AI agents call validate_tasks 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 task specifications to validate their structure and compliance. Validation is fundamentally a read operation with no side effects. The explicit [READ-ONLY] designation confirms it only inspects data without modification. Even if validation could theoretically inform downstream decisions, the tool itself performs no writes, executions, or destructive actions.
From the tool's definition The tool is explicitly marked [READ-ONLY] in its description and performs validation (a query/analysis operation) on tasks.md structure, dependencies, and spec compliance. It does not modify, execute, or delete any data.
Attacks that exploit this kind of access
[READ-ONLY] Validate tasks.md structure, dependencies, and spec compliance requirements. 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_tasks: 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_tasks 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_tasks 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_tasks. 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_tasks 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 →