AI agents call prompt_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.
The tool is explicitly marked as READ-ONLY and generates a prompt (text output) rather than executing any actions or modifying data. It retrieves/constructs a prompt string for the user to use externally, with no side effects.
From the tool's definition [READ-ONLY] Generate prompt to create tasks.md (WBS) that defines mandatory implementation steps
Attacks that exploit this kind of access
[READ-ONLY] Generate prompt to create tasks.md (WBS) that defines mandatory implementation steps. 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_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.
prompt_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 prompt_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 prompt_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.
prompt_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 →