AI agents use update-prompt to create or update resources in Dynamic MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dynamic MCP Server environment.
This tool modifies prompt data in a reversible manner. It does not delete, create financial transactions, execute arbitrary code, or destroy data. Update operations are classified as Write-category risks. Severity is medium because prompt manipulation could affect system behavior or user interactions if an agent updates prompts maliciously, but the impact is scoped to prompt configuration rather than systemic damage.
From the tool's definition Tool name 'update-prompt' explicitly indicates modification of existing data via the verb 'update'. Description states 'Update an existing prompt', confirming reversible data modification.
Documented attack patterns abuse exactly the kind of access update-prompt gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Dynamic MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update-prompt:
{
"version": "1",
"default": "deny",
"tools": {
"update-prompt": {
"limits": [
{
"counter": "update-prompt_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-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.
Update an existing prompt. It is categorised as a Write tool in the Dynamic MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dynamic MCP Server MCP server in PolicyLayer and add a rule for update-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 Dynamic MCP Server. Nothing to install.
update-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 update-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 update-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.
update-prompt is provided by the Dynamic MCP Server MCP server (scitara-cto/dynamic-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Dynamic 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.
18 Dynamic MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.