AI agents call list_credentials to retrieve information from CHARLIE without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries credential metadata without returning sensitive values and has no side effects. It fits the Read category definition: retrieves data with no side effects. The explicit safety guarantee in the description (NEVER returns values) and the fact it only lists metadata rather than extracting secrets makes this a low-severity information disclosure risk.
From the tool's definition Tool name 'list_credentials' and description 'List credential metadata. NEVER returns values.' indicate data retrieval with no side effects or modifications. The explicit statement about never returning values confirms this is a safe metadata read operation.
Attacks that exploit this kind of access
List credential metadata. NEVER returns values. It is categorised as a Read tool in the CHARLIE MCP Server, which means it retrieves data without modifying state.
Register the CHARLIE MCP server in PolicyLayer and add a rule for list_credentials: 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 CHARLIE. Nothing to install.
list_credentials 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 list_credentials 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 list_credentials. 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.
list_credentials is provided by the CHARLIE MCP server (t3cch/charlie). 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 →