build_prompt

Given a character name, returns a ready-to-use image-generation prompt

SERVERGelbooru MCP SOURCEcitronlegacy/gelbooru-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade C, identity unverified Pull the record →

This record as markdown: /tools/citronlegacy-gelbooru-mcp/build-prompt.md

WHAT IT DOES

What build_prompt does on Gelbooru MCP

AI agents call build_prompt to retrieve information from Gelbooru MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why build_prompt is rated Low

This tool reads character tag data from Gelbooru and assembles a prompt string. It retrieves/queries data and generates text output with no side effects, making it a Read operation. Severity is low as misuse only produces a text string.

From the tool's definition "Given a character name, returns a ready-to-use image-generation prompt"

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs build_prompt safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Gelbooru MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For build_prompt, this is the rule to start with:

build_prompt Allowed

build_prompt is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "build_prompt": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Gelbooru MCP, apply this rule, and every build_prompt call is checked against it from then on.

FAQ

Questions about build_prompt

What does the build_prompt tool do? +

Given a character name, returns a ready-to-use image-generation prompt. It is categorised as a Read tool in the Gelbooru MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on build_prompt? +

Register the Gelbooru MCP server in PolicyLayer and add a rule for build_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 Gelbooru MCP. Nothing to install.

What risk level is build_prompt? +

build_prompt is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit build_prompt? +

Yes. Add a rate_limit block to the build_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.

How do I block build_prompt completely? +

Set action: deny in the PolicyLayer policy for build_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.

What MCP server provides build_prompt? +

build_prompt is provided by the Gelbooru MCP server (citronlegacy/gelbooru-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Gelbooru, and thousands of servers like it.

This server

All 7 Gelbooru tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →