> **Building with AI coding agents?** If you're using an AI coding agent, install the official Scalekit plugin. It gives your agent full awareness of the Scalekit API — reducing hallucinations and enabling faster, more accurate code generation. > > - **Claude Code**: `/plugin marketplace add scalekit-inc/claude-code-authstack` then `/plugin install @scalekit-auth-stack` > - **GitHub Copilot CLI**: `copilot plugin marketplace add scalekit-inc/github-copilot-authstack` then `copilot plugin install @scalekit-auth-stack` > - **Codex**: run the bash installer, restart, then open Plugin Directory and enable `` > - **Skills CLI** (Windsurf, Cline, 40+ agents): `npx skills add scalekit-inc/skills --list` then `--skill ` > > `` / ``: `agent-auth`, `full-stack-auth`, `mcp-auth`, `modular-sso`, `modular-scim` — [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # PhantomBuster
Connect to PhantomBuster to launch and monitor automation agents, stream live container output, manage leads and lead lists, run AI completions grounded in real data, export usage reports, and control every aspect of your PhantomBuster organization programmatically.
PhantomBuster logo
Supports authentication: API Key **Plan requirements:** PhantomBuster tools require different subscription tiers. AI completions require **AI credits** (Pro+). CRM contact saving requires a configured **HubSpot integration** (Pro+). Branch management requires **Team+**. See the setup guide below for the full plan breakdown.
What you can build with this connector PhantomBuster automates web actions — primarily LinkedIn scraping, lead generation, and outreach at scale. With this connector your AI agent can: | Use case | Tools involved | |---|---| | **LinkedIn outreach pipeline** | `phantombuster_agent_launch` → `phantombuster_container_fetch_result` → `phantombuster_leads_save_many` | | **Scheduled scraping with monitoring** | `phantombuster_agent_save` (set schedule) → `phantombuster_org_fetch_running_containers` → `phantombuster_container_fetch_output` | | **Lead enrichment with AI** | `phantombuster_leads_fetch_by_list` → `phantombuster_ai_completions` (parse titles/skills) → `phantombuster_leads_save_many` | | **Quota-aware automation** | `phantombuster_org_fetch_resources` (check limits) → `phantombuster_agent_launch` → `phantombuster_org_export_container_usage` | | **Multi-org reporting** | `phantombuster_org_fetch` → `phantombuster_org_export_agent_usage` → `phantombuster_org_export_container_usage` | **Key concepts:** - **Agent** — a saved automation configuration (script + schedule + arguments). Launch an agent to create a container. - **Container** — a single execution run of an agent. Containers hold logs, status, and result data. - **Lead list** — a named collection of leads stored in your PhantomBuster organization.
## Set up the agent connector ## Usage ## Tool list --- ### Agent management ## `phantombuster_agents_fetch_all` Retrieve all automation agents in the PhantomBuster organization. Returns agent IDs, names, associated scripts, schedules, and current status. Use this to build an inventory of available agents before launching or managing them. **Required plan**: All plans. _This tool takes no input parameters._ ## `phantombuster_agent_fetch` Retrieve full details of a specific PhantomBuster agent by its ID — including name, script, schedule, launch type, argument configuration, and current status. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the agent to retrieve. | ## `phantombuster_agent_save` Create a new PhantomBuster agent or update an existing one. Supports configuring the script, schedule, proxy, notifications, execution limits, and launch arguments. Pass an `id` to update an existing agent; omit `id` to create a new one. **Required plan**: All plans. Custom scripts require **Team+**. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | No | Agent ID to update. Omit to create a new agent. | | `name` | string | No | Human-readable name for the agent. | | `scriptId` | string | No | ID of the script this agent runs. Use `phantombuster_scripts_fetch_all` to find script IDs. | | `schedule` | string | No | Cron-style schedule string (e.g., `0 9 * * 1-5` for weekdays at 9 AM). Set to `null` to disable. | | `launchType` | string | No | How the agent is triggered: `manually`, `automatically`, or `repeatedly`. | | `arguments` | object | No | Key-value pairs of input arguments the script expects. Must match the script's argument schema. | | `executionTimeLimit` | integer | No | Maximum execution time in minutes before the agent is force-stopped. | | `fileSizeLimit` | integer | No | Maximum output file size in MB. | | `proxy` | string | No | Proxy configuration: `none`, `datacenter`, or `residential`. | | `notifications` | object | No | Notification settings including `slackWebhookUrl` and notification triggers (`onSuccess`, `onError`). | ## `phantombuster_agent_delete` Permanently delete a PhantomBuster agent and all its associated data including execution history and output files. **This action is irreversible.