update_secret_reference
Update at least one selected field on a Secret Reference. auth_config is merged into the existing manager-specific configuration. allowed_workspaces replaces all workspace mappings and sets allow_all_workspaces=false; allow_all_workspaces=true removes workspace-specific mappings. Credential value...
This record as markdown: /tools/codeswhat-portkey-admin-mcp/update-secret-reference.md
What update_secret_reference does on Portkey Admin
AI agents use update_secret_reference 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 update_secret_reference is rated Medium
This is a Write operation because it modifies secret reference configuration in a reversible manner (auth_config can be updated again, workspace mappings can be replaced). However, severity is high rather than medium due to the explicit warning about credential exposure to transcripts and the sensitive nature of secret reference management.
From the tool's definition Tool description states it 'Update[s]' secret reference fields, which is a modification operation. The description explicitly warns that 'Credential values are sent to Portkey and exposed to the MCP transcript,' indicating sensitive data handling.
Attacks that exploit this kind of access
The rule that runs update_secret_reference 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 update_secret_reference, this is the rule to start with:
update_secret_reference 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 update_secret_reference call is checked against it from then on.
Questions about update_secret_reference
Update at least one selected field on a Secret Reference. auth_config is merged into the existing manager-specific configuration. allowed_workspaces replaces all workspace mappings and sets allow_all_workspaces=false; allow_all_workspaces=true removes workspace-specific mappings. Credential values are sent to Portkey and exposed to the MCP transcript. 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 update_secret_reference: 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.
update_secret_reference 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_secret_reference 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_secret_reference. 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_secret_reference 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