List available credentials (names only, no sensitive data)
AI agents call get_credentials to retrieve information from n8n MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only query of credential names/metadata. It explicitly does not return sensitive data, so there is no write, destructive, financial, or execution risk. The blast radius is minimal since an AI agent can only discover which credentials exist, not access their values or cause side effects. This is a standard Read operation with low severity.
From the tool's definition Tool description states 'List available credentials (names only, no sensitive data)' - this is a retrieval operation that queries credential metadata without exposing or modifying secrets.
Attacks that exploit this kind of access
List available credentials (names only, no sensitive data). It is categorised as a Read tool in the n8n MCP Server MCP Server, which means it retrieves data without modifying state.
Register the n8n MCP Server MCP server in PolicyLayer and add a rule for get_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 n8n MCP Server. Nothing to install.
get_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 get_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 get_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.
get_credentials is provided by the n8n MCP Server MCP server (nikolausm/n8n-mcp-server). 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 →