# How to connect Apify to Grok Bot (paste one key, 112 tools) > Connect Apify to Grok Bot with ClawLink: paste your Apify key once and 112 tools work from chat. No MCP server to run, nothing stored on your machine. Web version: https://claw-link.dev/grokbot/apify Grok Bot runs on its own cloud computer, so most Apify guides send you to register an OAuth app and paste keys into a sandbox that resets. ClawLink gives Grok Bot a more practical Apify setup: it runs one CLI command, you approve once in the browser, and Grok Bot can call real Apify actions from chat with no auth, token refresh, or tool wiring to build yourself. **Start here — paste this into Grok Bot to set up ClawLink:** > Set up ClawLink for me and tell me when it's ready. > 1. Pair this machine. It prints an approval link, so show me the link and stop, don't wait: `npx -y @useclawlink/cli login` > 2. I'll approve it in my browser, then reply "approved". > 3. When I say approved, connect the app: `npx -y @useclawlink/cli connect apify` > 4. Then run `npx -y @useclawlink/cli whoami` and tell me whether ClawLink is ready. ## Setup It takes three steps to connect Grok Bot to Apify. 1. **Pair from the terminal** — ask Grok Bot to run `npx -y @useclawlink/cli login` and approve the link it prints. 2. **Connect Apify** — `npx -y @useclawlink/cli connect apify`, then approve in the browser. 3. **Use it from chat** — ask Grok Bot in plain English. **The same CLI works from any agent with shell access:** ```bash npx -y @useclawlink/cli login # sign in via browser — no API key to paste npx -y @useclawlink/cli connect apify # connect Apify (browser OAuth) npx -y @useclawlink/cli actions apify # list available actions npx -y @useclawlink/cli run apify --input '' # execute (add --confirm for writes) ``` ### Install by command The prompt above does all of this. By hand, it is two commands Grok Bot runs in its own terminal, and one browser approval: ```bash npx -y @useclawlink/cli login # prints an approval link, approve it in your browser npx -y @useclawlink/cli connect apify ``` Pair once and it sticks: the key is written to ~/.clawlink/credentials.json inside Grok Bot's sandbox, so it survives between sessions. Prefer native tools over shell commands? Add `https://claw-link.dev/api/mcp` as a custom connector at grok.com/connectors and approve the ClawLink sign-in. Same account, no CLI. Verify the connection by asking Grok Bot: > Use Apify to actor task run sync get and walk me through the result in plain English. ### Using a different agent? The CLI above is not specific to Grok Bot. Claude Code, Cursor, Codex, or any agent that can run a shell command pairs with the same ClawLink account the same way: ```bash npx -y @useclawlink/cli login ``` `login` opens the same browser approval and stores a credential locally. Once Apify is connected in the dashboard, that agent calls the same 112 Apify tools over MCP. Full setup for MCP clients and shell agents: [connect apps to any AI agent](https://claw-link.dev/learn/connect-apps-to-any-ai-agent). ## Apify MCP for Grok Bot Looking for a Apify MCP server for Grok Bot? ClawLink connects Apify to Grok Bot and exposes 112 Apify tools your agent can call over [MCP](https://claw-link.dev/learn/what-is-an-mcp-server), with [hosted auth](https://claw-link.dev/learn/oauth-for-ai-agents) and nothing to run or maintain yourself. Using a different agent? The [OpenClaw Apify integration](https://claw-link.dev/openclaw/apify) and the [Hermes Apify integration](https://claw-link.dev/hermes/apify) connect the same ClawLink account the same way. ## What the Grok Bot Apify integration can do 112 Apify tools are ready for Grok Bot once the account is connected. The 30 below are the ones people reach for most; your agent can call all 112. ### 30 of 112 Apify tools for Grok Bot | Tool | What it does | |---|---| | **Actor task run sync get** `apify_actor_task_run_sync_get` | Run a task synchronously and get results | | **Acts get** `apify_acts_get` | List all Actors | | **Create task** `apify_create_task` | Create a new Actor task | | **Datasets get** `apify_datasets_get` | List all datasets | | **Get actor** `apify_get_actor` | Get Actor details | | **Get dataset items** `apify_get_dataset_items` | Get items from a dataset | | **Get key value record** `apify_get_key_value_record` | Get a record from a key-value store | | **Get list of runs** `apify_get_list_of_runs` | List Actor runs | | **Get list of tasks** `apify_get_list_of_tasks` | List all tasks | | **Get log** `apify_get_log` | Get Actor run logs | | **Key value stores get** `apify_key_value_stores_get` | List all key-value stores | | **Request queues get** `apify_request_queues_get` | List all request queues | | **Run actor** `apify_run_actor` | Run an Actor asynchronously | | **Run actor sync** `apify_run_actor_sync` | Run an Actor synchronously and get results | | **Run task** `apify_run_task` | Run a task asynchronously | | **Schedules get** `apify_schedules_get` | List all schedules | | **Users me get** `apify_users_me_get` | Get current user account data | | **Users me usage monthly get** `apify_users_me_usage_monthly_get` | Get monthly usage summary | | **Act runs last get** `apify_act_runs_last_get` | Get the most recent run of a specific Actor | | **Act version env var get** `apify_act_version_env_var_get` | Get environment variable details for a specific Actor version | | **Act version env vars get** `apify_act_version_env_vars_get` | Get the list of environment variables for a specific Actor version | | **Act version get** `apify_act_version_get` | Get details about a specific version of an Actor | | **Act versions get** `apify_act_versions_get` | Get the list of versions of a specific Actor | | **Act webhooks get** `apify_act_webhooks_get` | Get a list of webhooks for a specific Actor | | **Actor build get** `apify_actor_build_get` | Get detailed information about a specific Actor build | | **Actor build log get** `apify_actor_build_log_get` | Retrieve the log file for a specific Actor build | | **Actor builds get** `apify_actor_builds_get` | Get a paginated list of all builds for a user | | **Actor run get** `apify_actor_run_get` | Get details about a specific Actor run | | **Actor