AI workers for Claude.
Claude is the assistant you think with. WorkerKit gives it a fleet of specialists: background AI workers with their own instruction, memory, schedule, budget and pre-scoped app access, hosted around the clock and reporting back in short, costed digests. Long jobs stay out of the conversation, each worker gets its own narrow grant, and every run comes back with its settled cost. Setup takes about a minute of your time.
What Claude is
The assistant that wrote the protocol.
Claude is Anthropic's assistant, and it reaches the same person through several surfaces: the web app, the desktop and mobile apps, Cowork, and Claude Code in a terminal. It extends itself through connectors, which are MCP servers, and through skills, which are folders of instructions it loads when they are relevant. Anthropic created the Model Context Protocol, so a hosted tool surface is not a bolt-on here: it is the native way Claude reaches anything that is not itself.
| What a fleet adds | Why it helps |
|---|---|
| Room in the conversation | Machine output lands in a digest instead of the thread, so the reasoning you came for 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 Claude orchestrates the work without every integration hanging off one connector list. |
| Work that outlives the window | A hosted worker keeps its schedule whether or not Claude is open, which no conversation and no connector can do on its own. |
Claude is already excellent at the work you watch it do, and that is where it should stay. A fleet beside it takes the standing jobs: the ones that should keep running when the window is closed, hold their own app access, and report a paragraph rather than a screen.
Hired specialists
What a worker adds beside Claude.
An AI worker is a background agent with its own instruction, memory, triggers, budget, model, app permissions and key. WorkerKit hosts the runs, so Claude never has to hold a window open for them.
| Aspect | Claude | A WorkerKit worker |
|---|---|---|
| Context | One conversation, plus the projects and skills you keep | Its own, sealed per run; only the digest returns |
| Model | The Claude model behind this conversation | Chosen per worker from any supported provider, or your own provider key |
| Identity | The connectors you have added and approved | Its own key, with an explicit grant per app, read-only by default |
| When it runs | While you are there | Hosted around the clock: on demand, on a schedule in its own time zone, or on a signed inbound webhook |
| What comes back | The work itself, in the conversation | A closing report of at most 8,000 characters, a typed digest beside it, and the settled cost |
| Memory | Project knowledge and the memory you curate | 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 turn a skill off | Disable or revoke one worker; nothing else moves |
The operator pattern
Claude 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 | Claude | 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 | Claude 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. |
Claude becomes the fleet operator. The workers do the unattended work, Claude does the thinking about it, and the interactive work workers are not for stays exactly where it is.
Why Claude and WorkerKit
Each one covers what the other is not for.
Use Claude for the work you want to watch and steer. Use a WorkerKit worker for run unattended against my apps, on a schedule, with its own grant, and deliver to Slack.
| Claude strength | What WorkerKit adds beside it |
|---|---|
| Native MCP, on every surface | Two streamable-HTTP mounts, the public catalog and your fleet, live as soon as you add them |
| Skills that teach it your way of working | A skill file of our own, so the fleet arrives with its operating rules already written |
| Deep, careful reasoning in the moment | Sealed specialists that hand back digests, so a long job costs a paragraph of conversation rather than a screen of it |
| Claude Code, for work with a repository in reach | Hosted runs that keep going after the terminal is closed, with a receipt for every one |
| Projects that hold context for a body of work | Workers that hold context for a JOB, across runs, with memory you approve before it is used |
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 conversation stays clean.
- Sealed jobs, small returns Every job runs in its own context and only the digest comes back. A long 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.
- Money you can trust A run that never started costs nothing. A run that went silent mid-flight is absorbed by WorkerKit and labelled as an unbilled estimate. A failed run settles at actual usage with no minimum charge.
- 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 run that needs input does not guess or stall. It asks on every delivery channel and resumes as a linked follow-on run when you answer.
- Memory that compounds Rules and facts persist across runs, so the tenth run is smarter than the first. Anything a run proposes for memory waits for your approval before a future run may use it.