** **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the agent to permanently delete. | ## `phantombuster_agent_launch` Launch a PhantomBuster automation agent asynchronously. Starts execution immediately and returns a `containerId` to track progress. Use `phantombuster_container_fetch_output` or `phantombuster_container_fetch_result` to retrieve results. **Required plan**: All plans (execution time consumed from plan quota). | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the agent to launch. | | `arguments` | object | No | Override launch arguments for this run. Must match the script's argument schema. | | `output` | string | No | Output format: `result-object` or `file-manager`. | ## `phantombuster_agent_launch_soon` Schedule a PhantomBuster agent to launch within a specified number of minutes. Useful for delayed execution without setting up a full recurring schedule. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the agent to schedule. | | `minutes` | integer | Yes | Number of minutes from now to launch the agent (minimum 1). | ## `phantombuster_agent_stop` Stop a currently running PhantomBuster agent execution. Gracefully halts the agent and saves any partial results collected up to that point. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the agent whose current execution to stop. | ## `phantombuster_agents_fetch_deleted` Retrieve all deleted agents in the PhantomBuster organization. Returns agent IDs, names, creation timestamps, deletion timestamps, and who deleted each agent. Useful for audit trails and recovery planning. **Required plan**: All plans. _This tool takes no input parameters._ ## `phantombuster_agents_unschedule_all` Disable automatic launch for **all** agents in the current PhantomBuster organization. Agents remain intact but will only run when launched manually. Use with caution — this affects every scheduled agent in the org. **Required plan**: All plans. _This tool takes no input parameters._ --- ### Container management ## `phantombuster_containers_fetch_all` Retrieve all execution containers (past runs) for a specific PhantomBuster agent. Returns container IDs, status, launch type, exit codes, timestamps, and runtime events for each execution. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `agentId` | string | Yes | The ID of the agent whose execution history to retrieve. | | `page` | integer | No | Page number for pagination (default 1). | | `perPage` | integer | No | Number of containers per page (default 20, max 100). | ## `phantombuster_container_fetch` Retrieve a single PhantomBuster container by its ID. Returns status, timestamps, launch type, exit code, and optionally the full output, result object, and runtime events. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The container ID to retrieve. | | `withOutput` | boolean | No | Include the full console output in the response. | | `withResult` | boolean | No | Include the structured result object in the response. | | `withEvents` | boolean | No | Include runtime events (steps, warnings, errors) in the response. | ## `phantombuster_container_fetch_output` Retrieve the console output and execution logs of a specific PhantomBuster container. Useful for monitoring execution progress, debugging errors, and viewing step-by-step agent activity. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The container ID whose output to retrieve. | | `fromOutputPos` | integer | No | Byte offset to start reading from. Use the `nextOutputPos` value from a previous call to retrieve only new output since the last fetch (incremental polling). | ## `phantombuster_container_fetch_result` Retrieve the final result object of a completed PhantomBuster container. Returns the structured data extracted or produced by the agent — such as scraped profiles, leads, or exported records. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The container ID whose result to retrieve. | ## `phantombuster_container_attach` Attach to a running PhantomBuster container and stream its console output in real-time. Returns a live stream of log lines as the agent executes. Use when you need to monitor execution as it happens rather than polling after completion. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the running container to attach to. | ## `phantombuster_agent_fetch_output` Get the output of the most recent container of an agent. Designed for incremental data retrieval — use `fromOutputPos` to fetch only new output since the last call, avoiding re-reading data you have already processed. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The agent ID whose latest container output to retrieve. | | `fromOutputPos` | integer | No | Byte offset to start reading from. Pass the `nextOutputPos` value returned by a previous call to fetch only new output. | ## `phantombuster_org_fetch_running_containers` List all currently executing containers across the PhantomBuster organization. Returns container IDs, associated agent IDs and names, creation timestamps, launch types, and script slugs. Use to monitor live execution or detect runaway agents. **Required plan**: All plans. _This tool takes no input parameters._ --- ### Script management ## `phantombuster_scripts_fetch_all` Retrieve all scripts associated with the current PhantomBuster user. Returns script IDs, names, slugs, descriptions, branches, and manifest details. Use to discover available scripts before creating or configuring agents. **Required plan**: All plans. _This tool takes no input parameters._ ## `phantombuster_script_fetch` Retrieve a specific PhantomBuster script by ID, including its manifest, argument schema, and output types. Optionally include the full source code. **Required plan**: All plans. Source code access requires **Team+**. