Set up WorkerKit in Lovable.

Before you start

What you need.

A Lovable account on any plan. Lovable supports custom MCP servers on all of them.

On Business and Enterprise, custom MCP servers switched on for the workspace. They are on by default, and an admin can turn them off under Connectors, Admin settings, Chat connectors. If MCP server is greyed out in the plus menu, that is the reason.

A WorkerKit account, and admin access on it: choosing the key a connection will hold is an admin-only decision. The Free plan is enough, and no card is needed.

For the skill step, a Lovable workspace owner or admin: only they can add workspace skills and edit workspace knowledge.

About a minute of the person's time. Lovable does everything except adding the two servers and approving the connection.

Why this route: Lovable connects any remote MCP server as a chat connector, so the hosted WorkerKit MCP mounts go in directly, by URL, with nothing to install and no code to write. Both mounts are public HTTPS, so keep the form's Direct connection; Lovable static IPs is an Enterprise option for servers behind an allowlist, and WorkerKit needs none.

Why OAuth: it is the default in Lovable's form, and the fleet mount is an OAuth 2.1 authorization server with lovable.dev on the list of clients it accepts a registration from. The credential is issued to the connection rather than handled by a person, and revoking it later is one action in WorkerKit.

The live mounts are on mcp.workerkit.ai; workerkit.ai/mcp is the page that documents them. The table above has both addresses in full.

The case for connecting at all is on the Lovable page.

Step 0. Human, under a minute

Add the public catalog.

The catalog mount takes no credential, so it connects on the URL alone and proves the wiring before any account is involved.

• Lovable Connectors, the plus button, then MCP server Server name: WorkerKit directory Server URL: https://mcp.workerkit.ai/directory Authentication: No authentication

The catalog mount takes no credential at all, on either path. It is the fastest proof that the client can reach WorkerKit, and it is worth adding first for exactly that reason: if it connects and the fleet mount does not, the problem is the credential rather than the wiring.

Select Add server. If a Connection dropdown appears, keep Direct connection. If MCP server is greyed out in the plus menu, a workspace admin has switched custom MCP servers off, and the fix is a request to that admin rather than a retry.

Step 1. Human, about 60 seconds

Connect your fleet.

Add the fleet mount with OAuth and approve on the WorkerKit consent page. Nothing is pasted into a chat, and the reach is exactly the scopes on the key chosen there.

The fleet mount is an OAuth 2.1 authorization server as well as an MCP server: it publishes discovery, accepts dynamic client registration from lovable.dev and runs authorization code with PKCE. Lovable's form defaults to OAuth, so the connection is a URL, a sign-in and an approval.

1. 01

   Give the client the URL and nothing else

   The fleet mount publishes OAuth discovery, so a client that supports it finds the authorization server on its own and registers itself. There is no client ID to create, no secret to store and no redirect address to register in advance.

2. 02

   Approve on the WorkerKit consent page

   The client sends the person to https://workerkit.ai/mcpauth. Signing in there is what proves who is connecting; nothing is typed into the assistant.

3. 03

   An account admin picks the key the client will hold

   The consent page lists the account's manager keys and can create one on the spot, so a first connect needs no visit to Fleet access beforehand. It is admin-only on the server, not just in the page: a member sees an honest notice rather than a broken screen.

4. 04

   Scopes are chosen with the key, and are the whole of the reach

   Whatever that key carries is exactly what the assistant can do, and nothing on it reaches a connected app. Narrow it now or widen it later; a new key drops into the same connection.

• Lovable Connectors, the plus button, then MCP server Server name: WorkerKit fleet Server URL: https://mcp.workerkit.ai/workers Authentication: OAuth Select Add & authorize, then approve at https://workerkit.ai/mcpauth

Nothing is pasted into the chat on this path, which is its real advantage: the credential never passes through a message, a log or a screenshot, and revoking it later is one action in the dashboard rather than an edit inside the assistant.

If the sign-in does not complete, remove the server and add it again with Bearer token or API key.

