Grok Bot is a desktop AI assistant in Cursor's Grok Bot app: chat, a computer of its own, MCP connectors, and routines that fire on a schedule or an event. It is the conversational operator, and WorkerKit workers are the unattended specialists it operates.

Does Grok Bot connect to WorkerKit over MCP?

Yes. Add WorkerKit at https://mcp.workerkit.ai/workers to discover kits and manage workers. Enter a scoped manager key in protected credential settings. For published reports, use Knowledge MCP at https://mcp.workerkit.ai/knowledge with the same key and readKnowledge.

Can Grok Bot read my email or CRM through WorkerKit?

Grok Bot can run a worker that uses the email or CRM access you granted to that worker, and it can read app-derived information in run results when its fleet scopes allow it. Choose the worker's app permissions and the fleet connection's management and result scopes for the job.

What does the Grok Bot agent need to set this up?

An account admin creates a scoped key at workerkit.ai/fleet-access and enters it in protected credential settings. Grok Bot reads workerkit.ai/grok-bot/SKILL.md, verifies access and checks deployment, funding and budget before the first approved run.

How does Grok Bot get a worker's results?

Two paths. Grok Bot reads them with runs_feed and run_get: one connection watches every worker on the account, and each run's receipt carries the closing report, a typed digest when the run produced one, and the settled cost. People receive them through the worker's delivery channels: email, Slack, Teams, Telegram, Discord, Notion, SMS and WhatsApp, or a signed webhook.

I connected it and the fleet is empty. What now?

Choose a kit at workerkit.ai/kits, or ask Grok Bot to shortlist kits and preview one with kit_install_preview. Approve installation with the required scopes, connect its apps and deploy a model. Check funding and budget headroom, then run the job and read its result and receipt.

When do I use a routine and when do I use a worker?

Give WorkerKit a reusable app job that deserves its own instructions, model, approved memory and budget. Grok Bot can coordinate that worker alongside its routines, interpret the result and decide the next step with you.

WorkerKit has a Free plan with 5 workers and no card required. Model usage is billed separately. Wallet-funded tokens use provider list prices; loading the wallet carries a 5.5% fee with a $1 minimum. With your own model key, the first 1M tokens each month carry no platform fee, then the fee is 5% of list-price usage. Applicable app charges are separate. See workerkit.ai/pricing for plans and runtime fees.

For Grok Bot

AI workers for Grok Bot.

Give Grok Bot ready-made and custom workers for research, monitoring, classification and tasks across your apps. Each job gets its own instructions, memory, model, app access and budget. Grok Bot coordinates the fleet over MCP, brings back the results and helps you decide what comes next.

Start here

Connect WorkerKit to Grok Bot.

Use the prompt below to connect WorkerKit. Create a key, confirm the connection and enter the key in protected settings.

01
Create a manager key
At AI access, name the key Grok Bot. Start with read scopes and copy it once.
02
Paste the prompt into Grok Bot
Review and confirm the WorkerKit connection when Grok Bot asks.
03
Enter the key in protected settings
Enter the key in protected credential settings, never in chat. If Grok Bot has no protected field, use another client.

Paste into Grok Bot Help me connect WorkerKit: Add WorkerKit at https://mcp.workerkit.ai/workers for kit discovery and worker management. I will enter the scoped manager key in protected credential settings, outside chat. Ask me to confirm the connection, then call key_info and workers_list. Report the account, scopes and worker count.

Create a manager key At AI access, admin only. It is shown once, so keep it to hand.

The setup guide has every step in detail.

Why WorkerKit

Control your AI workforce from Grok Bot.

Ready-made, self-learning AI workers with only the access each job needs, a budget you set, and a record of every job and action.

Put AI workers on jobs with real ROI. Install a kit for work your team already repeats, and a worker arrives with its instructions, app permissions and schedule already written and reviewed. Start with the job that costs the most time, or build your own kit.
Turn your AI workers’ jobs and data into shared company knowledge. Each job’s instructions, apps and limits live in one kit your team keeps current, and workers that use the Records app keep what they find in shared tables and lists your team can open. Your team and every connected assistant work from the same process.
Choose what each AI worker can access. Each worker holds its own grant for each app, read-only by default, and nothing it reads can widen it. An assistant's key carries only the scopes you choose and never an app credential.
Track what your AI workers did and what they changed. Every run leaves a receipt with its result and its cost, and every tool call is logged with its outcome, so you can see what each worker did, when, and at what price.
Keep AI spending within the limits you set. Each worker has a per-run and a daily spending limit, under a limit for the whole account. When one is reached, new runs stop before any money moves, and the receipt says why.
Your AI workers learn as they work and keep getting better. A language worker can check every run against its job's quality criteria. A change that makes it better waits for your approval or, in Apply proven changes mode, applies on its own once it passes a comparison on your own examples. Its runs also propose what it should remember, and you approve what it keeps.

Put a worker to work

Give the follow-through to a worker.

Turn meeting notes into tasks: a worker reads the notes, creates tasks in your connected board and reports what needs your decision. Grok Bot uses the result to help you move the project forward.