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The script ID to retrieve. | | `withSource` | boolean | No | Include the full source code of the script in the response. Requires Team+ plan. | --- ### Branch management ## `phantombuster_branches_fetch_all` Retrieve all branches associated with the current PhantomBuster organization. Branches let you manage multiple versions of custom scripts — staging vs. production, for example. **Required plan**: Team+. _This tool takes no input parameters._ ## `phantombuster_branch_create` Create a new script branch in the current PhantomBuster organization. Use branches to develop and test script changes without affecting production agents. **Required plan**: Team+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `name` | string | Yes | A unique name for the new branch (e.g., `staging`, `dev-v2`). | ## `phantombuster_branch_delete` Permanently delete a branch by ID from the current PhantomBuster organization. All scripts associated with the branch will also be removed. **This action is irreversible.** **Required plan**: Team+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the branch to permanently delete. | ## `phantombuster_branch_release` Release (promote to production) specified scripts on a branch in the current PhantomBuster organization. Use this to deploy tested scripts from a staging branch to production. **Required plan**: Team+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the branch to release scripts from. | | `scripts` | array | Yes | List of script IDs to promote to production from this branch. | --- ### Organization ## `phantombuster_org_fetch` Retrieve details of the current PhantomBuster organization — including plan, billing information, timezone, proxy configuration, and connected CRM integrations. **Required plan**: All plans. _This tool takes no input parameters._ ## `phantombuster_org_fetch_resources` Retrieve the current PhantomBuster organization's resource usage and limits. Returns daily and monthly usage for execution time, mail, captcha, AI credits, SERP credits, storage, and agent count. Use to proactively manage quota before hitting limits. **Required plan**: All plans. _This tool takes no input parameters._ ## `phantombuster_org_fetch_agent_groups` Retrieve the agent groups and their ordering for the current PhantomBuster organization. Agent groups are used to organise agents in the dashboard. **Required plan**: All plans. _This tool takes no input parameters._ ## `phantombuster_org_save_agent_groups` Update the agent groups and their ordering for the current PhantomBuster organization. The order of groups and agents within groups is preserved exactly as provided. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `groups` | array | Yes | Ordered array of group objects. Each group must include `name` (string) and `agentIds` (array of agent ID strings). | ## `phantombuster_org_export_agent_usage` Export a CSV file containing agent usage metrics for the current PhantomBuster organization over a specified number of days (maximum 6 months / 180 days). **Required plan**: Pro+ (full 6-month range). Starter plan limited to 30 days. | Name | Type | Required | Description | | --- | --- | --- | --- | | `days` | integer | Yes | Number of past days to include in the export (1–180). | ## `phantombuster_org_export_container_usage` Export a CSV file containing container (agent run) usage metrics for the current PhantomBuster organization. Optionally filter to a specific agent to analyse a single automation's resource consumption. **Required plan**: Pro+ (full history). Starter plan limited to 30 days. | Name | Type | Required | Description | | --- | --- | --- | --- | | `agentId` | string | No | Filter the export to a specific agent ID. Omit to export all agents. | ## `phantombuster_org_save_crm_contact` Save a new contact to the organization's connected CRM (HubSpot). Requires a HubSpot CRM integration to be configured in **PhantomBuster dashboard → Settings → CRM**. **Required plan**: Pro+. HubSpot integration must be connected first. **CRM integration required:** This tool fails with a `403` error if no CRM is connected. Set up the HubSpot integration at [phantombuster.com](https://phantombuster.com) → **Settings** → **CRM** before calling this tool. | Name | Type | Required | Description | | --- | --- | --- | --- | | `firstName` | string | No | Contact's first name. | | `lastName` | string | No | Contact's last name. | | `email` | string | No | Contact's email address. Used as the unique identifier in HubSpot. | | `phone` | string | No | Contact's phone number. | | `company` | string | No | Company name associated with the