AI agents use updsts_update_sts_credential to create or update resources in Updsts — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Updsts environment.
This tool creates or modifies AWS credential files with STS tokens. While the operation is technically reversible (credentials can be updated again), the high severity reflects the sensitive nature of AWS credentials—misuse could grant an AI agent unauthorized access to AWS resources or enable privilege escalation.
From the tool's definition Tool name contains 'update' and server description states it 'Automatically update AWS credential files with temporary STS tokens'. The tool modifies AWS credential files, which is a reversible write operation on sensitive authentication data.
Attacks that exploit this kind of access
updsts_update_sts_credential. It is categorised as a Write tool in the Updsts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Updsts MCP server in PolicyLayer and add a rule for updsts_update_sts_credential: 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 Updsts. Nothing to install.
updsts_update_sts_credential 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 updsts_update_sts_credential 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 updsts_update_sts_credential. 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.
updsts_update_sts_credential is provided by the Updsts MCP server (zv-louis/updsts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →