Retrieve a secret value
AI agents call secrets.get to retrieve information from MCP Fullstack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves secrets (passwords, API keys, tokens, etc.) without modifying them, making it a Read operation. However, the severity is high because unauthorized access to secrets can enable lateral movement, privilege escalation, and compromise of downstream systems. The high severity reflects the sensitive nature of the data being accessed, even though the operation itself is non-destructive.
From the tool's definition Tool name 'secrets.get' and description 'Retrieve a secret value' indicate a read operation that accesses sensitive credential or configuration data.
Attacks that exploit this kind of access
Retrieve a secret value. It is categorised as a Read tool in the MCP Fullstack MCP Server, which means it retrieves data without modifying state.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for secrets.get: 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 MCP Fullstack. Nothing to install.
secrets.get 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 secrets.get 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 secrets.get. 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.
secrets.get is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). 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 →