Flowise MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FLOWISE_API_KEY | Yes | API key from Flowise (Settings > API Keys) | |
| FLOWISE_BASE_URL | No | URL where your Flowise instance is running | http://localhost:3000 |
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 |
|---|---|
| create_predictionB | Run a Flowise chatflow with a question and get a response. Use this to interact with AI workflows configured in Flowise. |
| create_prediction_with_historyB | Run a Flowise chatflow with conversation history for context-aware responses. |
| create_prediction_with_filesB | Run a Flowise chatflow with file attachments (images, documents, etc.). |
| create_prediction_with_leadB | Run a Flowise chatflow and capture a lead email for the conversation. |
| list_chatflowsA | List all chatflows available in Flowise. Returns chatflow IDs, names, and metadata. |
| get_chatflowA | Get a specific chatflow by ID, including its full configuration with nodes and edges. |
| create_chatflowC | Create a new chatflow in Flowise with specified nodes and edges configuration. |
| update_chatflowA | Update an existing chatflow's configuration, nodes, edges, or metadata. |
| delete_chatflowA | Delete a chatflow from Flowise. This action is irreversible. |
| list_nodesA | List all available node types in Flowise that can be used to build chatflows. |
| get_nodes_by_categoryA | Get all nodes in a specific category (e.g., 'Chat Models', 'Agents', 'Memory', 'Tools'). |
| get_nodeB | Get detailed information about a specific node type by its name. |
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 12 tools
The four create_prediction variants are closely related but have distinct, clearly described purposes (base, with history, with files, with lead). Chatflow management and node exploration tools are clearly separated. The main ambiguity is choosing among the prediction variants, but context usually resolves it.
All tools follow a consistent snake_case verb_noun pattern. List/get for retrieval, create/update/delete for chatflow operations, and create_prediction for execution. Modifiers like with_history, with_files, and with_lead are appended consistently.
With 12 tools, the server is well-scoped. It covers chatflow CRUD, multiple prediction modes, and node catalog exploration without unnecessary bloat. Each tool serves a clear purpose in the Flowise domain.
The tool set provides full lifecycle coverage for chatflows (create, read, update, delete) and a good range of prediction options. It also exposes node catalog information. Minor gaps like lead management or prediction history are not core to the Flowise workflow and can be worked around.