AI agents call get_section to retrieve information from Pdf Spec without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structured information from PDF specification documents without any ability to modify, delete, or execute operations. It is purely informational access to ISO 32000 specification content. The blast radius of misuse is minimal - an agent could only retrieve existing specification data, which poses no security risk to systems or data integrity.
From the tool's definition Tool description states 'Get the content of a specific section' - a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Get the content of a specific section from the PDF specification (ISO 32000-2). It is categorised as a Read tool in the Pdf Spec MCP Server, which means it retrieves data without modifying state.
Register the Pdf Spec MCP server in PolicyLayer and add a rule for get_section: 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 Pdf Spec. Nothing to install.
get_section is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_section 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 get_section. 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.
get_section is provided by the Pdf Spec MCP server (shuji-bonji/pdf-spec-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 →