A client that cannot run an OAuth flow takes the same fleet on one header instead. An account admin creates a key at https://workerkit.ai/fleet-access, copies it once, and it becomes the value of an Authorization header on the fleet mount. That header is the whole of the authentication: there is nothing to register and nothing to pre-approve. For Lovable, create a key used by nothing else, start it on the Observer scopes with an expiry, and type it into that field only: never into a project chat, a Chat or knowledge, where it would be kept as text.

A key carries the scopes it was granted when it was created. Granting a scope later never reaches an existing key: if a call answers 403 OPERATION_NOT_ALLOWED, an admin re-scopes the key at Fleet access or creates a new one, and the new key drops into the same place. Read key_info rather than assuming.

Step 2. Agent

Verify the scopes.

Call key_info on the fleet connector. The scope list it returns is the truth, whatever was intended on the consent page.

• Ask in a project chat or in Chats Use WorkerKit fleet to call key_info.

Naming the connector in the prompt is how Lovable's docs say to test a new connection. The call returns the account title, the key name, the scopes, the expiry and serverTimeUtc. Plan against that list: a missing scope means an admin re-scopes the key at Fleet access or creates a new one.

Say in plain words what the key makes Lovable before offering anything: an observer key reports on the fleet, an operator key runs workers, and a builder key installs kits.

Step 3. Agent, with a workspace admin

Keep the WorkerKit skill.

Save the file as a workspace skill, which loads when a request matches. Skills are not available in Chats, so the operating rules go into workspace knowledge as well.

• Workspace settings > Skills > Add > Write manually Name: workerkit-fleet Description: the description line from https://workerkit.ai/lovable/SKILL.md Instructions: the body of https://workerkit.ai/lovable/SKILL.md, below its front matter
• Workspace settings > Knowledge (always in context, Chats included) WorkerKit: call key_info before any fleet work. Ask me before you run, install or change anything. Never ask for a WorkerKit key in a chat.

Write manually takes the same three parts the file has: a name, a description and the instructions. Lovable's other routes do not fit it, since Import from GitHub takes public GitHub URLs only and Upload ZIP wants an archive. A skill may hold up to 100,000 characters, and workspace knowledge up to 10,000, which is why knowledge carries the rules and not the whole file.

Lovable can also save a skill from a project chat when asked to "save that as a skill", which is the quickest route when it already has the file's text in front of it.

Step 4. Agent

Run the smoke test.

List the fleet and read recent runs, which alone prove the setup. If the account has workers, read one before running it, run it with approval, and report the receipt.

If the fleet is empty, stop after step 3 and say so: a new account has no workers yet, and the steps above have already proved the setup, because the key authenticated and both read scopes answered. Do not read it as a fault, and do not invent a worker to run. Go to the first-worker step and give the fleet something to do.

If the fleet has workers, pick one whose effects are reads. Judge it from the instruction and the permissions, never from the name: a worker whose apps are all read-level and whose instruction only gathers, summarises or reports is safe to run; one that sends, posts, writes, orders or pays is not, whatever it is called. If none is clearly read-only, run one with an explicit prompt for that run bounding it to a read.

• 1. The directory is alive: confirm a kit count comes back directory_overview
• 2. The fleet list: report how many workers the assistant can see workers_list
• 3. Recent runs across the fleet: confirms readRuns runs_feed { "limit": 5 }
• 4. Before running anything, read what that worker does and what it may touch. Both ride on readWorkers, and this is the step that decides whether the run is safe instruction_get worker_permissions_get
• 5. Run it with the person's approval, then poll every 3 to 5 seconds until a terminal event arrives: run.succeeded, run.failed, run.blocked or run.awaiting_input worker_run run_events { "afterSeq": <lastSeq> }
• 6. Read the receipt: costAuthority first, then modelCostUsd run_get

Read costAuthority first, then modelCostUsd beside it, and report both. A null finalDigest is not a failure: a run produces one only when its harness wrote a report. A costAuthority of unbilled_estimate, none or in_flight is not a failure either; it says how far to trust the number, and the operating rules below say what each value means.

