Get the shield secret key of the active project
AI agents call get-shield-secret-key to retrieve information from Openfort MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves (reads) a sensitive secret key from the active project without modifying any data. While the severity is high due to the sensitive nature of shield secret keys (which could be misused if exposed), the action itself is purely a read operation. The tool does not create, modify, delete, execute code, or transfer funds.
From the tool's definition Tool name 'get-shield-secret-key' and description 'Get the shield secret key of the active project' indicate a retrieval operation of an existing credential/secret.
Attacks that exploit this kind of access
Get the shield secret key of the active project. It is categorised as a Read tool in the Openfort MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Openfort MCP Server MCP server in PolicyLayer and add a rule for get-shield-secret-key: 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 Openfort MCP Server. Nothing to install.
get-shield-secret-key is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get-shield-secret-key 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 get-shield-secret-key. 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.
get-shield-secret-key is provided by the Openfort MCP Server MCP server (openfort-xyz/-deprecated-mcp). 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 →