Connect Cargo to an external system and find out what it can do — authenticate connectors, browse the integration catalog, and resolve the `connectorUuid` and `actionSlug` a workflow node needs. Triggers: "connect my HubSpot", "is Salesforce connected", "what integrations do you support", "can Cargo

Cargo CLI — Connections Connector and integration management: listing connectors, discovering available integrations, and managing authenticated connector instances. See references/response shapes.md for full JSON response structures. See references/troubleshooting.md for common errors and how to fix them. See references/examples/connectors.md for connector CRUD and discovery examples. See references/examples/integrations.md for listing available integrations and OAuth flows. For third party connector rate limit handling and retry config in workflows, see cargo orchestration/references/polling.md and cargo orchestration/references/troubleshooting.md . Native integrations do not have rate limits. Bootstrap Already signed in ( cargo ai whoami returns a workspace)? Skip to the next section. Every command prints JSON to stdout; failures exit non zero with {"errorMessage": "..."} . Anything that creates a run or a batch is async — pass wait until finished or poll the matching get . When the full skill bundle is installed, [ ../cargo/references/prerequisites.md ](../cargo/references/prerequisites.md) adds the CLI version pin, token scopes, and the admin only surface. Key concepts Integration: The external service type (e.g. HubSpot, Clearbit, Salesforce). Integrations define what actions are available. Connector: An authenticated instance of an integration. One integration can have multiple connectors (e.g. two different HubSpot accounts). Connectors are what you reference in workflow node graphs. Discover resources first Looking for an action? Search for it — don't browse the catalog. Two keyword searches cover the whole surface, and both beat paging integration list or reading a whole integration get payload: Reach for the catalog commands when you need the integration , not an action — its auth fields, its extractors, or the full input schema of an action you have already picked: Deprecated integrations are hidden from the catalog by default. integration list , action list and action search leave them out unless you pass is deprecated true ; integration get <slug always returns one, with isDeprecated: true and a display name ending in (deprecated) . They cannot be connected any more. Existing connectors keep working, but never wire a new workflow to one. Two were deprecated in CLI 1.0.92, the self referential cargo integration among them. Read the flag rather than keeping a list: check isDeprecated before proposing any integration you found by browsing instead of by action list . Which action search? orchestration action list connection action search Covers connector, native, tools, agents connector catalog only Returns a runnable action object with connectorUuid , workspace connectors, credits , autocompletes integrationSlug + actionSlug , category, credits — you assemble the action yourself Filters kind , integration slug , category , is deprecated , limit category , integration , credits only , is deprecated , limit Needs CLI ≥ 1.0.66 CLI ≥ 1.0.36 Default to action list — it is the one that hands you something you can execute. Switch to action search for the question it alone answers: which paid actions match this? ( credits only ). Both rank an action slug or name hit above an integration hit, above a description hit, and require all query terms to match. integration get vs native integration get These two commands return different sets of actions and are not interchangeable: Command Third party service actions (HubSpot, Salesforce, Clearbit, …) Built in Cargo actions (HTTP, transforms, utilities) When to use integration get <slug ✓ ✗ You need actions for a specific third party service — use this for HubSpot, Salesforce, Clearbit, etc. native integration get ✗ ✓ You need Cargo native capabilities that don't belong to any specific third party connector Example: To find HubSpot specific actions, use integration get hubspot — native integration get will not return them. Quick reference Connectors Connectors are authenticated connections to external services. Note: slug (unique identifier) and name (display name) are required with config , and rejected without it (the hosted form asks for them). For OAuth based integrations, the authentication flow is completed separately via connection integration complete oauth . Rate limit and cache are per connector. rate limit takes {"unit": "second" "minute" "hour" "day", "max": <n , "strategy": "spread" "burst"} — spread paces calls evenly, burst lets them through and then waits, and burst with "second" is rejected. Set it below the provider's own ceiling when one API key is shared across plays. cache ttl milliseconds makes a workflow node with an identical computed config inside the TTL return the cached result instead of calling the provider — and bill 0 provider credits for it. It only takes effect on integrations whose actions are cache compatible; elsewhere it is ignored. A day long TTL on an enrichment connector is a free dedupe across overlapping batches. Integrations Integrations define the available services and their connector actions. Integration categories: engagement , marketing , sales , finance , analytics , freeform , success , support , enrichment , storage , custom . Use integration get <slug to discover all actions available