Read a secret value by name. Requires name to be whitelisted in project .claude/secrets.yml.
AI agents call get_secret to retrieve information from Claude Secrets without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored secrets without modification or side effects. While secrets are sensitive data, the tool itself performs only a read operation with gated access (whitelist requirement). Severity is low because the blast radius is limited by the whitelist mechanism—an agent can only read pre-approved secret names, not enumerate or access arbitrary secrets.
From the tool's definition Tool description explicitly states 'Read a secret value by name' with whitelist-based access control via project configuration.
Documented attack patterns abuse exactly the kind of access get_secret gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Secrets, and nothing reaches the server without passing your rules. This is the rule we recommend for get_secret:
{
"version": "1",
"default": "deny",
"tools": {
"get_secret": {}
}
}get_secret is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read a secret value by name. Requires name to be whitelisted in project .claude/secrets.yml. It is categorised as a Read tool in the Claude Secrets MCP Server, which means it retrieves data without modifying state.
Register the Claude Secrets MCP server in PolicyLayer and add a rule for get_secret: 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 Claude Secrets. Nothing to install.
get_secret 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_secret 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_secret. 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_secret is provided by the Claude Secrets MCP server (vaultry/claude-secrets). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Secrets, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Claude Secrets tools catalogued and risk-classified — across an index of 43,000+ MCP servers.