Returns form configuration
AI agents call get_form to retrieve information from PDF Generator API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns existing form configuration data. There is no indication of creation, modification, deletion, or execution of code. The operation is read-only with minimal blast radius—an AI agent calling this tool cannot cause unintended data loss, financial impact, or execute arbitrary operations. It simply fetches configuration information.
From the tool's definition Tool name 'get_form' and description 'Returns form configuration' indicate a retrieval operation with no side effects. The verb 'Returns' clearly indicates data is being queried, not modified or executed.
Attacks that exploit this kind of access
Returns form configuration. It is categorised as a Read tool in the PDF Generator API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PDF Generator API MCP Server MCP server in PolicyLayer and add a rule for get_form: 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 Generator API MCP Server. Nothing to install.
get_form 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_form 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_form. 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_form is provided by the PDF Generator API MCP Server MCP server (pdfgeneratorapi/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 →