n8n-mcp-mini
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| N8N_API_KEY | No | The API key for the n8n instance, created in n8n settings (Settings → n8n API → Create an API key). Required to enable live n8n management tools. | |
| N8N_API_URL | No | The base URL of the n8n instance's API, including /api/v1 (e.g. https://your-instance.example.com/api/v1). Required to enable live n8n management tools. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tools_documentationA | Usage guide: recommended workflow for looking up nodes, validating configs, and (if configured) managing a live n8n instance. Call this first if unsure where to start. |
| search_nodesA | Full-text search (SQLite FTS5) across all 538 node types (core + AI/langchain): name, description, keywords. Leave query empty to browse by category/package. |
| list_categoriesA | List every category in the node database, with counts. |
| list_packagesA | List the source npm packages the node database was built from (n8n-nodes-base, @n8n/n8n-nodes-langchain), with node counts. |
| get_nodeA | Get the schema for one node type: short name ('slack') or full type ('n8n-nodes-base.slack' / '@n8n/n8n-nodes-langchain.agent'). detail='minimal' (summary), 'standard' (default — cleaned-up properties), or 'full' (every raw property field). Use propertyQuery to search within one node's properties instead. |
| validate_nodeA | Check a node's parameters against its schema. mode='minimal' (default) checks required fields given the current resource/operation selection (respects displayOptions.show/hide — the same mechanism n8n's UI uses to decide which fields apply). mode='full' also flags unknown parameters and type mismatches as warnings. |
| validate_workflowA | Full validation of an n8n-format workflow: unknown node types, per-node required fields, connection structure (unique names, valid references, cycles, unreached nodes, missing trigger), and expression brace-balance checks. |
| validate_workflow_connectionsA | Just the structural checks: unique node names, valid connection references, cycles, unreached nodes, missing trigger node. |
| validate_workflow_expressionsA | Scan all node parameters for '{{ }}' expressions and flag unbalanced braces or empty expressions. |
| n8n_health_checkA | Verify N8N_API_URL/N8N_API_KEY are set and the instance is reachable and authenticated. |
| n8n_list_workflowsC | List workflows from your connected n8n instance. |
| n8n_get_workflowA | Fetch one workflow (full definition) by id from your connected n8n instance. |
| n8n_create_workflowA | Create a new workflow on your connected n8n instance. Consider running validate_workflow first. |
| n8n_update_workflowA | Replace a workflow's definition entirely (n8n's public API only supports full-workflow PUT, not partial/diff updates). Fetch it first with n8n_get_workflow, edit, then send the whole thing back. |
| n8n_delete_workflowB | Permanently delete a workflow from your connected n8n instance. |
| n8n_activate_workflowA | Activate (publish) a workflow so its triggers start listening. |
| n8n_deactivate_workflowC | Deactivate a workflow. |
| n8n_validate_workflowA | Fetch a workflow from your connected n8n instance by id and run full local validation against it (same checks as validate_workflow). |
| n8n_list_executionsC | List recent workflow executions. |
| n8n_get_executionC | Fetch one execution's details by id. |
| n8n_delete_executionC | Delete an execution record. |
| n8n_list_credentialsA | List credentials (metadata only — secrets are never returned by n8n's API). |
| n8n_get_credentialA | Fetch one credential's metadata by id (secrets are never returned). |
| n8n_get_credential_schemaA | Get the JSON schema (which fields are needed) for a credential type, e.g. 'slackOAuth2Api'. Use this before n8n_create_credential to know what |
| n8n_create_credentialA | Create a new credential. Check n8n_get_credential_schema first to know the required |
| n8n_delete_credentialC | Permanently delete a credential. |
| n8n_trigger_webhookA | n8n's public API has no 'run workflow now' endpoint — the real way to trigger a workflow over HTTP is calling its own Webhook/Form trigger URL directly. Provide the webhook's path (the part after /webhook/ or /webhook-test/ in the node's Production/Test URL). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/opsec12/mcp_server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server