nativeads
Nativeads.ai provides generative AI tools that create display, video, native, and social ad creatives from simple text prompts.
Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeCan modify data
What it can do
- Patch Brand Dna Version: Partially update a Brand DNA version's canonical payload with an RFC 7386 JSON Merge Patch: send ONLY the fields to change (nested objects deep-merge; a null value deletes a k
- Image To Video: Start a first-frame image-to-video generation for a brand (default model). Asynchronous: returns a task id; poll get_task for completion. Results are much stronger with active Brand DN
- Download Asset: Return a short-lived presigned download URL for an asset (image, video, or PDF) by its id.
What data it sees
Do you need an account
No: the server works without sign-in
Nativeads.ai provides generative AI tools that create display, video, native, and social ad creatives from simple text prompts. The platform helps advertisers and agencies generate on-brand assets at scale, supporting campaigns across social channels, connected TV, programmatic display, and native inventory
Server tool list (34)
Raw names from tools/list. Only developers need these.
| patch_brand_dna_version | Partially update a Brand DNA version's canonical payload with an RFC 7386 JSON Merge Patch: send ONLY the fields to change (nested objects deep-merge; a null value deletes a key). The server reads the current payload, merges, and writes it back atomically, so you never echo the whole DNA. Example patch: {"your_brand":{"brand_name":"Acme"}}. |
| image_to_video | Start a first-frame image-to-video generation for a brand (default model). Asynchronous: returns a task id; poll get_task for completion. Results are much stronger with active Brand DNA. Before generating, call get_active_brand_dna; if the brand has none, offer to create and activate Brand DNA first (it significantly improves output), and only proceed without it if the user declines. |
| download_asset | Return a short-lived presigned download URL for an asset (image, video, or PDF) by its id. |
| extend_generated_videos_group | Add more video variations to an existing image-to-video group, reusing its recipe. Asynchronous: returns a task id; poll get_task. The parent group must be completed; consumes video quota. |
| get_brand_dna | Fetch the active Brand DNA payload (the canonical DNA content) for a brand. For the full active version with metadata, use get_active_brand_dna. |
| enhance_scene_forge_prompt | Start prompt enhancement for a Scene Forge generation. Asynchronous: returns a task id; poll get_task for the enhanced prompt. Always show the enhanced prompt to the user for review before calling scene_forge with promptIsEnhanced=true. Uses active Brand DNA when present; if the brand has none, offer to create it first. |
| get_started | Call this first. Read-only orientation for the caller: plan, subscription status and lockout mode, whether Brand DNA is available on the plan, whether a brand already exists, the caller's role, and a plain-language nextAction. Works in any client. |
| rerun_brand_dna_version | Reset a Brand DNA version to pending and re-run extraction, replacing its source set with the supplied assetIds and/or website URLs. Asynchronous: returns a task id; poll get_task. URLs are SSRF-restricted (http/https only; internal/metadata addresses rejected). |
| cancel_asset_upload | Cancel an in-progress asset upload by its uploadId (from initiate_asset_upload). No committed asset is affected. Idempotent. |
| extend_scene_forge | Add more image variations to an existing Scene Forge, reusing its stored recipe for a consistent look. Prefer this over a fresh scene_forge when you want more of the same. Asynchronous: returns a task id; poll get_task. The parent Scene Forge must be completed; consumes image quota. |
| get_task | Fetch the status of an async task (generation / enhancement / extraction) by the task_id an async tool returned. Poll this until "terminal": true rather than matching a status word; "succeeded": true means it finished OK. Workflow status is one of pending, processing, completed, failed, cancelled (note: this reports "completed", NOT the brand-DNA-version word "ready"). On failure, "retryable" tells you whether resubmitting unchanged might help. Suggested cadence: first poll ~5s after submit, then every 10-15s. get_task returns status only; read the actual result with the get_*/list_* tool the submit result named in resultTool. |
| get_brand | Fetch a single brand by id. |
| list_brands | List brands in the caller's organization, with optional industry/name filters. |
| get_active_brand_dna | Fetch the active Brand DNA version detail for a brand. |
| update_brand_dna_version | Rename a Brand DNA version and/or overwrite its canonical DNA payload. Pass the version's current updatedAt as an optimistic-lock token (from get_brand_dna_version). Omit dna for a rename-only update. |
| list_scene_forges | List Scene Forge image generations for a brand, with optional status/partner filters and pagination. |
| list_generated_video_groups | List image-to-video generation groups for a brand, with optional partner filter and pagination. |
| confirm_asset_upload | Confirm a completed S3 upload and start asset processing. |
| get_feature_usage | Read the caller organization's usage consumed vs plan cap (image + video pools) for the current billing period. |
| create_brand | Create a new brand in the caller's organization. Only name is required; the descriptor fields are optional because Brand DNA, not free-text descriptors, is what drives on-brand output. When a human is present, do not create silently: ask the user for the brand name and their logo, propose an industry and a short description from what you know, and confirm these with the user before calling this tool. The logo and other brand files are uploaded after this call (asset upload needs the brand to exist first); then give the brand Brand DNA, which is what makes output on-brand. |
| get_img2video_prompt_enhancement | Fetch the result of an enhance_img2video_prompt run by its id (the task id that enhance call returned). Returns enhancedPrompt once status is completed. Show enhancedPrompt to the user for review before calling image_to_video with promptIsEnhanced=true. |
| list_recent_tasks | List your recent async tasks (generations, enhancements, Brand DNA extractions) to recover task ids lost after a disconnect, including prompt-enhancement ids that have no other list tool. Read-only. Each entry's task_id is the id the matching get_*/list_* tool consumes. |
| enhance_img2video_prompt | Start prompt enhancement for a first-frame image-to-video generation (default model). Asynchronous: returns a task id; poll get_task for the enhanced prompt. Always show the enhanced prompt to the user for review before calling image_to_video with promptIsEnhanced=true. Uses active Brand DNA when present; if the brand has none, offer to create it first. |
| get_scene_forge_prompt_enhancement | Fetch the result of an enhance_scene_forge_prompt run by its id (the task id that enhance call returned). Returns optimizedPrompt (and theme) once status is completed. Show optimizedPrompt to the user for review before calling scene_forge with promptIsEnhanced=true. |
| list_brand_dna_versions | List all Brand DNA versions for a brand. |
| scene_forge | Start a Scene Forge image generation for a brand. Asynchronous: returns a task id; poll get_task for completion. Results are much stronger with active Brand DNA. Before generating, call get_active_brand_dna; if the brand has none, offer to create and activate Brand DNA first (it significantly improves output), and only proceed without it if the user declines. |
| cancel_brand_dna_version | Cancel an in-progress Brand DNA extraction. Committed versions are unaffected. Idempotent. |
| activate_brand_dna_version | Make a Brand DNA version the active one for its brand, so useBrandDna applies it in generation. Idempotent: activating the already-active version succeeds with no change. |
| delete_brand_dna_version | Permanently delete a Brand DNA version. Destructive and not reversible. |
| create_brand_dna_version | Start a new Brand DNA extraction from brand assets and/or website URLs. Asynchronous: returns a task id; poll get_task for completion. Activate the resulting version before using useBrandDna elsewhere. |
| get_brand_dna_version | Fetch a specific Brand DNA version's detail (including its DNA payload) by id. Use list_brand_dna_versions to find ids; get_active_brand_dna only returns the active one. |
| initiate_asset_upload | Reserve an upload and return a presigned S3 PUT target + uploadId. The client performs the PUT out of band, then calls confirm_asset_upload. |
| list_assets | List assets in the caller's organization, with optional brand/type/status/tag/campaign filters. |
| update_brand | Update a brand's fields (name, descriptors, logo). Only the fields you pass are changed; omitted fields are preserved. Use get_brand first if you need the current values. |