--- name: scenario description: Use when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures, or game assets. Also when picking a Scenario model, running a LoRA, refining a generation prompt, uploading reference images, waiting on generation jobs, checking credits or quota, hitting Scenario auth, scope, or Forbidden errors, or setting up mcp.scenario.com in Claude Code, Cursor, VSCode, or another agent. license: MIT --- # Scenario ## Overview Scenario (scenario.com) generates AI images, video, 3D, and audio across 500+ models plus custom training, all through the core loop below. ## Setup Endpoint: `https://mcp.scenario.com/mcp` (Streamable HTTP). Prefer OAuth: no credentials pass through the conversation. Client config, API-key setup for headless use, and per-client re-authentication: [references/setup.md](references/setup.md). Never ask an agent to collect, encode, or echo a secret. A connection that authenticated once and fails later is re-authenticated per client (setup reference) before anything else is debugged; `diagnostics_run` names the failing layer (`auth`, `tenant-scope`, `api-unreachable`, or `healthy`). The default toolset is wider than the core loop below: `asset_get`, `job_get`, `jobs_list` and `models_list` are in it too and are called directly, so treat the table as the loop rather than the whole list. `?toolsets=full` exposes everything. The catalog tools are the ones outside it (collections, tagging, analysis, training, members, keys): `scenario_tools_search` with the tool name or plain keywords as `query` (it takes only `query` and `limit`) returns the schema and lane, and the matching `scenario_tool_execute_read` / `write` / `delete` runs it with `{name, parameters}`, scope ids inside `parameters` when the target's `inputSchema` declares them, which nearly every catalog tool does (`plan_generation`, which takes only `description`, is the exception), unlike a direct tool's top-level `team_id`/`project_id`. The lane is the result's own `permission`, not what the verb sounds like: `asset_download` and `asset_analyze` are both write-class. ## Scope first Resolve scope first, then pass `team_id` and `project_id` on every later call. `teams_list` returns the teams with their projects; `projects_list` requires a `team_id`, so it cannot come first. Confirm the pair with the user: a guess writes into someone else's project. A non-interactive run takes the pair from its task instructions; when they name none, stop and list the choices. The server fills scope in only for read-only tools with one candidate remaining; anything else fails rather than guesses, and the error names which half is wrong (see Errors and recovery). Scope errors are the most common failure here, surfacing mid-session on the first call that drops the pair once a second team or project is in play. ## Quick reference | Step | Tool | Notes | | ----------------- | ---------------------------------------- | ---------------------------------------------------------------------------- | | Resolve scope | `teams_list`, then `projects_list` | Once per session; pass the ids on every call | | Find a model | `search` or `recommend` | Free; `recommend` for a capability, `search` for a name | | Get the schema | `model_schema_get` | Always before `model_run`; check `runs_as` and caps | | Generate | `model_run` | Schema-conformant `parameters`; `dry_run` for cost | | Wait | `jobs_wait` | Whenever `model_run` returns a `job_id` without assets; never loop `job_get` | | View / save | `asset_display` / `asset_download` | Never paste raw asset URLs; `format` converts images, meshes | | Inspect an asset | `asset_get` | Free; dimensions, duration, `firstFrame` / `lastFrame` ids | | Upload inputs | `upload_asset` + `upload_asset_complete` | Local files become asset_ids | | Refine a prompt | `prompt_spark` | Advisory rewrite; needs `model_id` | | Quota / debugging | `usage`, `diagnostics_run` | CU consumption; `diagnose` MCP prompt | | Saved preferences | `memory_recall` | OAuth only; before generating in a project, again after switching | A multi-step request ("product video with voiceover", "concept to 3D") goes to `plan_generation` (catalog-only, read lane): plain words in `description`, ordered steps out, each naming a tool and optional model hint; it runs nothing. Single-step: `recommend`. A stated preference ("always 9:16") goes to catalog `memory_set` with `scope` `project_user_memory` (`user_memory` across projects): it replaces the whole layer, so `memory_get` and merge first, and it runs on the delete lane. ## Worked example Generating a stylized game prop image: 1. `recommend` with the user's own words as `prompt` when the need is a capability; `search` with `target="models"`, `query="flux"`, `public=true` when you have a name. `search` ranks by keyword and its `filters` hold no capability key, so a capability-worded query can rank the wrong output type first. For the user's own trained models, omit `public` on `search` (`search` has no private flag); on `recommend` the flag is `include_private_models: true`. Re-discover ids each time: availability differs per team. 2. `model_schema_get` on the pick: exact field names, types, required flags, defaults, and caps such as the prompt's `max_length` (an overrun is a 400, never a trim). File fields take asset ids even when named `...Url`, and `cost_impact: true` flags what moves the price. 3. If the schema carries `runs_as` (`"lora"` or `"composition"`), never send that model's own id to `model_run`. Its `run_with.required_arguments` holds the real call: `model_id` there is the base model, and its `parameters` (the `loras` or `modelId` wiring) merge into inputs from the same schema. Sending `required_arguments` alone discards your prompt. 