- Kits: install one or make your own Browse the catalog, install a ready-made worker, or author your own through the authoring guide, the validator and the publisher. Every path runs the same validators.
- Fleet operations Clone a tuned worker for the next client, set budgets, route deliveries, and start and stop workers, all from the assistant you already talk to.
- Delivery where people live Results land in email, Slack, Teams, Telegram, Discord, Notion, or SMS and WhatsApp, where their readers already are, instead of waiting in a chat nobody opens.
- Auditable trails Every run leaves a typed event stream, liveness heartbeats, owner and self scores, and the allow or redact outcome of each tool call underneath it.
What the two mounts expose
A public catalog, and your fleet.
WorkerKit publishes two mounts over streamable HTTP. The catalog is public, so it is never walled behind a sign-in; the fleet is yours, so it is never anonymous.
| Mount | Address | What it carries |
|---|---|---|
| Directory | https://mcp.workerkit.ai/directory | The public kits catalog: 9 read-only tools, including what WorkerKit is and when to use it, written for an agent, plus the guide, the vocabulary and the app-by-app tool explorer a kit is written from. No key at all, so the catalog can be browsed before anyone signs in. |
| Workers | https://mcp.workerkit.ai/workers | Your fleet and authoring on one connection: 91 tools in the full profile (84 manager tools plus 7 public discovery reads), or 20 tools in the decision profile. Discover sources, create classifiers, run and configure workers; the full profile also includes fleet administration, publishing and connection management. A manager key on the header, and the key's scopes are exactly its reach. |
| Area | Tools | What it covers |
|---|---|---|
| Key | key_info | What your key is and exactly which scopes the other tools will honour. Call it first. |
| Fleet | workers_list, worker_get, worker_set_enabled, worker_permissions_get | Every worker with live run state, one worker in full, start or stop, and what a worker may touch, read-only, in the same vocabulary a kit is written in. |
| Runs | worker_run, run_bulk, worker_runs, run_get, run_events, run_transcript, run_cancel, run_score, run_clear_digest | Trigger a run with a prompt for that run, or one prompt across up to 20 workers; watch it step by step, read the receipt and the stored process log, cancel or grade it. On a decision worker it decides instead and acts on what it routes: sourceArgs and maxItems narrow and cap what is judged, and waitSeconds waits for the settled receipt, which carries the per-item decisions. |
| Fleet activity | runs_feed, fleet_pulse, fleet_health, account_usage | Every worker’s runs in one feed, everything running right now, what is quietly wrong across the fleet, and the account’s headroom before you spend a slot or a run. One call each, instead of asking each worker in turn. |
| Two-way runs | run_question, run_answer | A run that needs an answer ends by asking; the answer starts a linked follow-on run. |
| Memory | memory_get, memory_add, memory_update, memory_delete | The rules and facts a worker carries into every run. |
| Schedules | schedules_list, schedule_create, schedule_update, schedule_delete | When a worker starts on its own, in its own time zone. |
| Instruction | instruction_get, instruction_set, instruction_versions, instruction_version_get, instruction_restore | The standing instruction, versioned on every change, with the history to compare against and roll back to. On a decision worker it reads the routing table and the install questions instead, and writes their answers. |
| Deliveries | delivery_list, delivery_channels, delivery_create, delivery_update, delivery_secret_rotate, delivery_delete | Where a run report goes when the worker finishes: email, Slack, Teams, Telegram, Notion, Discord, SMS or a signed webhook. |
| Deployment | models_list, deployments_list, deployment_get, worker_deploy, deployment_update, worker_undeploy | What makes an installed worker actually run: pick its model from the priced catalog, cap its spend, pause or resume it, take it off again. A worker with no deployment fires no schedule and refuses a run with not_deployed. |
| Budgets | budget_get, budget_set, fleet_budget_get, fleet_budget_set | A worker’s spend and run ceilings, and the account-wide fleet ceiling. Their own scope, because raising a dollar cap is the one management action that can cost money. |