for a specific third party service (e.g. HubSpot, Salesforce). Use native integration get only for built in Cargo actions — it does not return HubSpot or other service specific actions. Actions are referenced by actionSlug in workflow node graphs (see the cargo orchestration skill's references/nodes.md ). Custom integrations A custom integration is an integration you host: an HTTP server that speaks Cargo's integration protocol — GET /manifest , POST /actions/<slug /execute , POST /extractors/<slug /fetch (and /count ), POST /autocompletes/<slug , POST /dynamicSchemas/<slug — registered with the workspace so its actions and extractors show up beside the catalog's. It runs either on your own server ( external ) or on a Cargo Hosting worker ( worker ; scaffold one with cargo ai hosting worker init <dir template custom integration ). Registration assigns the integration a generated slug ; create a connector against it with connector create integration slug <that slug as for any other integration. An external base URL must be publicly reachable — private and loopback addresses are refused ( unsafeOutboundUrl ), so a local server needs a tunnel. worker fails with workerNotFound until the worker exists in this workspace. Connector autocomplete — fetching available values for action fields Some action fields don't accept freeform input — their allowed values must be fetched dynamically from the connector. When you inspect an action's config (via integration get <slug or native integration get ), look at the uiSchema alongside the jsonSchema . If a field's uiSchema contains "ui:widget": "IntegrationAutocompleteWidget" , the valid values for that field must be retrieved using connector autocomplete . How to detect autocomplete fields When an action's config looks like this: The objectType field requires autocomplete. The ui:options.slug ( "listObjects" ) is the autocomplete slug you pass to connector autocomplete . How to call connector autocomplete Flag Required Description connector uuid yes The UUID of the connector to autocomplete against slug yes The autocomplete slug from uiSchema[field]["ui:options"].slug params yes JSON object of parameters (use {} when none are needed) value no Search string to filter results refresh no Bypass cache and fetch fresh results Autocomplete with parameters Some autocomplete fields depend on the value of another field. This is indicated by a params object in ui:options : Here, propertyName depends on the selected objectType . Replace the $this.$parent... expression with the actual value you chose: Response format Use the value field in your node config. The label is the human readable display name. Results may also include optional description and parent fields. Dynamic schemas — fields whose shape depends on another value A field whose uiSchema carries "ui:widget": "DynamicSchemaWidget" has no fixed schema: its sub fields come from the connector at configuration time (HubSpot's form consent options, for one, depend on the chosen formId ). Fetch the schema the same way as an autocomplete — the ui:options.slug and its params , with $this.$parent… references replaced by the values you chose: slug is the dynamic schema slug from ui:options , not the action slug (the help said "action slug" before CLI 1.0.128). The response carries schema (JSON Schema for the field) and uiSchema ; fill the field to match. Params that don't validate return an empty result (no schema ) rather than an error, so an empty answer usually means a missing or misnamed param. End to end example: configuring a HubSpot action Using connector actions in workflows Connector actions are used as nodes in workflow graphs. To use an action: Reading an action's input schema — and where the inputs go An action's input fields live at actions.<slug .config.schema in the integration get <slug output ( config.jsonSchema is the same schema decorated for the form UI). Read it before calling an action — don't guess field names. Two footguns: For a top level action ( action execute / execute batch ), the input values go in data , NOT in the action's config . The fields described by config.schema are the data payload; the action definition carries no config key at all. Misplacing them is no longer a loud failure: older backends rejected the call with A top level action does not use action.config; pass the action's inputs via data instead. , newer ones strip config on the way in, so its inputs never arrive — the call is refused before it runs on the first missing required field ( invalidData ), or runs on nothing when none is required, never with a message about config . If an action comes back empty or refused for no obvious reason, check that the inputs are in data . A misspelled key in data is refused before the run ( Unknown field: <key ). (Inside a workflow node graph those same fields go in the node's config — see cargo orchestration/references/nodes.md . The " data , not config " rule is specific to action execute / execute batch .) Some inputs must be resolved first via autocomplete. If a field's uiSchema carries IntegrationAutocompleteWidget , fetch its values with connector autocomplete (above). Notably, LinkedIn engagement/extraction actions ( connectProfile , visitProfile , extractEventAttendees , extractProfileViewers ) require identityIds — the connected account that acts — resolved via the listIdentityIds autocomplete. A must match format "uuid" error means that identity is missing. Example connector node (Clearbit company enrichment): Help Every command supports help :

cargo-connection