AI agents use register_asset to create or update resources in Narrarium — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Narrarium environment.
This tool writes data by copying images and creating metadata files in a repository structure. While non-destructive and reversible (files can be modified or deleted), it permanently adds assets to the canonical storage. This is a Write-class operation because it creates persistent data structures, though the impact is scoped to asset management for a creative writing tool, making it medium severity rather than high.
From the tool's definition Tool 'registers' (creates and copies) image files and metadata into a 'canonical assets tree' - involves file creation/writing operations that modify the asset repository structure.
Attacks that exploit this kind of access
Copy an existing image into the canonical assets tree and create its matching prompt metadata file. It is categorised as a Write tool in the Narrarium MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Narrarium MCP server in PolicyLayer and add a rule for register_asset: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Narrarium. Nothing to install.
register_asset 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 register_asset rule in your PolicyLayer 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 PolicyLayer policy for register_asset. 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.
register_asset is provided by the Narrarium MCP server (narrarium-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →