AI agents call prompt_code 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 reads or retrieves specification/prompt information to generate code implementation guidelines. It has no side effects on the system, does not execute code, and does not modify persistent state. The '[READ-ONLY]' label is decisive. Severity is low because misuse would at worst produce unhelpful guidance, with no destructive capability.
From the tool's definition Tool is explicitly marked '[READ-ONLY]' and 'Generate essential implementation guidelines' — it produces guidance text without modifying, executing, or deleting any data or systems.
Attacks that exploit this kind of access
[READ-ONLY] Generate essential implementation guidelines that enforce strict adherence. 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_code: 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_code 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_code 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_code. 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_code 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 →