What it does
Read one run this credential started: a paid tool answers a job handle {jobId, status:"running"} when its work outlives the time a client waits (render_cut and decompose_frame always do), and the work carries on. status: queued | running | landed | failed | house | cancelled. A landed job's result is exactly the answer the tool call would have given; the receipt says what ran, what it was quoted, what the lanes charged and the policy it ran under. A job accepted with queue:true reads queued until PREVIZ starts it, with its place in line and an estimated start (queue). waitSeconds (0–25) holds the call until the job leaves running (or a queued job starts) or the wait ends — a long-poll, free. A job's state comes only from what the engine and the lanes said, never from a clock: a run whose worker was lost is finished by PREVIZ's sweeper with nobody watching. A chain's jobId (run_chain) also answers a chain block: the chain's own status (running, input_required, landed, stopped, cancelled), every step with its own jobId, what it was quoted and charged and what it made, and the chain's receipt; the wait ends when the chain stops moving. Free.
- Access class
read· Reads only; changes nothing and costs nothing.- Cost
- Free.
- Project
- Not tied to one project.
A key holds only the access classes its owner gave it, set in Account → API keys → the key's Access: a new key holds read and write, and spend needs a monthly credit cap. tools/list shows only the tools a key holds, and a call to any other is refused with INSUFFICIENT_SCOPE. A key made before access classes existed keeps what it could do then (read, write, spend and live) until its owner sets its access; produce is given, never inherited.
Price
Free. This tool never spends credits.
Arguments
jobIdstring · required- The jobId from a paid tool's answer or from list_jobs.
waitSecondsnumber (0–25) · optional- Hold the call up to this many seconds for the job to leave running (default 0: answer now).
dryRunboolean · optional- true: answer what this call WOULD do — the route its engines would take under the project's policy, its price in every mode, whether it writes — and run nothing: nothing is written, nothing is charged.
Unknown arguments are refused by name rather than ignored, so a misspelling never runs quietly.
Answer
The fields this tool's answer declares. They arrive as structuredContent, and as the same JSON in the first text block for clients that read text.
jobId- The job.
op- The tool the job runs.
status- queued | running | landed | failed | house | cancelled. queued = accepted with queue:true and waiting for its engine lane's pace (grey): PREVIZ starts it by itself. failed = the engine refused it (red). house = stopped on PREVIZ's side, or a queued job that could not start (grey): never the request's fault, never a credits problem. cancelled = taken out of the queue before it started (grey): nothing ran, nothing was charged.
tone- working | done | red | grey — how a face shows the status.
queue- While queued: position (its place in the person's line on that engine lane, from 1; null while it waits on other work), estimatedStartAt (an estimate from the lane's pace) and waitingOn.
follows- On a one-step voiced take's job (the conversion animate_frame reserved with castVoice): takeJobId and shapeId of the take it waits on, and the character. It starts by itself when that take lands.
creditsQuoted- While queued: the price it was accepted at — held against the spending agreement, charged only when it runs.
queuedAt- While queued: when it was accepted.
projectId- The project it runs in.
quoteId- The quote (or idempotency key) it was charged under.
createdAt- When the row was written — before any engine was called.
updatedAt- Its last change.
finishedAt- When it landed, failed or stopped.
creditsCharged- What the lanes reported charging, once settled.
label- The run's label (the call's own `label`), or null.
note- A sentence for the agent about what the answer means or what to do next.
error- Why it failed or stopped.
actionUrl- On a job that ended on something only a person can lift (credits to buy, a spending agreement to sign again, a key's cap or access): the exact PREVIZ page to hand them. Behind their own sign-in; nothing in the address is a credential.
actionLabel- What the person does on actionUrl, in a few words.
result- When landed: the tool's own answer (imageUrl, videoUrl, where, creditsDeducted …).
receipt- What ran: op, request (money arguments removed), creditsQuoted, creditsCharged, policyVersion, engine (a capability, never a vendor), attempt.
next- While running or queued: when to ask again.
chain- For a chain's job: status, steps (each with id, tool, status, its own jobId, creditsQuoted, creditsCharged and outputs), receipt, and approvalUrl when a step waits on a person.
Behaviour hints
The hints the tool declares to clients, so an agent can decide what needs a person's approval.
- Read-onlyYes
- DestructiveNo
- IdempotentYes
- Reaches outside PREVIZNo
Call it
The JSON-RPC message, then the same call over HTTPS. Placeholders are in capitals.
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "get_job",
"arguments": {
"jobId": "YOUR_JOB_ID"
}
}
}curl -s https://mcp.aimpreviz.com \
-H "Authorization: Bearer $PVZ_KEY" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_job","arguments":{"jobId":"YOUR_JOB_ID"}}}'From an agent client you never write this by hand: connect it once (Claude Code, Cursor, TypeScript or Python) and ask for what you want.
When it fails
What the door answers instead, and what to do next. A refusal never charges.
- A call from a web page on an origin that is not allowed
- HTTP 403, JSON-RPC error -32003, before the body or the key is read. Call the door from a server, a terminal or a desktop client.
- A body that is not one JSON-RPC 2.0 message, or a batch
- HTTP 400, JSON-RPC error -32700 (unparseable) or -32600 (invalid or a batch), before the key is read. Send one message per POST with "jsonrpc": "2.0", a method and a string or number id.
- No key, a malformed key or a revoked key
- HTTP 401 with a WWW-Authenticate challenge, before any method runs, the handshake included. Stop and ask your person for a key; retrying will not help.
- An MCP-Protocol-Version header naming a version this door does not speak
- HTTP 400, JSON-RPC error -32600, naming the versions it supports. A request with no such header is accepted. Send the protocolVersion that initialize returned, or leave the header off.
- An unknown method
- JSON-RPC error -32601, "Unknown method" with the method's name. Use initialize, ping, tools/list or tools/call.
- An unknown tool
- JSON-RPC error -32602, "Unknown tool", naming tools/list. Call tools/list for the tools this door offers.
- Arguments that do not match the tool's input schema
- Protocol 2025-06-18: JSON-RPC error -32602 with the issues. Protocol 2025-11-25: a tool answer with isError set, naming each issue. Fix the named arguments. Unknown arguments are named, never ignored; confirm sent as the text "true" is refused, never coerced.
- A tool whose access class the key does not hold
- A tool answer with isError set, beginning INSUFFICIENT_SCOPE, naming the class the tool needs and the classes the key holds. Nothing ran and nothing was charged. Ask the key's owner to add it in Account → API keys → the key's Access; spend needs the key's monthly cap first.
- A refusal only a person can lift: the person's credits ran out (INSUFFICIENT_CREDITS), a monthly cap is missing or reached, a key lacks an access class, a freeze, or a spending agreement that was revoked, expired or does not cover the call
- The refusal carries actionUrl and actionLabel: the exact PREVIZ page for the person to press on, behind their own sign-in. For an agreement to sign again, the page opens with the old agreement's numbers suggested. A run answered by a job handle (a queued job, a long render) carries the same two fields on its job: get_job, list_jobs and the job's event. Nothing ran and nothing was charged. Hand the person actionUrl as it is. After they act, send the same call again with the same quoteToken or idempotencyKey. Two cases take a new idempotencyKey instead: a key whose first call already ran under an earlier agreement, and a queued job that has ended.
- A spend sent with your own idempotencyKey by an API key that has neither a monthly credit cap nor a signed spending agreement covering the call
- A tool answer with isError set, beginning CAP_REQUIRED, with actionUrl (the key's cap) and agreementUrl (the signing page). It is answered before anything is written, so the idempotencyKey is not used up. Nothing ran and nothing was charged. Hand the person either page. Once they have set a cap or signed an agreement, send the same call again with the same idempotencyKey.
- A webhook endpoint whose URL is not https on port 443, carries a user name, or resolves to a private address; or a call for an endpoint this key did not subscribe
- A tool answer with isError set, beginning URL_REFUSED (subscribe_webhook; nothing was subscribed), WEBHOOK_NOT_FOUND, WEBHOOK_INVALID (an unknown event kind) or WEBHOOK_LIMIT (ten endpoints per key). Give a public https URL that answers 2xx itself (a redirect is never followed), name kinds or families from the subscribe_webhook reference, and read list_webhooks for this key's endpoints.
- A replay that cannot be made exactly: a job whose request is no longer kept, a tool that changed shape, a policy that now leaves it no engine, or stale work that changed since its quote
- A tool answer with isError set, beginning REPLAY_UNAVAILABLE and saying which. Nothing ran and nothing was charged; PREVIZ never runs it on a different engine or from a guess. For replay_stale, call it again for a new plan and quote. For replay_job, call the tool yourself with the arguments you want.
- A tool that a rule for agents says is never run: the organisation's rule, or the person's own
- A tool answer with isError set, beginning GOVERNANCE_DENIED, naming whose rule it is. The call is refused before its arguments are read: nothing was priced, run or charged. get_governance lists every rule that binds this credential. An owner or admin changes the organisation's rule in PREVIZ; a person changes their own in their account.
- resume_chain on a chain that cannot carry on: cancelled, ended, past its quote, or stopped on a step that was charged or has used its attempts
- A tool answer with isError set, beginning CHAIN_STATE (or CHAIN_NOT_FOUND for a chain this credential did not start). Nothing ran and nothing was charged. replay_job on the chain's jobId quotes the same chain afresh; get_job reads what the chain already made.