What a fleet adds	Why it helps
Room in the chat	Machine output lands in a digest instead of the conversation, so the thinking stays in front of you.
A session per job	Each job gets its own context and its own model, chosen for that job rather than inherited from the chat.
A grant per job	App access is wired once, per worker, so Grok Bot orchestrates the work without carrying every integration itself.

Start with the Meeting Action Item Collector, review its app requirements and choose the accounts it should use.

Hired specialists

What a worker adds beside Grok Bot.

An AI worker is a background agent with its own instruction, memory, triggers, budget, model, app permissions and key. WorkerKit hosts each run and Grok Bot uses the result in your conversation.

Aspect	Grok Bot	A WorkerKit worker
Context	One conversation, plus the routines you save	Its own, sealed per run; only the digest returns
Model	The model behind this chat	Chosen per worker from any supported provider, or your own provider key
Identity	The connectors and tools the bot holds	Its own, holding only the apps, tools and permissions its job needs
When it runs	While you chat, or on a Grok Bot routine	Hosted by WorkerKit: on demand or on a schedule in its own time zone
What comes back	The work itself, in the chat	A closing report of at most 8,000 characters, a typed digest beside it, and the settled cost
Memory	The bot's memory about you	The worker's own rules and facts, carried across runs, and approved by you before a run may use them
Taking it back	Remove a connector or pause a routine	Pause a worker, cancel a run or manage its schedules in WorkerKit

Sealed standing jobs: long recurring work runs in its own context and returns a short, costed digest.

Access chosen for the job: Grok Bot operates workers through approved fleet scopes; each worker uses its own app grants and returns results from that work.

Per-run cost brakes: budgets cap spend and run count, and every receipt states the settled cost.

Workers can use email, calendars, documents, CRM, GitHub and research tools, plus curated MCP apps and your own custom MCP servers. Explore workers by app.

The operator pattern

Grok Bot operates. Workers work.

Step	Who	What happens
1	You	Ask in plain language. "Which workers ran today?", "Run the invoice chase now", "Pause the scanner."
2	Grok Bot	Reads its key's scopes first with key_info, picks the matching MCP tool, and follows the operating rules in its WorkerKit skill.
3	The worker	Executes in its own context, on its own runtime, on its schedule or on demand.
4	Both	Grok Bot reads the result with runs_feed and run_get: one connection covers the whole fleet, and the run's receipt carries the digest, the typed structure when the run produced one, and the settled cost. People receive it through the worker's delivery channels.

Let Grok Bot find a kit, prepare its configuration and operate the worker through approved access. Use the result in your next conversation or action.

For agents: search by the requested outcome and app with kits_search, inspect kit_get, then preview installation. For a custom classification job, read kit_app_tools(purpose:"decision") and use decision_worker_create to turn your questions into a worker. For an exact app operation with no model, use action_worker_create, then worker_tool_call.

Example: create a worker that classifies email previews into your categories. The setup guide covers deployment and funding before the first run.

Why Grok Bot and WorkerKit

Keep the conversation. Add the workforce.

Give recurring app work its own configuration, model and delivery destination. Grok Bot coordinates it alongside the rest of your work.

Grok Bot strength	What WorkerKit adds beside it
Custom MCP servers, added in chat	WorkerKit for kit discovery and worker management; Knowledge MCP for published reports
Conversational ops	Sealed specialists that hand back digests, so a long job costs a paragraph of chat rather than a screen of it
The desktop and the browser, when a job needs them	Hosted runs that keep going after the desktop session is closed
Routines on a schedule or an event	Hosted schedules in their own time zone, with per-run budgets, an app firewall and a receipt for every run
Ops workflows end to end	Ready-made kits and custom workers for monitoring, follow-ups, reporting and triage across the apps you connect

What it unlocks

Background work that stays out of the chat.

Each run executes sealed inside its own context, settles its exact cost and returns a digest. The worker remembers its own state. Your Grok Bot chat stays clean.

Sealed jobs, small returns Every job runs in its own context and only the digest returns to the chat. A large crawl becomes the few paragraphs that matter, so many workers fit in one conversation.
The right model per job Inexpensive models scan, frontier models judge. Every run is priced to the token, with reserved-versus-settled tracking, so background work is never a black box on your bill.
A budget for each job Set per-run and daily spending limits for the worker. Review the result, status and model cost together on its run receipt.
Standing monitors and briefings Workers watch on a schedule and report only what is new, so you stop relying on remembering to ask.
Two-way work A worker can ask for a decision. Grok Bot reads the question with run_question and supplies your answer through run_answer to start a linked follow-on run.
Memory that compounds Keep useful rules and facts with the job across runs. Approve proposed memory to make it available to future work.
Kits: install one or make your own Browse the catalog with kits_search and kit_get, install with kit_install, or author your own through kit_authoring_guide, kit_validate and kit_publish. Every path runs the same validators.
Create your own decision workers Give Grok Bot your questions and categories. It can create a decision worker over email previews, calendar events or Google Sheets rows, returning categories, scores or probability judgments for each item.
Fleet operations Clone a tuned worker for the next client with worker_clone or worker_clone_bulk, set budgets, route deliveries, and start and stop workers, all from the chat.
Delivery where people live Send reports to the destinations connected to your account, including email, Slack and Teams. Choose which runs should notify you.
Auditable trails Open the run receipt to inspect the outcome, status and settled cost. Read the transcript or structured decision results to understand the work.

MCP connections

Discover kits and manage workers.

Connect WorkerKit for your fleet. Add Knowledge to search published worker reports.

Connection	Address	What it does
WorkerKit	`https://mcp.workerkit.ai/workers`	Find kits and manage workers with a scoped manager key.
Knowledge MCP	`https://mcp.workerkit.ai/knowledge`	Search and read published worker reports with the same key and readKnowledge.

Read the MCP reference for the complete tool catalog, including creating decision workers, managing runs and configuring deliveries.

Access and control

Scoped per worker, and scoped for Grok Bot too.

Layer	What it holds
Per-worker grant	You connect each account yourself and choose what the worker may do there: per-app operations, read-only by default, narrowed by rules such as contact blocks, label and folder rules, customer-domain limits, time windows and IP allowlists. An account-level ceiling caps what any worker can be granted.
The app firewall	WorkerKit checks app calls against the granted operations and configured rules. Configure field masking, redaction and rate limits for connected apps, and inspect call outcomes.
Changes you control	Review instructions and app grants for the job. Approve proposed memory before future runs use it, and inspect instruction versions when changing the method.
Grok Bot's own access	Fleet scopes control worker management and result access. Running a worker uses its app grants; results can include app-derived content. Revoke client access at AI access, and manage workers and schedules separately in WorkerKit.

Choose the app operations for each worker and the fleet operations Grok Bot can request. Review results, change budgets and pause individual jobs in WorkerKit.

How it connects

Connect, choose a job, get a result.

Add WorkerKit with a manager key in protected settings. Ask Grok Bot to read the WorkerKit skill and find a suitable kit.

The setup guide covers access, installation, deployment and funding. Run a small job, inspect its result and cost, then choose its schedule and report destination.

The same fleet answers from anywhere else you work: any MCP client, the wk CLI in a terminal, and REST hosts such as Meta Muse, which reaches services over their APIs. The fleet outlives the choice of assistant.

Start with the Free plan and set a budget for model usage. See plans and runtime fees.

Questions

Grok Bot and WorkerKit, answered.

What is Grok Bot? Grok Bot is a desktop AI assistant in Cursor's Grok Bot app: chat, a computer of its own, MCP connectors, and routines that fire on a schedule or an event. It is the conversational operator, and WorkerKit workers are the unattended specialists it operates.
Does Grok Bot connect to WorkerKit over MCP? Yes. Add WorkerKit at https://mcp.workerkit.ai/workers to discover kits and manage workers. Enter a scoped manager key in protected credential settings. For published reports, use Knowledge MCP at https://mcp.workerkit.ai/knowledge with the same key and readKnowledge.
Can Grok Bot read my email or CRM through WorkerKit? Grok Bot can run a worker that uses the email or CRM access you granted to that worker, and it can read app-derived information in run results when its fleet scopes allow it. Choose the worker's app permissions and the fleet connection's management and result scopes for the job.
What does the Grok Bot agent need to set this up? An account admin creates a scoped key at workerkit.ai/fleet-access and enters it in protected credential settings. Grok Bot reads workerkit.ai/grok-bot/SKILL.md, verifies access and checks deployment, funding and budget before the first approved run.
How does Grok Bot get a worker's results? Two paths. Grok Bot reads them with runs_feed and run_get: one connection watches every worker on the account, and each run's receipt carries the closing report, a typed digest when the run produced one, and the settled cost. People receive them through the worker's delivery channels: email, Slack, Teams, Telegram, Discord, Notion, SMS and WhatsApp, or a signed webhook.
I connected it and the fleet is empty. What now? Choose a kit at workerkit.ai/kits, or ask Grok Bot to shortlist kits and preview one with kit_install_preview. Approve installation with the required scopes, connect its apps and deploy a model. Check funding and budget headroom, then run the job and read its result and receipt.
When do I use a routine and when do I use a worker? Give WorkerKit a reusable app job that deserves its own instructions, model, approved memory and budget. Grok Bot can coordinate that worker alongside its routines, interpret the result and decide the next step with you.
What does it cost? WorkerKit has a Free plan with 5 workers and no card required. Model usage is billed separately. Wallet-funded tokens use provider list prices; loading the wallet carries a 5.5% fee with a $1 minimum. With your own model key, the first 1M tokens each month carry no platform fee, then the fee is 5% of list-price usage. Applicable app charges are separate. See workerkit.ai/pricing for plans and runtime fees.

Ready? The setup guide is written for the Grok Bot agent doing the work, and the MCP server page holds the surface behind it.

To build a kit of your own, how to build a kit walks the procedure, and the kit-authoring skill is the file an agent keeps for it.