Assembles the complete system prompt by orchestrating all
AI agents call assemble_prompt to retrieve information from 3DCityDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and assembles existing prompt/configuration data without side effects. It orchestrates information gathering (reading from other tools/schemas) to construct a system prompt, which is a read-only operation. The lack of action words like 'create', 'modify', 'delete', 'execute', or 'run' confirms this is a Read category tool with low severity risk.
From the tool's definition Tool name 'assemble_prompt' and description 'Assembles the complete system prompt by orchestrating all' indicate data retrieval and composition of prompt/configuration information.
Documented attack patterns abuse exactly the kind of access assemble_prompt gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 3DCityDB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for assemble_prompt:
{
"version": "1",
"default": "deny",
"tools": {
"assemble_prompt": {}
}
} assemble_prompt 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.
Assembles the complete system prompt by orchestrating all. It is categorised as a Read tool in the 3DCityDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the 3DCityDB MCP Server MCP server in PolicyLayer and add a rule for assemble_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 3DCityDB MCP Server. Nothing to install.
assemble_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 assemble_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 assemble_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.
assemble_prompt is provided by the 3DCityDB MCP Server MCP server (tum-gis/3dcitydb-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 3DCityDB 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.
14 3DCityDB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.