Skip to main content
Glama
736,842 tools. Updated 2026-11-02 16:19

"Rockwell Automation" matching MCP tools:

  • Compile an automation’s version and store the result so it can be switched on. It does NOT switch the automation on: set_automation_state does that. It requires a human confirmation round-trip: call it once WITHOUT confirmation_token, show the person which automation and version, and call it again with the token. version_id defaults to the newest version; confirm_actions names, one by one, each destructive action of the automation the person approved. Call validate_automation first: a deploy that fails to compile wastes the confirmation.
    ConnectorOAuth
  • Create a new automation DEFINITION for the authenticated user. The new automation is always created INACTIVE (a definition only) — it does NOT run, send, or activate. Use when the user wants to define a new automation by name. Do NOT use to activate, run, or wire the automation's step graph — activation is a separate, later capability and is not available here. Do NOT use to edit an existing automation — use mcp_crm_automations_update. The automation's status cannot be set via this tool. Tenant is bound to the session and cannot be changed via arguments. Automation-level RULES (all optional, and all independent of the step graph — use mcp_crm_automations_set_steps for that): entryConditions / exitConditions / restartConditions are arrays of {type, segmentId, operator, contactFilters, campaignIds, linkUrl} where type is one of added_to_lists, removed_from_lists, contact_in_segment, contact_matches_filters, email_opened, email_clicked, email_unsubscribed; a membership type needs segmentId, contact_matches_filters needs contactFilters, and the email types take optional campaignIds (plus linkUrl on email_clicked). operator is MATCHES or DOES_NOT_MATCH. Pass an EMPTY array to clear a slot; omit the key to leave it unchanged. reentryPolicy is once (a contact runs this automation at most once) or every_time, with reentryWaitMinutes as the cool-down before a contact may re-enter. onDeactivate is continue (in-flight contacts finish) or cancel (in-flight contacts are cancelled when a human deactivates the automation). Returns the created automation projection (id, name, status, rules, version).
    ConnectorOAuth
  • Check a supplied CSV before importing it into an HMI project. Use tags_csv for a supported FactoryTalk View tag export, digital_alarms_csv for a digital-alarm export, and analog_alarms_csv for an analog-alarm export; each argument is the complete CSV text and may be omitted when that export type is not being checked. The tool validates deterministic import contract rules such as the expected export version marker, record shape, required fields, addresses, alarm severity and analog threshold structure. It returns result (PASS, REVIEW_REQUIRED, or INSUFFICIENT_INPUT), issue_count, a list of issues with code/severity/message and row or record provenance when available, plus a summary by issue code. Use this tool for static import preflight only; it does not connect to any HMI or PLC and does not certify runtime or safety behavior. This is an independent compatibility check, not an official Rockwell Automation service.
    ConnectorNo auth
  • Check a supplied CSV before importing it into an HMI project. Use tags_csv for a supported FactoryTalk View tag export, digital_alarms_csv for a digital-alarm export, and analog_alarms_csv for an analog-alarm export; each argument is the complete CSV text and may be omitted when that export type is not being checked. The tool validates deterministic import contract rules such as the expected export version marker, record shape, required fields, addresses, alarm severity and analog threshold structure. It returns result (PASS, REVIEW_REQUIRED, or INSUFFICIENT_INPUT), issue_count, a list of issues with code/severity/message and row or record provenance when available, plus a summary by issue code. Use this tool for static import preflight only; it does not connect to any HMI or PLC and does not certify runtime or safety behavior. This is an independent compatibility check, not an official Rockwell Automation service.
    ConnectorNo auth
  • Start one of the user's automations now, the same as "Run now" in the web app. The AI agent then drives the automation's phones on its own; this returns the run at once with status "queued". Poll get-automation-run-tool with its `id` until `status` is done, failed or stopped, then read `outcome`, `result` and `phone_reports`. A run can be refused (the automation is off, a run is already going, the daily limit is reached, no phone is online, or the agent is unavailable); the error says which. A `tiktok_warmup` automation (see list-automations-tool) has no daily limit and starts one session per phone at once, so this returns the first one already "running" alongside `sessions`, the number started, and `skipped_busy_slots`, the phones left alone because another run already drives them; `payload` is ignored, it has no parameters.
    Connector
    Destructive
    OAuth
  • Change one seller-owned channel's saved listing scope. Read spellbook_inventory_management_get first. Switching legacy all mode to selected mode clears management for all current listings. On an eligible backfilled account, restore_legacy_all explicitly manages every current and future listing on that connected seller account; saved automation settings remain unchanged. In selected mode, use a named candidateId from current SpellBook Finance rows to manage or stop managing a complete listing. Stopping management leaves its live listing and order history intact. These actions save permission for existing automation and do not enable automation or publish a listing.
    Connector
    Destructive
    No auth

