N8n

43 tools. 26 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated:

26 can modify or destroy data
17 read-only
43 tools total

Community server · catalogue entry verified 30/06/2026

How to control N8n ↓

What N8n exposes to your agents

Read (17) Write / Execute (21) Destructive / Financial (5)
Critical Risk

The most dangerous N8n tools

26 of N8n's 43 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control N8n

PolicyLayer is an MCP gateway — it sits between your AI agents and N8n, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "delete_credential": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "create_credential": {
    "limits": [
      {
        "counter": "create_credential_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "discover_capabilities": {
    "limits": [
      {
        "counter": "discover_capabilities_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register N8n — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON N8N →

Instant setup, no code required.

All 43 N8n tools

READ 17 tools
Read discover_capabilities Discover available API capabilities based on the current API key's scopes. Read generate_audit Generate a security audit. Categories: credentials, database, nodes, filesystem, instance. Read get_credential_schema Get the required fields for a credential type (e.g., 'slackApi', 'githubApi'). Read get_data_table Get a data table's schema and column definitions. Read get_execution Get detailed information about a specific execution, including per-node inputs and outputs. Read get_execution_tags Get annotation tags for an execution. Read get_tag Get a specific tag by ID. Read get_workflow Get detailed information about a specific workflow including its nodes, connections, and settings. Read get_workflow_tags Get all tags assigned to a workflow. Read get_workflow_version Retrieve a specific version of a workflow from the version history. Read list_credentials List all credentials (metadata only — secrets are never exposed). Read list_data_tables List all data tables in the instance. Read list_executions List workflow executions. Filter by workflow_id, status (success/error/running/waiting/canceled/crashed), proj Read list_tags List all tags in the instance. Read list_variables List all instance variables — key-value pairs accessible across all workflows. Read list_workflows List all workflows with optional filtering by active status, tags, name, or project. Read query_table_rows Query rows from a data table with optional filtering, sorting, and full-text search.

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about N8n

Can an AI agent delete data through the N8n MCP server? +

Yes. The N8n server exposes 5 destructive tools including delete_credential, delete_execution, delete_tag. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through N8n? +

The N8n server has 13 write tools including create_credential, create_data_table, create_tag. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach N8n.

How many tools does the N8n MCP server expose? +

43 tools across 4 categories: Destructive, Execute, Read, Write. 17 are read-only. 26 can modify, create, or delete data.

How do I enforce a policy on N8n? +

Register the N8n MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every N8n tool call.

Deterministic rules across all 43 N8n tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

43 N8n tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.