AI agents call validate_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 only reads and validates a requirements document, then outputs guidance for fixes. It does not create, modify, delete, execute commands, or move money. The [READ-ONLY] designation and fact that it merely generates instructions (rather than applying them) confirm it belongs in the Read category with low severity.
From the tool's definition Tool name explicitly states 'validate' (analysis without modification), description declares '[READ-ONLY]' and specifies it 'generates fix instructions' (advisory output, not execution of changes). No side effects or data modification.
Attacks that exploit this kind of access
[READ-ONLY] Validate requirements.md and generate fix instructions if needed. 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 validate_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.
validate_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 validate_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 validate_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.
validate_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 →