Allows selection of specific enhancement techniques
AI agents use custom_enhance_text to create or update resources in UNO-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UNO-MCP environment.
This tool takes existing text and applies selected enhancement techniques to produce modified output. It creates/modifies content (Write), but does not execute code, delete data, or involve financial operations. Severity is medium because an AI agent could use it to alter content in unintended ways, but effects are generally reversible and limited to text transformation.
From the tool's definition 'enhance_text' and 'Allows selection of specific enhancement techniques' — modifies or transforms input text
Documented attack patterns abuse exactly the kind of access custom_enhance_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and UNO-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for custom_enhance_text:
{
"version": "1",
"default": "deny",
"tools": {
"custom_enhance_text": {
"limits": [
{
"counter": "custom_enhance_text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}custom_enhance_text 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.
Allows selection of specific enhancement techniques. It is categorised as a Write tool in the UNO-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the UNO- MCP server in PolicyLayer and add a rule for custom_enhance_text: 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 UNO-MCP. Nothing to install.
custom_enhance_text 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 custom_enhance_text 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 custom_enhance_text. 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.
custom_enhance_text is provided by the UNO- MCP server (mushroomfleet/uno-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from UNO-MCP, 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.
3 UNO-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.