| Creation | worker_clone_preview, worker_clone, worker_clone_bulk | Clone a worker into new ones, singly or in bulk, with a dry run first. A clone carries only permissions a person already approved on the source. |
| Deletion | worker_delete | Remove a worker for good, with its sub-workers. Permanent, where stopping one is not — which is why it is a scope of its own. |
| Kits | kit_install_preview, kit_install | Preview a directory kit against your account, then install it as a new worker — with deploy set, in the same call, which is what makes it run. |
| Kit authoring | kit_validate, kit_publish, kit_update, kit_replace, kit_unpublish, kit_relist, kit_make_private, kit_delete, kit_scan_get, my_kits_list, publisher_get_mine, publisher_set | Validate a kit in one dry run that reports every gate at once, publish it from content or from a worker you own, keep it private or list it, and keep your publisher profile. A private kit installed with kit_install is how an agent builds a worker from scratch. |
| Connected apps | apps_list, app_connect, app_disconnect | Which apps an operator can use right now, in the kit vocabulary, and connecting the rest by credential: validated live, stored encrypted, never returned. Browser sign-ins stay on the Apps page. |
| Model keys | model_keys_list, model_key_set, model_key_delete | Your own model-provider API keys, so runs bill your provider account instead of the wallet. |
| Onboarding and wallet | onboarding_get, wallet_get, wallet_checkout_create, wallet_checkout_get | Check model funding, hand off BYOK setup, inspect wallet balance, and request a human-confirmed Stripe checkout. A purchase is complete only when its status is credited. |
| Custom MCP servers | mcp_servers_list, mcp_server_get, mcp_server_create, mcp_server_discover, mcp_server_set_tools, mcp_server_delete | An app the platform does not offer, reached through its MCP server: register it as your own custom MCP app with its credential in the same call, enable the tools a job needs, and bind it in a kit. |
| Decision authoring | decision_worker_create | Compile typed questions and a supported source recipe into a private kit and installed decision worker. Optional deploy; never starts a run. Requires publishKits and installKits, plus manageDeployments when deploying. Retry the same requestId and body to recover the receipt. |
| Discovery and authoring reads | workerkit_about, directory_overview, kits_search, kit_get, kit_app_tools, kit_authoring_guide, kit_vocabulary | Public reads also available on the workers connection. Discover classification sources with kit_app_tools(purpose:"decision") and read kit_authoring_guide(section:"decision"). These reads never forward the manager bearer upstream. |
The manager key reaches the fleet only. It grants no access to any connected app: workers reach apps under their own grants and firewall, and no prompt can widen that.
The same two mounts answer every other MCP client, and the same fleet answers the REST API for hosts that speak plain HTTPS instead.
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 publishKits and installKits; 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 has 91 tools (84 manager tools and 7 public discovery reads); only decision_worker_create is new. 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 20 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 and event-stream tools require the full profile. Successful responses include structured content and a text fallback; creation declares an output schema.
Access and control
Scoped per worker, and scoped for Claude 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 | Every tool call is checked against the grant and the rules, field-masked, scanned for sensitive data, redacted, rate-limited and logged with its outcome. The worker's model never sees what the rules removed. |
| Prompt injection | A worker steered by content it reads still cannot exceed its grant. Proposed memory waits for a human. Publishing a kit to the directory runs a supply-chain and prompt-safety scan that fails closed. |
| The assistant's own access | A manager key carries explicit scopes, is shown once and stored hashed. It reaches the fleet only: no scope on it reads a mailbox, a calendar or a CRM. An agent reads its scopes before planning, and an admin can revoke the key at any time without touching a worker. |
A worker is only as trustworthy as the access behind it, so the access is yours to give, to narrow and to take back, one worker at a time. You delegate without handing over the kingdom.
How it connects
Two servers, one key, a skill.
