is a new session that may repeat writes.",
      "source": "https://docs.gumloop.com/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/gumloop"
    },
    {
      "slug": "kestra",
      "name": "Kestra",
      "company": "Kestra Technologies SAS",
      "grade": "C",
      "fit": "caveat",
      "why": "GET /executions/{id} plus actions/restart (failed tasks, chosen revision) and actions/replay from a task run id cover diagnosis and recovery, but no idempotency key, so a partly written failed task repeats.",
      "source": "https://kestra.io/kestra.yml",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/kestra"
    },
    {
      "slug": "kognitos",
      "name": "Kognitos",
      "company": "Kognitos, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Runs, run events and exceptions with troubleshooting guides name the failure, and :replay reuses recordings of completed book calls rather than repeating them. Replay works only for single-phase (Main) automations and takes updated code.",
      "source": "https://docs.kognitos.com/guides/mcp/mcp.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/kognitos"
    },
    {
      "slug": "make",
      "name": "Make API + MCP",
      "company": "Celonis, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Execution details, module logs and incomplete executions (bundles, failed blueprint, resolve attempts) name the failing module. Replay reruns the latest scenario with the original data, repeating earlier writes, and no idempotency key is documented.",
      "source": "https://developers.make.com/api-documentation/api-reference/scenarios/logs.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/make"
    },
    {
      "slug": "n8n",
      "name": "n8n API + MCP",
      "company": "n8n GmbH",
      "grade": "D",
      "fit": "caveat",
      "why": "Executions keep per-node data (acc-01) and the retry POST takes an Idempotency-Key, but both execution retry and Retry On Fail resent 49 delivered emails, the latter showing success (acc-31).",
      "source": "https://docs.n8n.io/connect/connect-to-n8n-mcp-server/mcp-server-tools-reference.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/n8n"
    },
    {
      "slug": "paragon",
      "name": "Paragon ActionKit + MCP",
      "company": "Forge Technology, Inc. (d/b/a Paragon)",
      "grade": "D",
      "fit": "caveat",
      "why": "The Task History API lists executions by user, workflow and FAILED status, but per-step input and output and a replay call aren't in it, and auto-retry repeats a whole step.",
      "source": "https://docs.useparagon.com/apis/task-history.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/paragon"
    },
    {
      "slug": "pipedream",
      "name": "Pipedream API + MCP",
      "company": "Pipedream, LLC",
      "grade": "BB",
      "fit": "caveat",
      "why": "Event history exists for Workflows until shutdown, but action runs have no idempotency and acc-30 records a timed-out SSH write that left a file with the wrong checksum.",
      "source": "https://pipedream.com/docs/llms.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/pipedream"
    },
    {
      "slug": "power-automate",
      "name": "Microsoft Power Automate",
      "company": "Microsoft Corporation",
      "grade": "C",
      "fit": "caveat",
      "why": "FlowRun gives each run's status, trigger type, error code and error message, but at run level, not per action, and no documented call resubmits a run.",
      "source": "https://learn.microsoft.com/en-us/power-automate/dataverse/cloud-flow-run-metadata",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/power-automate"
    },
    {
      "slug": "prismatic",
      "name": "Prismatic",
      "company": "Prismatic Software Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "replayExecution and bulkReplayExecutions re-run an execution, but they take no idempotency key and the docs read don't say whether completed steps repeat.",
      "source": "https://prismatic.io/docs/api/schema/mutations.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/prismatic"
    },
    {
      "slug": "tray",
      "name": "Tray.ai API + MCP",
      "company": "Tray.ai, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Headless lists a workflow's executions, reads one and drills into each step's input and output, but no replay or idempotency key appears in the pages read, so a re-fire repeats every step.",
      "source": "https://tray.ai/documentation/platform/tray-headless/headless-for-claude-code.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/tray"