4. Optional: `prompt_spark` rewrites a thin prompt into an on-model one; pass the discovered id (a LoRA's own, not its base) and the draft `prompt`. Skip deliberate prompts. 5. `model_run` with `model_id` and schema-conformant `parameters`. If cost matters (the default assumption unless the user says otherwise), price first with `dry_run: true`, a top-level argument beside `model_id`: no job is created and the response's `creativeUnitsCost` is the exact payload's price; a `recommend` cost quote assumes defaults, and the schema's `cost_impact` fields move the real number. Then run: asset_ids come back, or a `job_id` for `jobs_wait`. The `status` beside it is `in_progress` when the server's wait budget ran out; with `wait=false` it is the backend's live word at creation (`queued`, `in-progress`, `warming-up`), a spelling that is not a different state. 6. `jobs_wait` with `job_ids=[...]` (up to 32); each completed row carries `assetIds` and `cuCost`, so no `job_get` follow-up; on timeout re-call with the returned `pending_job_ids` as `job_ids`. Failed jobs are reimbursed, except xAI generations stopped by moderation. 7. `asset_display` shows the asset inline; its `format` picks the rendering: `display` (the default) returns an inline image plus links and viewer data; `viewer` returns a lighter payload for a host that renders the interactive widget; `json` and `markdown` return metadata and links. `display` does not disable a host's widget. For PNG files, use `asset_download` with `format: "png"`, one call per asset. `asset_download` returns a file URL (save with `curl -L`, it may redirect). `format` is an image conversion (`png`, `webp`, `jpg`, and `gif` to keep an animated GIF animated: the `png` default flattens it to one frame) and nothing else; omit it for video, 3D, and audio. When `curl` reports `host_not_allowed` or `CONNECT tunnel failed, response 403` while MCP calls work, check the host's proxy or sandbox egress policy. A CDN 403 alone does not establish the cause; request a fresh download URL before diagnosing it: [Sandbox network access](https://mcp.scenario.com/docs/troubleshooting#sandbox-network-access) names the setting that lifts it, an organization-level allowlist on some hosts that the user may not be able to change. Meanwhile hand over the `app_url` that `asset_display` returns, where the user downloads directly and, for a mesh, picks the 3D export format the app offers, none of which `asset_download` converts to. The signed URL also opens in a browser but expires, so it is a last resort, never the deliverable. Local inputs go up with `upload_asset`: always `file_name`, `content_type`, and `kind` (`image`, `audio`, `video`, `3d`), plus exactly one of `file_size` or `data`, since the call fails without either. Prefer `file_size`, the file's exact byte count read from disk, and omit `data`: the reply carries presigned part URLs and `instructions`; PUT each part's raw bytes to its URL with no added headers (a checksum header makes the store answer 403), check every PUT returned 200, then `upload_asset_complete` with the `upload_id`. Inline base64 `data` only under 100KB (that path returns the asset directly, with no complete step); a larger file is rejected naming the cap. Scope rides on both; they take no other fields: no parts list, no etags. The server decodes the file at completion, so `Upload upl_… failed: Corrupt JPEG data`, `premature end of data segment`, `bad Huffman code` or `libpng read error` means the uploaded image could not be decoded: check for a corrupt source, a truncated or re-encoded body, a missing part, or a mismatched `file_size`. Confirm the local file opens, its content type matches, and its byte count is correct, then start over with a fresh `upload_asset` and raw PUTs; never re-complete the same `upload_id`. A phone's HEIC photo uploads as is (`content_type: "image/heic"`), so do not convert it first; `Unhandled image format` lists what `kind: "image"` accepts, so convert a file of any other type locally. A host with no shell cannot PUT parts at all; the user uploads in the web app at app.scenario.com and the agent continues from the asset id. Filing is part of delivering, not a tidy-up: run the catalog tools above with arguments under `parameters` (never `arguments`, which the executor drops silently, surfacing as a scope error that is not one). `collection_create` takes a name and the scope pair only; `asset_ids` sent there is ignored without an error, so adding is always a second call, `collection_add_assets` with `collection_id` and `asset_ids`. It is atomic: one filed id fails the whole call with 400 `One or more assets are already part of the collection`, naming none, so read `collectionIds` via `assets_get_bulk` first and send only missing ids; `search` `filters={"collection_ids": [...]}` lags on a fresh write. `collection_add_assets` takes at most 49 ids per call (past it, 400 `You can not add more than 49 assets at once`), so chunk a larger set. `asset_add_tags` is additive, one `asset_id` per call, and a tag the asset already carries returns 400 `Duplicated tag`: read `tags` from that same bulk read and send only the missing ones. For reusable templates or reference content, follow the [shared asset lifecycle](references/shared-assets.md): resolve existing assets, stage new versions, publish only through a supported operation, and verify public access before recording public IDs. Uploading and filing alone are not publication. ## Errors and recovery | Error | Recovery | | ---------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `context_missing` | Nothing resolved: `teams_list`, then `projects_list` | | `context_ambiguous` | Several fit: present the options; the user picks (non-interactive: task instructions name the pair, else stop and list) | | 403 Forbidden | Usually wrong scope, not missing: re-check the id pair | | 403 naming a plan | Surface the upgrade or switch models; retrying never clears it. `recommend` pre-flags these as `requires_plan_upgrade` (never run one) unless its response says plan gating is `_degraded`; then this row is the backstop | | 429 with `details.actionName` = `parallel-custom-jobs` | Per-team generation concurrency ceiling: keep at most `actionLimit` jobs in flight, use `wait=false` for launches and `jobs_wait` to retire existing jobs before launching more. An immediate retry repeats the error | | 429 naming a quota, balance, or seat limit | Read the reason and `details` together, including `actionLimit` and `limitScope` when present. Generic plan-limit wording alone does not distinguish concurrency from consumption or feature access. A CU limit does not prove the balance is zero; the requested run may exceed what remains. Stop the affected batch, use `usage` for consumption, and report the stated remedy. A per-user cap goes to the team admin; a seat-cap error can also block uploads. Do not change billing or membership automatically | | 429 with an explicit retry delay | Respect the returned delay before retrying; this is not evidence that the user needs an upgrade | | Other 429, including an unfamiliar `actionName` | Do not classify every other action as a count quota, or infer a training quota's behavior from its name. Report the error and run `diagnostics_run` in the same scope before choosing recovery | | `jobs_wait` timeout (`in_progress`) | Not an error: re-call with the returned `pending_job_ids`, never a second `model_run` or a cancel; it takes no timeout argument | | Transport error on `model_run` (no HTTP status) | The request may still have landed: `jobs_list` before any re-run, or a lost response becomes a double charge; a `dry_run` call creates no job and always retries safely | | 400 `Cannot cancel this type of job` | A launched job is committed spend: `job_cancel` rejects most generation jobs, so plan batches with no abort path | | 400 `Invalid target format` | `format` converts images and `glb`/`fbx`/`obj` meshes: omit it for video, audio | | `Either 'file_size' … or 'data' is required` on `upload_asset` | Read the byte count from disk and send it as `file_size` (omit `data`); inline `data` is for files under 100KB only | | `Upload upl_… failed: Corrupt JPEG data` (or `libpng read error`) | The uploaded image could not be decoded: check the source file, content type, byte count, and part transfers before a fresh upload; re-completing does not repair corrupt bytes | | 404 on `asset_get` | The id does not exist and no retry makes it appear: re-read `assetIds` off the `jobs_wait` or `job_get` row, since a guessed or mistyped id is the usual cause | | 400 `At least one of query, filter, image, or images must be provided` | `search` never lists bare: a "newest first" asset listing is `target="assets"`, `filter="createdAt EXISTS"` with `sort_by=["createdAt:desc"]` | | `recommend` client-side timeout | It ranks on live data and commonly runs 30 seconds, sometimes over a minute: wait or re-call it; do not fall back to `search` for a capability | ## Common mistakes - A bare value where the schema says `array: true`: silently dropped, the run ignoring your reference or LoRA. `asset_get` on the output echoes what the run consumed (`metadata.referenceImages`, `parentId`), the cheapest proof it was not. - Taking `recommend`'s `ranked[0]` blindly: read `next_step.type` first. On `ask_user`, present the options; the user's pick wins (non-interactive: task instructions, else `proceed`). On `proceed`, prefer `specialty.model_id`, else the first `ranked` entry its own text does not mark deprecated, reading `tradeoff` and `explanation` as well as `caveats`, since the flag lands in any of them: the ranking is by measured performance, not by lifecycle, so a deprecated member can top it. - Debugging blind: the `diagnose` MCP prompt (or `diagnostics_run` with the scope pair the failure happened under and any `mcpt_` ids seen as `observed_trace_ids`) returns trace ids; `usage` answers credit questions. - Guessing a file field's name: 400 `Input image is required` (or `images`, `referenceImages`, `startImage`, `frontImage`, `video`, `model`, each a different model's name for the same idea) means the payload never carried the field the schema's `required` list names, so copy that name verbatim; a URL in a file field reads as missing too, since file fields take asset ids only. - Feeding an image field a video, audio, or 3D asset: 400 `Unhandled image format` lists the image types it accepts. `asset_get` reports the asset's `mimeType`; pull a still with the clip's `firstFrame` when the model wants an image. - `filters.kind` on `search` with `target="models"`: a 400 `"kind" is not a filterable field`, since `kind` describes assets. Narrow models with `filters.type` (the architecture) or `tags`, or go through `recommend` for a capability. - Filtering `models_list` by `type` without `privacy: "public"`: a 400 says so. A private listing narrows by `status` or `modality`, or goes through `search` (private by default).