Both mounts are added the way Claude adds any remote MCP server: by URL. The catalog takes no credential at all. The fleet mount is an OAuth 2.1 authorization server as well, so Claude discovers it, registers itself and sends you to a WorkerKit consent page, where an account admin picks or creates the manager key that connection will hold. Nothing is pasted into the chat, and there is nothing to register in advance.
Claude Code can do the same, or take a key directly on an Authorization header, which is the better fit for a terminal and for a key kept in an environment variable.
The whole procedure, written for the agent doing it, is the setup guide. The human's part is two steps and about a minute.
The same fleet answers from anywhere else you work: any other MCP client, the wk CLI in a terminal, and the REST API for hosts that speak plain HTTPS. The fleet outlives the choice of assistant.
Cost: WorkerKit has a Free plan with no card required. Runs bill model tokens at the provider list price with no markup, from a prepaid wallet or your own provider key, inside the budgets you set. Connecting Claude is not a paid feature, and the plans are on the pricing page.
Questions
Claude and WorkerKit, answered.
- Does Claude connect to WorkerKit over MCP? Yes, and it is the native path. Anthropic created the Model Context Protocol, and every Claude surface reaches remote MCP servers. WorkerKit publishes two: the public directory mount at https://mcp.workerkit.ai/directory, which needs no key, and the fleet mount at https://mcp.workerkit.ai/workers, which carries a manager key as a bearer header.
- Which Claude surface should I set this up on? Any of them. claude.ai, Claude Desktop and Cowork add both mounts as custom connectors by URL: the catalog with "No sign-in", the fleet with the sign-in flow the server publishes, approved on the WorkerKit consent page by an account admin. Claude Code does the same, and can also take the manager key directly on an --header flag, which suits a terminal and a key held in an environment variable. Team and Enterprise add connectors from Organization settings, and only an Owner can.
- Do I have to paste a key into Claude? On the hosted surfaces, no. The fleet mount publishes OAuth discovery and accepts dynamic client registration, so Claude registers itself and sends you to workerkit.ai/mcpauth to approve; the key is chosen there, by an account admin, and never passes through a message. Pasting a key on a header is the alternative, and it is what Claude Code offers for a terminal-shaped setup.
- Can Claude read my email or CRM through WorkerKit? No. The manager key Claude holds operates workers and grants no access to any connected app. Workers reach apps under their own per-app grants, firewall and rules; the fleet surface does not, and no prompt can change that.
- What does Claude need to set this up? A WorkerKit account with admin access, a manager key created at workerkit.ai/fleet-access, and the WorkerKit skill file at workerkit.ai/claude/SKILL.md. The person's part is about a minute: create the key and hand it over once. Claude adds both servers, verifies the scopes, keeps the skill and runs a smoke test.
- My connector says it cannot reach the server. What now? Hosted Claude surfaces connect from Anthropic's infrastructure rather than from your device, so a URL that works in curl can still fail there. Anthropic documents the causes: the host must resolve to globally routable IPv4 addresses, a redirect to a different host drops the Authorization header, and a WAF or CDN in front of the server must allow Anthropic's outbound range. WorkerKit's mounts are public and need none of that, which is why the catalog mount is the fastest proof the wiring is sound.
- How does Claude get a worker's results? Two paths. Claude 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? That is the expected state of a new account, and the connection is already proved. Install a kit to get the first worker: open any kit at workerkit.ai/kits and install it in one click, which needs no scope on the key at all, or, with installKits on the key, let Claude shortlist with kits_search, preview exactly what the new worker would be allowed to touch with kit_install_preview, and install it with kit_install once you approve. Then ask Claude to run it and read you the receipt.
- What does it cost? WorkerKit has a Free plan with no card required: 5 workers, 500 tool calls a day and the complete safety layer. Runs bill model tokens at the provider list price with no markup, from a prepaid wallet or your own provider key, inside the per-worker and fleet budgets you set. Connecting Claude is not a paid feature.
The setup guide is written for the agent doing the work, the MCP server page holds the surface behind it, and the wk CLI reaches the same fleet from a terminal.