Provides tools for reviewing and monitoring n8n workflow status, including active/inactive counts and workflows with errors.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@n8n Advisor check workflow status in my n8n instance"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for n8n workflow management. Provides AI assistants with the ability to review workflow status in n8n instances.
check_workflows: Reviews all workflows and reports their status, including active/inactive counts and workflows with recent errors.
Related MCP server: Cursor n8n Builder
pip install m2ai-mcp-n8n-advisorCreate a .env file or set environment variables:
# Base URL of your n8n instance (no trailing slash)
N8N_BASE_URL=https://your-n8n-instance.app.n8n.cloud
# API key from n8n Settings > API
N8N_API_KEY=your_api_key_hereOpen your n8n instance
Go to Settings > API
Create a new API key or copy an existing one
Use the full URL of your n8n instance for N8N_BASE_URL
Add to your claude_desktop_config.json:
{
"mcpServers": {
"n8n": {
"command": "n8n-advisor",
"env": {
"N8N_BASE_URL": "https://your-n8n-instance.app.n8n.cloud",
"N8N_API_KEY": "your_api_key_here"
}
}
}
}Or run directly with Python:
{
"mcpServers": {
"n8n": {
"command": "python",
"args": ["-m", "n8n_mcp.server"],
"env": {
"N8N_BASE_URL": "https://your-n8n-instance.app.n8n.cloud",
"N8N_API_KEY": "your_api_key_here"
}
}
}
}Reviews all workflows and reports their status.
Parameters: None
Returns:
total_workflows: Total number of workflows
active_workflows: Number of active workflows
inactive_workflows: Number of inactive workflows
workflows_with_errors: Count of workflows with recent errors
error_workflows: List of workflows with errors (id, name, error count)
workflows: Detailed list of all workflows with execution stats
Example Response:
{
"total_workflows": 5,
"active_workflows": 3,
"inactive_workflows": 2,
"workflows_with_errors": 1,
"error_workflows": [
{"id": "2", "name": "Data Sync", "errors": 3}
],
"workflows": [
{
"id": "1",
"name": "Email Notifications",
"active": true,
"recent_executions": {
"success": 10,
"error": 0,
"waiting": 0,
"running": 0
}
}
]
}# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run tests with coverage
pytest --cov=n8n_mcp
# Type checking
mypy src/
# Linting
ruff check src/MIT
Reviews all workflows and reports status. Shows total count, active/inactive breakdown, and identifies workflows with recent errors.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the burden. It describes the tool as reviewing and reporting, which implies a read-only operation. However, it does not explicitly state it is non-destructive or mention any potential side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, tightly written with no superfluous words. It front-loads the main action and then details the specific information provided.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters and no output schema, the description is sufficiently complete. It describes what the tool does and what information it reports. It could optionally mention that it is read-only or real-time, but overall it is adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4. The description adds value by explaining the scope ('all workflows') and the outputs, which complements the schema's complete coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reviews all workflows and reports status, including total count, active/inactive breakdown, and recent errors. It uses a specific verb and resource, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for getting an overall workflow status overview, with no siblings or alternatives provided. It lacks explicit when-not-to-use or exclusion criteria but provides clear context for when it is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0check_workflowsScored across 1 tool
Only one tool exists, so there is no possibility of confusion or ambiguity between tools.
With a single tool, naming is trivially consistent and follows a logical verb_noun pattern.
A single read-only 'check' tool is insufficient for an 'Advisor' server, which implies broader capabilities like querying, analyzing, or modifying workflows.
The tool surface is severely incomplete: it offers only one check operation with no ability to act on workflows, retrieve details, or perform any state changes.
Know when your n8n workflows, URLs, and AI apps break, before your customers do.
n8n MCP — query your own n8n instance (BYO).
Read-only triage for n8n, MCP, webhook, and AI agent workflow production failures.
Security scanner for n8n workflows: 18 rules, OWASP Agentic mapped. Free MCP, paid x402 API.