    },
    {
      "slug": "windmill",
      "name": "Windmill API + MCP",
      "company": "Windmill Labs, Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "Runs show status, logs, inputs and steps, restart/f/{id} restarts a flow at a chosen step keeping earlier iterations, and a caller-supplied job_id refuses a duplicate. Whether per-step retry attempts are readable wasn't checked.",
      "source": "https://www.windmill.dev/docs/core_concepts/mcp.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/windmill"
    },
    {
      "slug": "workato",
      "name": "Workato API + MCP",
      "company": "Workato, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Get a job returns lines with each step's input, output and error. Repeat jobs reruns whole master jobs on the latest recipe version, 25 a call, with no idempotency key, so steps that succeeded repeat.",
      "source": "https://docs.workato.com/en/workato-api/jobs.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/workato"
    },
    {
      "slug": "bind-ai",
      "name": "Bind AI",
      "company": "1Fort Inc.",
      "grade": "F",
      "fit": "no",
      "why": "No run or execution history endpoint in the API definition.",
      "source": "https://api.1fort.com/api-docs/?format=openapi",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/bind-ai"
    },
    {
      "slug": "mandl-cooper",
      "name": "Cooper (Mandl)",
      "company": "Cooper AI Tech, Inc.",
      "grade": "F",
      "fit": "no",
      "why": "No run history is exposed outside the workspace.",
      "source": "https://www.askcooper.ai/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mandl-cooper"
    },
    {
      "slug": "motive-agents",
      "name": "Motive Agents",
      "company": "Motive Technologies, Inc.",
      "grade": "F",
      "fit": "no",
      "why": "No run history for Agents is exposed through the developer portal.",
      "source": "https://developer.gomotive.com/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/motive-agents"
    },
    {
      "slug": "node-red",
      "name": "Node-RED",
      "company": "OpenJS Foundation",
      "grade": "B",
      "fit": "no",
      "why": "No execution history, per-run data or retry in the Admin API; failures show only in logs and debug output.",
      "source": "https://nodered.org/docs/api/admin/methods/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/node-red"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 8,
    "after": [
      "workflow-automation.connect-app-accounts",
      "chat.report-to-user"
    ],
    "area": "business",
    "asks": [
      "why did last night's run fail",
      "retry the failed execution",
      "did the emails go out before it broke",
      "is my workflow still running"
    ],
    "before": [
      "workflow-automation.unattended-sync",
      "workflow-automation.run-workflow-as-tool"
    ],
    "blockers": [
      "retry re-sends items that already succeeded and reports success",
      "no idempotency key on run or retry",
      "error analysis tool invents an error on a successful run",
      "execution not saved for failed production runs by default"
    ],
    "capabilities": [
      "automation.workflows",
      "agent.tools"
    ],
    "category": "workflow-automation",
    "categoryName": "Workflow automation",
    "checked": "2026-11-15",
    "companies": {
      "fit": 0,
      "fitWithLimit": 13,
      "tagged": 47
    },
    "competition": "none",
    "fits": null,
    "fitsWithLimit": [
      "activepieces",
      "copilot-studio-mcp",
      "gumloop",
      "kestra",
      "kognitos",
      "make",
      "n8n",
      "paragon",
      "pipedream",
      "power-automate",
      "prismatic",
      "tray",
      "windmill",
      "workato"
    ],
    "id": "workflow-automation.debug-failed-run",
    "listings": {
      "caveat": 14,
      "no": 4,
      "notRead": 0,
      "tagged": 48,
      "unchecked": 0,
      "yes": 0
    },
    "name": "Find out why a run failed and recover it without repeating its effects",
    "status": "draft",
    "success": "The agent names the failing step and whether the failure is transient or a broken connection from logged attempt data, and a recovery run completes with zero duplicated external writes. Measured: this takes under 5 calls.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/workflow-automation.debug-failed-run.json",
    "weight": 13,
    "weightBasis": "8 of 48 accounts, all n8n (forum threads on retries and liveness, n8n-mcp executions tool, Hacker News); other listings unevidenced"
  }
}