contact. | | `jobTitle` | string | No | Contact's job title. | | `linkedinUrl` | string | No | Contact's LinkedIn profile URL. | | `website` | string | No | Contact's or company's website URL. | --- ### Lead management ## `phantombuster_leads_save` Save a single lead to PhantomBuster organization storage. If a lead with the same identifier already exists, it is updated. **Required plan**: Starter+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `listId` | string | Yes | The ID of the lead list to save the lead into. | | `firstName` | string | No | Lead's first name. | | `lastName` | string | No | Lead's last name. | | `email` | string | No | Lead's email address. | | `linkedinUrl` | string | No | Lead's LinkedIn profile URL. Used as a unique identifier if present. | | `company` | string | No | Company the lead is associated with. | | `jobTitle` | string | No | Lead's job title. | | `additionalFields` | object | No | Any extra key-value pairs to store with the lead (e.g., `{"source": "webinar", "score": 90}`). | ## `phantombuster_leads_save_many` Save multiple leads at once to PhantomBuster organization storage. Existing leads with matching identifiers are updated. More efficient than calling `phantombuster_leads_save` in a loop for bulk operations. **Required plan**: Starter+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `listId` | string | Yes | The ID of the lead list to save leads into. | | `leads` | array | Yes | Array of lead objects. Each object supports the same fields as `phantombuster_leads_save` (`firstName`, `lastName`, `email`, `linkedinUrl`, `company`, `jobTitle`, `additionalFields`). Maximum 1,000 leads per call. | ## `phantombuster_leads_delete_many` Permanently delete multiple leads from PhantomBuster organization storage by their IDs. **This action is irreversible.** **Required plan**: Starter+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `ids` | array | Yes | Array of lead IDs to permanently delete. Maximum 1,000 IDs per call. | ## `phantombuster_leads_fetch_by_list` Fetch paginated leads belonging to a specific lead list in PhantomBuster organization storage. Use `page` and `perPage` to iterate through large lists. **Required plan**: Starter+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `listId` | string | Yes | The ID of the lead list to fetch leads from. | | `page` | integer | No | Page number for pagination (default 1). | | `perPage` | integer | No | Number of leads per page (default 20, max 1,000). | --- ### Lead lists ## `phantombuster_lists_fetch_all` Retrieve all lead lists in the PhantomBuster organization's storage. Returns list IDs, names, lead counts, and creation timestamps. Use to discover available lists before fetching or saving leads. **Required plan**: Starter+. _This tool takes no input parameters._ ## `phantombuster_list_fetch` Retrieve a specific lead list from PhantomBuster organization storage by its ID. Returns the list metadata including name, lead count, and creation timestamp. **Required plan**: Starter+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the lead list to retrieve. | ## `phantombuster_list_delete` Permanently delete a lead list from PhantomBuster organization storage by its ID. All leads within the list are also deleted. **This action is irreversible.** **Required plan**: Starter+. | Name | Type | Required | Description | | --- | --- | --- | --- | | `id` | string | Yes | The ID of the lead list to permanently delete. | --- ### AI and utilities ## `phantombuster_ai_completions` Get an AI text completion from PhantomBuster's AI service. Supports multiple models including GPT-4o and GPT-4.1-mini. Optionally request structured JSON output via a response schema — useful for extracting structured data from unstructured agent output. **Required plan**: Pro+. Each call consumes **AI credits** from your plan quota. Monitor credit usage at **Dashboard → Usage**. | Name | Type | Required | Description | | --- | --- | --- | --- | | `model` | string | Yes | Model to use: `gpt-4o` (highest quality) or `gpt-4.1-mini` (faster, lower credit cost). | | `messages` | array | Yes | Conversation messages in OpenAI format: `[{"role": "user", "content": "..."}]`. Supported roles: `system`, `user`, `assistant`. | | `responseSchema` | object | No | JSON Schema object defining the expected response structure. When provided, the model returns structured JSON conforming to the schema instead of free-form text. | ## `phantombuster_location_ip` Retrieve the country associated with an IPv4 or IPv6 address using PhantomBuster's geolocation service. Useful for validating proxy locations or enriching lead data with geographic context. **Required plan**: All plans. | Name | Type | Required | Description | | --- | --- | --- | --- | | `ip` | string | Yes | The IPv4 or IPv6 address to geolocate (e.g., `8.8.8.8` or `2001:4860:4860::8888`). | --- ## More Scalekit documentation | Resource | What it contains | When to use it | |----------|-----------------|----------------| | [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content | | [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas | | [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |