Create a background Marker parse job for a PDF.
AI agents invoke parse_pdf_structure to trigger actions in Asset Aware. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes an external parsing operation (Marker job creation) rather than simply reading or querying data. While it doesn't permanently modify the original PDF or delete data, it does trigger computation and processing logic whose behavior is input-dependent.
From the tool's definition Tool description states it will 'Create a background Marker parse job' — this initiates an external operation (a parsing job) whose effects depend on the PDF argument provided.
Attacks that exploit this kind of access
Create a background Marker parse job for a PDF. It is categorised as a Execute tool in the Asset Aware MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Asset Aware MCP server in PolicyLayer and add a rule for parse_pdf_structure: 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 Asset Aware. Nothing to install.
parse_pdf_structure is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the parse_pdf_structure 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 parse_pdf_structure. 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.
parse_pdf_structure is provided by the Asset Aware MCP server (u9401066/asset-aware-mcp). 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 →