AI agents call get_form_guide to retrieve information from Sdds without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and returns documentation/guide content. There are no side effects, data modifications, code execution, or destructive operations. The blast radius of misuse is minimal since the tool only provides informational content about form implementation. Confidence is high because the 'get_' prefix and 'retrieves' verb clearly indicate a read operation.
From the tool's definition Tool name contains 'get_' prefix and description uses 'retrieves' - both indicate data retrieval without modification. The tool fetches form guides and documentation for libraries (native HTML forms, React Hook Form, component support).
Attacks that exploit this kind of access
This tool retrieves the combined ${libraryName} form guides for native HTML forms, React Hook Form, and component support in these forms. It is categorised as a Read tool in the Sdds MCP Server, which means it retrieves data without modifying state.
Register the Sdds MCP server in PolicyLayer and add a rule for get_form_guide: 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 Sdds. Nothing to install.
get_form_guide 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_guide 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_guide. 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_guide is provided by the Sdds MCP server (@salutejs/sdds-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 →