AI agents call get_credential_schema to retrieve information from N8n without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure information retrieval tool that queries credential type schemas. It has no ability to create, modify, delete, execute, or move money. The worst-case scenario is that an AI agent learns what fields are required for credentials, which is non-sensitive metadata. Classification as Read is appropriate with low severity due to minimal blast radius.
From the tool's definition Tool description states 'Get the required fields for a credential type' - this is a retrieval/query operation with no side effects. It fetches schema metadata about credential field requirements without modifying or executing anything.
Attacks that exploit this kind of access
Get the required fields for a credential type (e.g., 'slackApi', 'githubApi'). It is categorised as a Read tool in the N8n MCP Server, which means it retrieves data without modifying state.
Register the N8n MCP server in PolicyLayer and add a rule for get_credential_schema: 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. Nothing to install.
get_credential_schema 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_credential_schema 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_credential_schema. 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_credential_schema is provided by the N8n MCP server (siddharth0903/n8n-mcp). 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 →