Manage n8n credentials. Actions: list, get, create, update, delete, getSchema. Use getSchema to discover required fields before creating. For list, page beyond 100 results with cursor (from the previous response\
AI agents use n8n_manage_credentials to create or update resources in N8n — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your N8n environment.
While the tool includes destructive actions (delete), the primary scope is managing credentials through reversible operations (create, update). The delete action on credentials is severe due to potential workflow disruption, but credentials themselves are configuration data.
From the tool's definition Tool description explicitly lists actions including 'create, update, delete' on credentials. 'Manage n8n credentials' with delete capability present.
Documented attack patterns abuse exactly the kind of access n8n_manage_credentials gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and N8n, and nothing reaches the server without passing your rules. This is the rule we recommend for n8n_manage_credentials:
{
"version": "1",
"default": "deny",
"tools": {
"n8n_manage_credentials": {
"limits": [
{
"counter": "n8n_manage_credentials_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}n8n_manage_credentials stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Manage n8n credentials. Actions: list, get, create, update, delete, getSchema. Use getSchema to discover required fields before creating. For list, page beyond 100 results with cursor (from the previous response\. It is categorised as a Write tool in the N8n MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the N8n MCP server in PolicyLayer and add a rule for n8n_manage_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. Nothing to install.
n8n_manage_credentials is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the n8n_manage_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_manage_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_manage_credentials is provided by the N8n MCP server (@czlonkowski/n8n-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from N8n, 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.
22 N8n tools catalogued and risk-classified — across an index of 43,000+ MCP servers.