Updates an existing prompt. Updates are always written to the project-specific directory, creating an override if necessary.
AI agents use update_prompt to create or update resources in Prompt Registry MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prompt Registry MCP environment.
This tool modifies existing prompts in a file-based registry by overwriting or creating override files. The operation is reversible (prompts can be updated again or reverted), affects only local prompt template data with no external side effects, and does not delete, execute code, or move financial resources. It clearly falls under Write category.
From the tool's definition Tool description states 'Updates an existing prompt' and 'Updates are always written to the project-specific directory, creating an override if necessary.' The verb 'update' combined with 'written to' indicates reversible modification of data.
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 Prompt Registry MCP, 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.
Updates an existing prompt. Updates are always written to the project-specific directory, creating an override if necessary. It is categorised as a Write tool in the Prompt Registry MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Prompt Registry 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 Prompt Registry MCP. 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 Prompt Registry MCP server (stevengonsalvez/promptregistry-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Prompt Registry 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.
7 Prompt Registry MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.