🔗 Combine Prompts: Combine multiple existing prompts into a single prompt. Perfect for creating complex multi-step workflows. 📋 WORKFLOW: Use search_prompts to find prompt names first, then compose them.
AI agents call compose_prompts to retrieve information from Smart Prompts MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and combines existing prompts into a new composed prompt. It does not persist anything to storage (no 'save' or 'create' language), functioning more like an aggregation/read operation. However, since the output could be used downstream, severity is low. Confidence is slightly reduced because the description doesn't explicitly confirm whether the result is saved or just returned.
From the tool's definition Combine multiple existing prompts into a single prompt
Documented attack patterns abuse exactly the kind of access compose_prompts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Smart Prompts MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for compose_prompts:
{
"version": "1",
"default": "deny",
"tools": {
"compose_prompts": {}
}
}compose_prompts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
🔗 Combine Prompts: Combine multiple existing prompts into a single prompt. Perfect for creating complex multi-step workflows. 📋 WORKFLOW: Use search_prompts to find prompt names first, then compose them. It is categorised as a Read tool in the Smart Prompts MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Smart Prompts MCP Server MCP server in PolicyLayer and add a rule for compose_prompts: 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 Smart Prompts MCP Server. Nothing to install.
compose_prompts 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 compose_prompts 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 compose_prompts. 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.
compose_prompts is provided by the Smart Prompts MCP Server MCP server (jezweb/smart-prompts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Smart Prompts MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Smart Prompts MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.