task get** `apify_actor_task_get` | Get complete details about an Actor task | | **Actor task run sync get dataset items get** `apify_actor_task_run_sync_get_dataset_items_get` | Run an actor task synchronously and retrieve its dataset items | ## Example prompts **Actor Task Run Sync Get** > Use Apify to actor task run sync get and walk me through the result in plain English. **Acts Get** > Use Apify to acts get and walk me through the result in plain English. **Create Task** > Create it in Apify for me, then confirm the important fields before you finish. **Datasets Get** > Use Apify to datasets get and walk me through the result in plain English. ## ClawLink vs. building it yourself The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for Grok Bot. That is fine if you want to build and maintain the integration yourself. Most teams just want Apify working from chat. | | Manual | ClawLink | |---|---|---| | **Credential handling** | Collect, validate, store, and rotate the Apify API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Apify account becomes available to the agent without you building credential management. | | **Ongoing maintenance** | You own refresh logic, permission debugging, environment config, and every provider-specific edge case for Apify. | ClawLink handles the repetitive integration plumbing so your team can focus on the workflow instead of the infrastructure. | | **Agent usability** | You still need to expose the right Apify actions to the runtime in a format your agent can reliably use. | 112 tools for Apify are already exposed through ClawLink, so the agent can read and act from chat immediately. | ## ClawLink vs. Composio Composio also exposes Apify to AI agents. It is developer infrastructure: Python and TypeScript SDKs, an MCP server, and a catalog past 1,000 apps, aimed at teams shipping agent products. ClawLink is built for Grok Bot users instead. You install the plugin once, connect Apify in the browser, and the 112 tools above work from chat. There is no SDK and no config file, and the Apify key you paste at setup is stored server-side rather than kept in your environment. Choosing between them? Read the full [Composio alternatives](https://claw-link.dev/hub/composio-alternatives) comparison. ### Grok Bot says it cannot add ClawLink as an MCP server Grok Bot only attaches MCP servers that are reachable over the public internet, so a local stdio server is refused. You do not need one. Ask Grok Bot to run `npx -y @useclawlink/cli login` in its terminal instead. The CLI is a shell command, not an MCP server. If you would rather have native tools, add `https://claw-link.dev/api/mcp` as a custom connector at grok.com/connectors and approve the ClawLink sign-in. ### Connection succeeds but no tools appear Reconnect Apify from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded. ### "Tool schema not loaded yet" error when calling Apify tools Apify tool schemas load on demand the first time a tool runs and are cached after that, so this error usually clears on its own: wait a few seconds and retry the same request. If every Apify call keeps failing with it in a fresh chat, reconnect from the dashboard, and contact support if it still persists — that pattern points to a configuration problem on our side, not something you can fix by reconnecting again. ### Apify returns 403 or "permission denied" on one action while others work Two usual causes. The connected account may not have access to the specific workspace, inbox, store, or project in the request — check that first. If access looks right, the agent may have sent a placeholder value (like "YOUR_ID" or an example id from documentation) instead of a real one: ask it to run a list or search tool first, then retry the action with a real id from those results. Most failures at this stage are one of these two, not ClawLink bugs. ### API key setup works but results look incomplete Double-check that the API key for Apify has the right scopes or account access. A valid key can still be too limited for some reads or writes. ### Is there a Grok Bot Apify integration? Yes. ClawLink is the fastest way to connect Grok Bot to Apify: link your Apify account once in the browser and Grok Bot can call the Apify API through 112 ready-made tools — no custom code or token handling. ### How do I connect Apify to Grok Bot with ClawLink? Ask Grok Bot to run `npx -y @useclawlink/cli login` in its terminal and approve the link it prints, then `npx -y @useclawlink/cli connect apify` to authorize Apify. Grok Bot calls the tools from the next message, and the pairing persists in its sandbox, so this is a one-time step: no config files, and the Apify key you paste is stored server-side instead of in your environment. ### How long does it take to connect Apify to Grok Bot? About two minutes. Sign in, click Connect next to Apify in the dashboard, authenticate, and Grok Bot can use it from the next chat message. ### Why use ClawLink instead of wiring Apify up myself? The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for Grok Bot. That is fine if you want to build and maintain the integration yourself. Most teams just want Apify working from chat. ### Grok Bot says it cannot add ClawLink as an MCP server Grok Bot only attaches MCP servers that are reachable over the public internet, so a local stdio server is refused. You do not need one. Ask Grok Bot to run `npx -y @useclawlink/cli login` in its terminal instead. The CLI is a shell command, not an MCP server. If you would rather have native tools, add `https://claw-link.dev/api/mcp` as a custom connector at grok.com/connectors and approve the ClawLink sign-in. ## Related - [Connect GitHub](https://claw-link.dev/grokbot/github) — Manage repositories, issues, pull requests, and workflows - [Grok Bot PagerDuty integration](https://claw-link.dev/grokbot/pagerduty) — Manage incidents, on-call schedules, and services - [Grok Bot SafetyCulture integration](https://claw-link.dev/grokbot/safetyculture) — SafetyCulture (formerly iAuditor) is a workplace operations platform that enables teams to conduct digital inspections, manage audits, track issues, schedule tasks, and maintain compliance through mobile and web applications.