> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# CrewAI

> Run deployed CrewAI automations and manage CrewAI AMP SaaS control-plane resources.

![CrewAI logo](https://mintcdn.com/composio-preview/NPf8agM6UrvZD-Iu/images/toolkits/crew_ai.svg?fit=max\&auto=format\&n=NPf8agM6UrvZD-Iu\&q=85\&s=436ac52c8c011dd37fde8d2e03d0bbf9)

* **Category:** ai agents
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 8
* **Triggers:** 0
* **Slug:** `CREW_AI`
* **Version:** 20261030\_00

## Tools

> [accordion] Get Deployment Logs
>
> **Slug:** `CREW_AI_GET_DEPLOYMENT_LOGS`
>
> Return deployment lifecycle logs for a CrewAI deployment UUID to diagnose build or runtime deployment failures.
>
> #### Input Parameters
>
> **crew\_uuid** `string` *required*
>
> Crew deployment UUID returned by CREW\_AI\_LIST\_CREW\_DEPLOYMENTS.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Deployment Status
>
> **Slug:** `CREW_AI_GET_DEPLOYMENT_STATUS`
>
> Return the current AMP deployment status for one crew UUID from the SaaS control plane.
>
> #### Input Parameters
>
> **crew\_uuid** `string` *required*
>
> Crew deployment UUID returned by CREW\_AI\_LIST\_CREW\_DEPLOYMENTS.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Execution Status
>
> **Slug:** `CREW_AI_GET_EXECUTION_STATUS`
>
> Return the current state, progress, result, or error for a deployed-crew execution started with a kickoff ID.
>
> #### Input Parameters
>
> **kickoff\_id** `string` *required*
>
> Execution identifier returned by CREW\_AI\_START\_CREW\_EXECUTION.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Required Inputs
>
> **Slug:** `CREW_AI_GET_REQUIRED_INPUTS`
>
> Return the input names required by the connected deployed CrewAI automation before starting an execution.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Crew Deployments
>
> **Slug:** `CREW_AI_LIST_CREW_DEPLOYMENTS`
>
> List CrewAI crew deployments visible to the selected SaaS organization and return their identifiers for status, logs, or redeployment.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Redeploy Crew
>
> **Slug:** `CREW_AI_REDEPLOY_CREW`
>
> Trigger a new deployment of an existing CrewAI automation by UUID; this irreversibly changes the live deployment and may replace its runtime URL or token.
>
> #### Input Parameters
>
> **crew\_uuid** `string` *required*
>
> Existing CrewAI automation UUID to redeploy, obtained from CREW\_AI\_LIST\_CREW\_DEPLOYMENTS.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Resume Crew Execution
>
> **Slug:** `CREW_AI_RESUME_CREW_EXECUTION`
>
> Approve or retry a human-in-the-loop task and resume its paused CrewAI execution. Resuming may continue externally effectful work.
>
> #### Input Parameters
>
> **task\_id** `string` *required*
>
> Task ID from CrewAI's pending human-input notification for the task that should receive the decision.
>
> **is\_approve** `boolean` *required*
>
> Set true to approve and continue, or false to retry the task using human\_feedback.
>
> **execution\_id** `string` *required*
>
> Kickoff ID returned by CREW\_AI\_START\_CREW\_EXECUTION for the execution that is paused for human input.
>
> **human\_feedback** `string` *required*
>
> Approval context or retry feedback to give the paused task.
>
> **crew\_webhook\_url** `string`
>
> Original crew webhook URL to keep completion notifications active; CrewAI does not carry it forward automatically.
>
> **step\_webhook\_url** `string`
>
> Original step webhook URL to keep step notifications active; CrewAI does not carry it forward automatically.
>
> **task\_webhook\_url** `string`
>
> Original task webhook URL to keep task notifications active; CrewAI does not carry it forward automatically.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start Crew Execution
>
> **Slug:** `CREW_AI_START_CREW_EXECUTION`
>
> Start one execution of the connected deployed CrewAI automation and return its kickoff ID for status checks. The automation may perform irreversible external actions.
>
> #### Input Parameters
>
> **meta** `object`
>
> Optional metadata to associate with this execution.
>
> **inputs** `object` *required*
>
> Input values keyed by the names returned by CREW\_AI\_GET\_REQUIRED\_INPUTS.
>
> **crew\_webhook\_url** `string`
>
> Optional URL notified when the execution completes.
>
> **step\_webhook\_url** `string`
>
> Optional URL notified after each agent thought or action.
>
> **task\_webhook\_url** `string`
>
> Optional URL notified after each task completes.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
