AI agents use categorize-prompt to create or update resources in MCP Prompt Manager — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Prompt Manager environment.
This is a Write operation because it creates or modifies data reversibly. Setting a category updates prompt metadata but does not delete data or cause irreversible effects. The medium severity reflects that misuse could corrupt prompt organization or metadata, but the blast radius is limited to organizational metadata rather than data destruction or financial impact.
From the tool's definition Tool modifies prompt metadata by setting/changing the category field on an existing prompt resource. The description "Set category for a prompt" indicates a state change operation that persists but is reversible.
Documented attack patterns abuse exactly the kind of access categorize-prompt gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Prompt Manager, and nothing reaches the server without passing your rules. This is the rule we recommend for categorize-prompt:
{
"version": "1",
"default": "deny",
"tools": {
"categorize-prompt": {
"limits": [
{
"counter": "categorize-prompt_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}categorize-prompt stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Set category for a prompt. It is categorised as a Write tool in the MCP Prompt Manager MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Prompt Manager MCP server in PolicyLayer and add a rule for categorize-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 MCP Prompt Manager. Nothing to install.
categorize-prompt is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the categorize-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 categorize-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.
categorize-prompt is provided by the MCP Prompt Manager MCP server (tae4an/mcp-prompt-manager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Prompt Manager, 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.
33 MCP Prompt Manager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.