Matching MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    An MCP server for auditing automation health, finding failures, stale logs, and non-functional endpoints that report success while quietly failing.
    7
    MIT

Matching MCP Connectors

  • Check an automation document (ir) with Cosend’s compiler and return its full report: every error with a JSON pointer into the document and, where one exists, a fix you can apply. Nothing is written and nothing is deployed. Call it on EVERY draft and resolve every error before upsert_automation. id is the automation the draft belongs to; a brand-new automation gets its id from upsert_automation, which checks the document the same way. It needs the automations:write permission because it is the authoring tool, though it changes nothing.
    ConnectorOAuth
  • Permanently deletes an automation. Pauses any scheduled sends first, then removes the automation. Behavior: - DESTRUCTIVE and irreversible — the automation cannot be recovered. No undo. - Errors when the perspective or automation is not found, or you do not have access. Deleting an already-deleted automation errors as well. - If pausing the scheduled sender fails, the deletion is aborted and you'll get success: false with "Failed to stop running workflow. Please try again." — the automation stays intact in that case. When to use this tool: - The user explicitly asked to remove an automation and confirmed. - Cleaning up a misconfigured automation that automation_test repeatedly fails on. When NOT to use this tool: - The user just wants to pause it temporarily — use automation_update with { enabled: false } instead. - You're not sure which automation_id is correct — confirm via automation_list first.
    Connector
    Destructive
    OAuth
  • Postkey: Builds a new DRAFT Instagram DM automation from a template and returns its automation_id, for example comment-to-DM: send a link by DM when someone comments a keyword. It is made the same way as on Postkey's New automation screen. Use it for a new automation; to change one that exists use postkey_update_automation. It is not switched on: nobody gets a message until postkey_publish_automation (preview that first). Pass keyword and link_url when the template's needs_keyword or needs_link is true. The answer says back runs_on and followers_only (follow_note when follow-gated). Refused before anything is made: an X account or one not connected for DMs (invalid_arguments), and a follow-gated automation on a Facebook Page (not_on_this_network).
    ConnectorOAuth
  • Get Arcadia workflow guides and reference documentation. Call this before multi-step workflows (opening LP positions, enabling automation, closing positions) or when you need contract addresses, asset manager addresses, or strategy parameters. Topics: overview (addresses + tool catalog), automation (intent-based automation setup), strategies (step-by-step templates), selection (how to evaluate and parameterize strategies).
    ConnectorNo auth
  • List the authenticated user's automations. An automation is a saved task for the AI phone agent (`prompt`) that runs across one or more phones, on a schedule (`schedule_cron` in `timezone`), when its webhook is called, or on demand with run-automation-tool. Each run is followed with list-automation-runs-tool and get-automation-run-tool. `kind` is "prompt" for that, or "tiktok_warmup" for a TikTok account warm-up: its `settings` (niche, keywords, comment language, daily window, session counts and lengths) replace `prompt` and it has no `schedule_cron` — it plans and runs its own sessions every day on its own timetable, and run-automation-tool only ever starts an extra one now. Not the same as macros (list-macros-tool), which replay recorded input exactly with no AI. Automations are created and edited in the web app.
    ConnectorOAuth
  • Set up a Duvo Module (a ready-made solution such as AP Invoice Intake & Routing or Freight Audit) as a new Automation on the team, the same as pressing Set up on the Module in the web app. Creates the Module's Agents, code steps, Queues, Policy and dashboards in one call. If the team already has a demo of this Module open, the call is refused with 409 unless `convert_existing_demo` is true; then that demo becomes the Automation and its sample cases and Runs are deleted, so ask the user first. The Automation starts in setup and does not run yet: call `getAutomationReadiness` next to see what is left of the setup, the Policy questions, the current process and the automation proposal, whose approval builds the automation. Connections and routing come once the approved proposal is being built, so don't raise them before. Give the user the `url`.
    Connector
    Destructive
    No auth
  • Save a new automation as a draft: a trigger step, action steps, and connections between step keys. Saving runs nothing; steps run only after start-automation (for each matching event) or trigger-automation (one run). Each action does the same as one tool: send_email = send-email with a template, forward_email = forward-email, add_to_audience = add-audience-subscriber, remove_from_audience = remove-audience-subscriber, update_subscription = bulk-unsubscribe/resubscribe, edit_contact = update-contact, add_tag/remove_tag = add/remove-contact-tags, update_score = update-contact-score, create_contact = create-contact, add_to_suppressions = create-suppression, remove_from_suppressions = delete-suppression, exit_automation = remove-contact-from-automation. Steps that call webhooks can only be added in the dashboard or the REST API. Flow steps: wait, wait_until (date / event / condition, with timeout), condition, goal (runs jump to it when the contact meets it), experiment, run_automation (enter or move to another automation), end_run, end. settings.exit_conditions cancels a contact's run when an event or condition matches (e.g. a purchase). Plans: goal steps and custom events (contact.on_event in exits, goals and waits) need Pro or Business; the contact.on_event trigger needs Business (403 plan_required otherwise). Example "webinar": trigger contact.added_to_audience (registrants) -> wait_until date {type: "global", key: "webinar_date"} 1 day before -> send_email reminder -> wait_until date 1 hour before -> send_email; a goal on contact.on_event c:purchase -> add_tag customer -> exit_automation all -> run_automation onboarding; a separate automation on contact.score_changed threshold 50 starts the sales sequence.
    ConnectorAPI key
  • Sends up to five selected saved Automation email steps to one explicit test address. This does not start the Automation or run other actions. Effect: external-email. Retry with the same idempotency_key. Permissions: live_actions:write, subscribers:read, automations:write. API reference: https://mailrith.com/developers/api-reference.
    Connector
    Destructive
    No auth
  • Pause an automation (active=false) so it stops running and stops spending leads, or resume it (active=true). Pausing is the safe way to stop an automation you might want back — use delete_automation only when the user wants it gone for good.
    ConnectorNo auth
  • Set the account’s default marketing-automation destination list by a resolved list_id from search_ma_lists. The default affects newly created campaign channels; existing channels retain their captured values. Returns the updated setting or a failure such as PERMISSION_DENIED or DISCONNECTED. Account marketing-automation write access is required.
    ConnectorAPI key
  • List automation runs, newest first. Filter by automation template, status, or a created_at window to find a run that stalled or errored, then read its steps with list_automation_run_steps. Journey runs are listed by list_journey_runs instead.
    ConnectorNo auth
  • Retrieve command-by-command screenshots captured during a test session. Returns screenshot URLs for each step. Web automation (Selenium, Playwright, Cypress) only: an app automation session returns not found; listMobileSessions carries the video and screenshot links of app sessions.
    ConnectorOAuth
  • Retrieve the video recording URL for a completed test session. Web automation (Selenium, Playwright, Cypress) only: an app automation session returns not found; listMobileSessions carries the video and screenshot links of app sessions.
    ConnectorOAuth