publish_prompt
Publish a specific version of a prompt as the active default, unlike promote_prompt which copies across environments or update_prompt which creates a new draft. This immediately routes all callers using the slug to that version and there is no rollback, so use list_prompt_versions to pick the ver...
This record as markdown: /tools/codeswhat-portkey-admin-mcp/publish-prompt.md
What publish_prompt does on Portkey Admin
AI agents use publish_prompt to create or update resources in Portkey Admin, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Portkey Admin environment.
Why publish_prompt is rated Medium
This tool modifies the active/default state of a prompt version, affecting all callers immediately. While it doesn't delete data, it is a high-impact write operation that changes routing for all users of that prompt slug. The 'no rollback' note increases severity but doesn't make it truly Destructive since the previous version still exists — it's just not easily reversible in practice.
From the tool's definition 'Publish a specific version of a prompt as the active default' and 'immediately routes all callers using the slug to that version and there is no rollback'
Attacks that exploit this kind of access
The rule that runs publish_prompt safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Portkey Admin, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For publish_prompt, this is the rule to start with:
publish_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Portkey Admin, apply this rule, and every publish_prompt call is checked against it from then on.
Questions about publish_prompt
Publish a specific version of a prompt as the active default, unlike promote_prompt which copies across environments or update_prompt which creates a new draft. This immediately routes all callers using the slug to that version and there is no rollback, so use list_prompt_versions to pick the version and update_prompt first if you need to create new content before promoting it. It is categorised as a Write tool in the Portkey Admin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Portkey Admin MCP server in PolicyLayer and add a rule for publish_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 Portkey Admin. Nothing to install.
publish_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 publish_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 publish_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.
publish_prompt is provided by the Portkey Admin MCP server (codeswhat/portkey-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Portkey Admin, and thousands of servers like it.
This server
Across the catalogue