AI agents call n8n_list_credentials to retrieve information from Mcp N8n without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists credentials but explicitly excludes sensitive data, making it a non-destructive, non-modifying read operation. There is minimal blast radius—an AI agent would gain visibility into credential metadata but not secrets. The tool poses no risk of data modification, deletion, code execution, or financial impact.
From the tool's definition Tool name 'n8n_list_credentials' and description 'List all credentials (without sensitive data)' indicate a query operation that retrieves data. The parenthetical note explicitly states sensitive data is excluded, confirming this is a safe read-only operation.
Attacks that exploit this kind of access
List all credentials (without sensitive data). It is categorised as a Read tool in the Mcp N8n MCP Server, which means it retrieves data without modifying state.
Register the Mcp N8n MCP server in PolicyLayer and add a rule for n8n_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 Mcp N8n. Nothing to install.
n8n_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 n8n_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 n8n_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.
n8n_list_credentials is provided by the Mcp N8n MCP server (lyzetam/mcp-n8n). 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 →