AI agents call validate_design 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 performs structural analysis and validation of a design document, returning diagnostic information and guidance. It retrieves and analyzes data without creating, modifying, deleting, or executing code. The explicit '[READ-ONLY]' designation confirms it has no side effects. Severity is low because misuse would only result in incorrect analysis feedback, not compromise of actual systems or data.
From the tool's definition Tool name is 'validate_design' with description explicitly marked '[READ-ONLY]' and states it validates structure and generates instructions (no modifications to files or systems).
Attacks that exploit this kind of access
[READ-ONLY] Validate design.md structure and traceability, 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_design: 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_design 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_design 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_design. 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_design 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 →