render_prompt
AI agents call render_prompt to retrieve information from Durable MCP Tripleshot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to render/display an existing prompt template from the Tripleshot API without modifying, executing external commands, or deleting data. Rendering a template is a retrieval and presentation operation with no side effects, fitting the Read category. Severity is low because misuse would only expose or display existing prompts without affecting systems or data.
From the tool's definition Tool name 'render_prompt' combined with server description stating it 'retrieve[s] AI prompts' and provides 'template rendering capabilities'.
Attacks that exploit this kind of access
render_prompt. It is categorised as a Read tool in the Durable MCP Tripleshot MCP Server, which means it retrieves data without modifying state.
Register the Durable MCP Tripleshot MCP server in PolicyLayer and add a rule for render_prompt: 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 Durable MCP Tripleshot. Nothing to install.
render_prompt 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 render_prompt 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 render_prompt. 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.
render_prompt is provided by the Durable MCP Tripleshot MCP server (leopold16/durable-mcp-tripleshot-1). 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 →