node-red-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NODE_RED_URL | Yes | URL of your Node-RED instance | |
| NODE_RED_TOKEN | No | API access token for Node-RED (optional) | |
| MCP_SERVER_PORT | No | Port for the MCP server (optional) |
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
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 20 tools
Without descriptions, several tools appear to have overlapping purposes (e.g., get-flows, get-flows-formatted, get-flows-state; search-nodes and find-nodes-by-type). This ambiguity could cause an agent to select the wrong tool.
All tool names follow a consistent hyphen-case pattern with a clear verb_noun structure (e.g., create-flow, get-flows, set-flows-state). The naming is uniform and predictable.
With 20 tools, the server covers a broad range of Node-RED operations. While the count is slightly high, it remains within a reasonable scope for a comprehensive administration tool.
The tool set includes flow CRUD, node management, state control, diagnostics, and settings. However, operations like flow export/import or detailed debugging are missing, leaving notable gaps for full lifecycle management.