AI agents call prompt_requirements to retrieve information from Wassden without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes user input, then generates a prompt for requirements documentation. It performs no writes, deletes, executions of external code, or financial operations. The read-only designation confirms no state modification occurs. Misuse by an AI agent would be limited to generating unhelpful prompts, with minimal blast radius.
From the tool's definition Tool description explicitly states '[READ-ONLY]' and describes analysis and prompt generation without modifying external state.
Attacks that exploit this kind of access
[READ-ONLY] Analyze user input for completeness and generate requirements.md creation prompt. It is categorised as a Read tool in the Wassden MCP Server, which means it retrieves data without modifying state.
Register the Wassden MCP server in PolicyLayer and add a rule for prompt_requirements: 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 Wassden. Nothing to install.
prompt_requirements 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 prompt_requirements 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 prompt_requirements. 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.
prompt_requirements is provided by the Wassden MCP server (tokusumi/wassden-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 →