Train a brand-consistent LoRA from 20-50 sample images, returning a `lora_id` the `comfyui-*` and SDXL-family providers can reference. Requires a user-owned training endpoint (Modal / Runpod / self-host) at PROMPT_TO_BUNDLE_MODAL_LORA_TRAIN_URL. Phase-4 scaffold: the MCP tool does the packaging, ...
Part of the Prompt To Asset MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use asset_train_brand_lora to create or modify resources in Prompt To Asset. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call asset_train_brand_lora repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Prompt To Asset.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
asset_train_brand_lora:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Prompt To Asset policy for all 24 tools.
Agents calling write-class tools like asset_train_brand_lora have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Train a brand-consistent LoRA from 20-50 sample images, returning a `lora_id` the `comfyui-*` and SDXL-family providers can reference. Requires a user-owned training endpoint (Modal / Runpod / self-host) at PROMPT_TO_BUNDLE_MODAL_LORA_TRAIN_URL. Phase-4 scaffold: the MCP tool does the packaging, validation, and HTTP; the user owns the deployment and pricing. See docs/research/06-stable-diffusion-flux/6d-lora-training-for-brand-style.md.. It is categorised as a Write tool in the Prompt To Asset MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for asset_train_brand_lora. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Prompt To Asset MCP server.
asset_train_brand_lora is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the asset_train_brand_lora rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for asset_train_brand_lora. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
asset_train_brand_lora is provided by the Prompt To Asset MCP server (prompt-to-asset). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.