flowise-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FLOWISE_API_KEY | Yes | API key for authentication | |
| FLOWISE_TIMEOUT | No | Request timeout in seconds (default: 60) | 60 |
| FLOWISE_BASE_URL | Yes | Your Flowise instance URL |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| flowise_list_flowsA | List all chatflows and agentflows in the Flowise instance. This tool retrieves a summary of all available flows, including their deployment status, visibility, and categories. Args: params: Input parameters containing optional flow_type filter and response_format. Returns: A formatted list of all flows with their basic information. Examples: - List all flows: Use with no parameters - List only agentflows: Use flow_type='AGENTFLOW' - Get JSON output: Use response_format='json' |
| flowise_get_flowA | Get detailed information about a specific chatflow or agentflow. This tool retrieves the full configuration of a flow, including all nodes, edges, and settings. Args: params: Input containing flow_id and response_format. Returns: Detailed flow information including configuration and nodes. Examples: - Get flow details: Use with the flow ID from flowise_list_flows |
| flowise_predictA | Send a message to a chatflow or agentflow and get a response. This is the primary tool for interacting with Flowise flows. It sends a question/message to the specified flow and returns the AI response. Args: params: Input containing flow_id, question, and optional session_id, streaming preference, and override_config. Returns: The response from the Flowise flow. Examples: - Simple question: Use flow_id and question - With session: Add session_id to maintain conversation context - Override settings: Use override_config to adjust temperature, etc. |
| flowise_analyze_flowA | Analyze a chatflow or agentflow and provide improvement suggestions. This tool examines the flow configuration and provides actionable recommendations for enhancing the flow's capabilities, performance, and best practices compliance. IMPORTANT: This is the primary tool for answering questions like "How can I improve this agentflow to do X?" or "What can I add to make my chatflow better at Y?" Args: params: Input containing flow_id, optional improvement_goal, and response_format. Returns: A detailed analysis with: - Current flow structure overview - Identified issues or gaps - Prioritized improvement suggestions - Best practices recommendations - Specific nodes to add or configure Examples: - General analysis: Use with just the flow_id - Targeted improvements: Add improvement_goal like "improve accuracy" - Speed optimization: Use improvement_goal="faster responses" - Add capabilities: Use improvement_goal="handle customer support queries" |
| flowise_create_flowA | Create a new chatflow or agentflow in Flowise. This tool creates a new flow with the specified configuration. The flow_data should be a valid JSON string containing the nodes and edges configuration. Args: params: Input containing name, flow_data (JSON), flow_type, is_public, and category. Returns: The created flow's details including its new ID. Examples: - Create a simple chatflow with a name and empty flow_data: '{}' - Create an agentflow: Set flow_type='AGENTFLOW' |
| flowise_update_flowA | Update an existing chatflow or agentflow. This tool updates the specified flow with new configuration. Only provided fields will be updated. Args: params: Input containing flow_id and optional fields to update. Returns: Confirmation of the update with the flow's details. Examples: - Rename a flow: Use flow_id and name - Update configuration: Use flow_id and flow_data - Make public: Use flow_id and is_public=True |
| flowise_delete_flowA | Delete a chatflow or agentflow from Flowise. WARNING: This action is irreversible. The flow and its configuration will be permanently deleted. Args: params: Input containing the flow_id to delete. Returns: Confirmation of deletion. |
| flowise_get_chat_historyA | Retrieve chat message history for a specific flow. This tool gets the conversation history from a chatflow or agentflow, useful for reviewing past interactions or debugging. Args: params: Input containing flow_id, optional session_id, limit, and response_format. Returns: List of chat messages with timestamps and content. |
| flowise_list_variablesA | List all global variables configured in Flowise. Variables can be used across flows for storing API keys, URLs, or other configuration values. Args: params: Input containing response_format. Returns: List of configured variables. |
| flowise_list_toolsA | List all tools available in Flowise. This retrieves the list of registered tools that can be used in agentflows and chatflows. Args: params: Input containing response_format. Returns: List of available tools with their descriptions. |
| flowise_pingA | Check if the Flowise server is reachable and responding. Use this tool to verify connectivity before making other requests. Returns: Server status message. |
| flowise_list_assistantsB | List all assistants configured in Flowise. Assistants are pre-configured AI agents that can be used for specific tasks. Args: params: Input containing response_format. Returns: List of configured assistants. |
| flowise_get_assistantB | Get detailed information about a specific assistant. Args: params: Input containing assistant_id and response_format. Returns: Detailed assistant information including configuration. |
| flowise_delete_chat_historyA | Delete chat message history for a specific flow. This removes conversation history from the database. Use with caution. Args: params: Input containing flow_id, optional session_id and chat_id. Returns: Confirmation of deletion. |
| flowise_list_document_storesA | List all document stores configured in Flowise. Document stores contain indexed documents for RAG (Retrieval-Augmented Generation). Args: params: Input containing response_format. Returns: List of document stores with their details. |
| flowise_get_document_storeB | Get detailed information about a specific document store. Args: params: Input containing store_id and response_format. Returns: Detailed document store information. |
| flowise_upsert_vectorB | Insert or update vectors in a chatflow's vector store. This triggers the flow's document processing pipeline to update the vector store. Args: params: Input containing flow_id, optional override_config and stop_node_id. Returns: Summary of the upsert operation results. |
| flowise_query_vector_storeA | Execute a retrieval query on a document store's vector store. This searches for relevant documents based on the query. Args: params: Input containing store_id and query. Returns: Retrieved documents with relevance information. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze_agentflow | Prompt template for analyzing an agentflow and suggesting improvements. |
| improve_chatbot | Prompt template for improving a chatbot based on a specific issue. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| list_all_flows | Resource to get all flows as a JSON list. |
Latest Blog Posts
- 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/JuliDir/flowise-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server