A Skipped run is also a pass, and it is the cost brake working: the gate refused the run before any money moved. Report the skipReason rather than retrying. Then report the fleet size, the active scopes, and what the test cost, and the fleet is live.

Expect an approval card on the first write. Lovable asks before any tool the server has not marked read-only, so worker_run waits for a click. Approve that one call rather than choosing Always allow all tools from this connection, which would also cover every tool added later.

Step 5. Human and agent

Give the fleet its first worker.

A new account starts empty. Install a kit from its page in one click, or let Lovable preview and install one with kit_install_preview and kit_install once the person approves.

A new WorkerKit account starts with no workers, so the last step of setup is getting one. A kit is a ready-made worker: its instruction, its exact app permissions and its schedule, written and reviewed in advance, so installing one is how a fleet usually starts rather than a shortcut. There are two paths, and either ends with something to operate.

1. 01

   The one-click path: install a kit from its page

   Browse the catalog at workerkit.ai/kits, open a kit whose job you recognise, and install it. It arrives pre-instructed, pre-permissioned and pre-scheduled, and asks for whatever it needs to connect. This path needs no scope on the manager key at all, so it works on the first session whatever the key can do.

2. 02

   The agent path: shortlist, preview, approve, install

   With installKits on the key, the assistant can do the whole thing in chat: shortlist with kits_search, read the candidate with kit_get, then call kit_install_preview to surface its setup questions and exactly what the new worker would be allowed to touch. Put that in front of the person in plain words, and call kit_install once they approve, with deploy set to true so the new worker is actually able to run (that half needs manageDeployments on the key; without it the worker is installed but inert until worker_deploy). The new worker's key is shown once in the response.

3. 03

   Then run it once and read the receipt

   A worker earns its place on the first run. Trigger it with worker_run, follow run_events until a terminal event arrives, and report the digest and the settled cost from run_get. Set a schedule with schedule_create when the person is happy with what it did, and the fleet is not just connected, it is working.

The catalog mount is anonymous, so Lovable can shortlist ready-made workers and explain what each one would touch before the fleet is connected at all.

Step 6. Workspace admin, optional

Let an app you build read your workers.

A chat connector never reaches a published app. To show worker results inside an app built in Lovable, a workspace admin defines a custom connector over the WorkerKit REST API with a read-only key.

• Lovable Connectors, the plus button, then Custom connector Display name: WorkerKit Authentication: Bearer token API base URL: https://api.workerkit.ai Test request: GET /api/manage/workers/key-info Connect it with a manager key holding readWorkers and readRuns only.

Lovable stores a custom connector's credential encrypted and injects it on its server, so the key never appears in the project's code or chat. The connector is workspace-wide, and anyone who can use the published app can trigger what the app calls through it: so this key gets the Observer scopes and nothing that runs, installs or changes a worker, and the app sits behind a sign-in of its own, because run results can carry data from the apps a worker reads.

The endpoints and their scopes are on the API page, and the OpenAPI document it links is what Lovable should read before it writes the calls. The test request in Lovable's form proves the connection before the app makes a single call.

Classification on demand

Create a decision worker from your questions.

Categorize, score or triage connected data, then reuse and adjust the worker.

Reuse an existing worker or decision kit when its questions fit. For a custom classification task, creation compiles a supported source recipe and typed questions into a private kit and an installed decision worker. Optional deploy:true adds deployment; creation never starts a run or adds a schedule. The kit can be edited and published later through the normal kit lifecycle.

On the workers connection, call kit_app_tools(purpose:"decision") for recipes, argument schemas, permissions and examples, then kit_authoring_guide(section:"decision"). Check account connections with apps_list; public discovery does not check them. Send the request to decision_worker_create, follow nextCall, then use worker_run and run_get. Running needs runWorkers; results need readRuns. Use instruction_get / instruction_set for saved category or level answers, or answers on one run. Structural question/source changes need a revised kit and a replacement install. Check receipt status, coverage, omissions, warnings and cost before claiming completion.

Start with email-previews, calendar-events or sheets-rows. These recipes return judgments without app writes. Email previews do not include full threads; calendar events are invitation data, not transcripts; Sheets needs a Google file ID, a finite tab-qualified range and a columns map. A connected app alone does not make every tool a supported source. Source filters select evidence, not permissions: the Sheets recipe grants spreadsheet reads across the linked Drive account.

Supply 1–8 questions: choice with named options, score with ordered levels, or noul for the probability of a statement. Choice adds unclear automatically. Set an explicit confidenceFloor between 0 and 1; it routes uncertainty and does not promise accuracy. maxItems is 1–50, default 20. Creation requires createWorkers; optional deployment also needs manageDeployments.

Use a fresh requestId for each new worker. Retry with the same ID and identical body to recover the original receipt; a changed body returns 409. The response includes tokenId for MCP/CLI worker commands, stable workerId, kitSlug, readiness and nextCall. A deploymentError means the worker already exists: fix deployment on that worker. The receipt is a snapshot; check current worker readiness before running. No worker API secret is returned.

The workers connection includes discovery and authoring, so classification needs one MCP connection. Its full profile includes fleet management, app resource discovery, kit authoring and public directory reads. For a smaller list, a client that supports custom headers can send X-WorkerKit-Profile: decision on every request, including initialization, listing and calls, to select 24 workflow tools. A server operator can instead set MCP_WORKERS_PROFILE=decision. The endpoint and existing sign-in stay the same; a profile grants no additional permissions. Reconnect and relist after changing profiles. Use the advertised tool list: fleet administration, publishing, Action worker and event-stream tools require the full profile. Successful responses include structured content and a text fallback; creation declares an output schema.

Read the request example and full contract.

App tools, no model

Call app tools through an Action worker.

One exact app operation per call, with the inputs you supply.

An Action worker (modelType: "none") exposes 1 to 64 selected app tools and has no model, instruction, schedule or deployment. Each call invokes one tool with the arguments the caller sends, under the worker's own app access, and readiness.canInvoke on worker_get says whether its tools can be called now. Run and deploy requests answer 400 action_worker_requires_invoke.

On the workers connection's full profile: action_worker_options lists apps, tool schemas and defaults (readWorkers); action_worker_create copies an app's default tools, or takes an actionSpec of 1 to 64, plus a slackConnectionId for Slack tools when the account has more than one Slack bot (createWorkers); worker_tools lists the saved tools (readWorkers); worker_tool_call calls one with arguments, plus an idempotencyKey on a write (invokeActions); worker_tool_invocation reads a write's receipt (invokeActions). Pass the returned tokenId. kits_search(modelType:"none") finds Action kits; install one with kit_install and no deploy.

A write tool (readOnly: false) needs an idempotency key. Repeating the key with the same arguments returns the stored receipt (a confirmation, not the app's response) without calling the app again; with other arguments it is a 409. A call answers with status succeeded, denied, failed, in_progress or outcome_unknown; branch on it, not on the HTTP code. On outcome_unknown the write may have happened: never resend it automatically, under any key; read the receipt and check the app. Each call counts toward the worker's daily request limit; a refusal marked retryable, such as usage_limit, is retried later under a new key. Only the owner changes the selected tools, in the dashboard.

Read the call examples.

Least privilege

What each scope grants.

The key's scopes are exactly its reach, and a refusal names the scope it wanted. Start with the reads and add scopes as the work asks for them.

Operating rules

What the agent follows on every call.

The same rules the skill file carries, so a session that read neither still has them. Every row is a fact of the platform, not advice.

Quick answers

Symptoms, causes, fixes.

Each WorkerKit failure names itself in the response, so an agent never has to guess which one it met: read the code, apply the row, and carry on.