# FlowiseAI MCP for AI Agents AI Agent Connect

> FlowiseAI lets you connect your self-hosted Flowise instance to your AI client. You can trigger chatflows, manage RAG pipelines, and update vector stores using natural language. It turns your agent into a coordinator for your entire LLM orchestration setup.

## Overview
- **Category:** friends-mcp
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_lh0zyPoJJj1xxwGDq27KDGRA6H9DV4YmiVFcM13z/ai-agent-connect
- **Tags:** llm-workflows, rag-pipelines, chatbot-development, visual-programming, ai-agents, low-code

## Description

FlowiseAI lets you connect your self-hosted Flowise instance to your AI client to handle complex LLM orchestration and RAG workflows through simple conversation. If you've built intricate chatflows or multi-step agents, you know how tedious it is to jump between the visual builder and your testing environment. This Connector removes that friction. You can trigger specific chatflows and get back responses using just natural language, making it much easier to test logic on the fly. It also gives your agent the ability to push new documents or raw data into your vector stores, which keeps your RAG context accurate without manual file uploads. You can keep a pulse on your production environment by asking for lead reports or user feedback directly in your chat. It even lets you manage global variables and credentials across your entire ecosystem. Because Vinkius hosts this Connector, you can plug it into your existing setup and start managing your flows from a single window. Your agent becomes the coordinator for your entire LLM infrastructure, handling the heavy lifting of interacting with the Flowise backend so you can focus on the logic. You can also inspect the technical structures of any flow to see exactly how the nodes are connected and what metadata is being passed. Instead of clicking through dozens of nodes to find a specific variable, your agent can pull that info for you instantly. This setup is perfect for moving from prototype to production because it gives you a direct line to your Flowise backend.

## Tools

### list_chatflows
List all LLM orchestration flows. Use this to see what's currently active in your Flowise instance.

### list_flowise_credentials
List configured credentials. This helps you manage access keys across your entire environment.

### list_chat_feedback
List user feedback for a chatflow. Use this to see what your users actually think of your bots.

### list_flow_leads
List captured leads. It's a quick way to see who is interacting with your AI flows.

### list_external_tools
List custom tools. Use this to understand what extra actions your agent can take.

### execute_chatflow_prediction
Trigger an LLM flow prediction. This lets your agent actually run the logic and give you an answer.

### upsert_vector_data
Push data into a vector store. It keeps your RAG context fresh without manual uploads.

### get_chatflow_details
Get details for a specific chatflow. This is great for deep-diving into how a flow is built.

### get_server_version
Get Flowise version. Use this to ensure your instance is up to date.

### list_ai_assistants
List your OpenAI-style assistants. This helps you keep track of all the specialized agents you've built.

### list_marketplace_templates
List chatflow templates. This helps you find starting points for new projects.

### list_flow_variables
List global variables. This helps you manage settings that apply to your entire Flowise setup.

## Prompt Examples

**Prompt:** 
```
Show me all the chatflows I have in Flowise.
```

**Response:** 
```
I've retrieved your active flows. Here is what's currently set up:

| Flow Name | ID | Status |
| :--- | :--- | :--- |
| Customer Support | cf_01 | Active |
| RAG Knowledge Base | cf_02 | Active |
| Lead Gen Bot | cf_03 | Active |

Would you like to see the details for any of these?
```

**Prompt:** 
```
Run the 'Customer Support' flow and ask 'How do I reset my password?'
```

**Response:** 
```
**Prediction Complete!**

The bot responded: 
> "To reset your password, please go to the login screen and click on 'Forgot Password'. You'll receive an email with further instructions."

I can also pull the user feedback for this flow if you'd like to see how others are reacting.
```

**Prompt:** 
```
Add this new product description to the RAG store for the 'RAG Knowledge Base' flow.
```

**Response:** 
```
✅ **Data Ingested!**

I've successfully pushed the new product description into the vector store associated with the RAG Knowledge Base flow. The new context is now available for your agent to use in future predictions.
```

## Capabilities

### Trigger chatflows with natural language
Run specific LLM flows and get responses back without leaving your chat window.

### Update vector stores automatically
Push new data into your RAG context to keep your agent's knowledge fresh.

### Monitor leads and feedback
Pull reports on user interactions and captured leads directly into your conversation.

### Manage flow variables
Adjust global settings and credentials for your entire Flowise environment.

### Inspect flow structures
Get the technical metadata and node details for any orchestration flow.

## Use Cases

### Testing RAG accuracy
A developer asks the agent to run a specific flow with a test prompt to see if the vector store is returning the right context.

### Automated data ingestion
A data engineer tells the agent to push a new batch of documents into the vector store for a specific chatflow.

### Lead tracking
A product manager asks for a summary of all leads captured in the last 24 hours from the Sales Bot flow.

### Flow auditing
An admin asks the agent to list all active chatflows to see what's currently live in the production environment.

## Benefits

- Run chatflows without the UI: Trigger specific flows and get answers back instantly without clicking through nodes.
- Keep context fresh: Push new documents into your vector stores automatically to keep your RAG data accurate.
- Monitor leads in real time: Get a list of captured leads and user feedback directly in your chat window.
- Inspect flow logic: View the technical structure and metadata of any flow to understand how it's built.
- Manage environment settings: Control global variables and credentials across your entire Flowise setup easily.

## How It Works

The bottom line is you get a way to run and manage your Flowise workflows without leaving your chat window.

1. Connect your Flowise instance URL and API key to your AI client.
2. Tell your agent which chatflow to run or what data to push to your vector store.
3. Receive the LLM response or confirmation of the update in your chat window.

## Frequently Asked Questions

**Can I use FlowiseAI with my existing self-hosted setup?**
Yes. You just need to provide your Flowise instance URL and your API key. The Connector will then connect your AI client directly to your backend.

**How does FlowiseAI help with RAG pipelines?**
It allows your agent to push new data into your vector stores automatically. This keeps your RAG context fresh without you having to manually upload files.

**Can my agent see the leads I've collected?**
Yes, it can. You can ask your agent to list captured leads from any of your active flows to see who is interacting with your bots.

**Does FlowiseAI work with any AI client?**
It works with any MCP-compatible client, including Claude, Cursor, and Windsurf, giving you a unified way to manage your flows.

**How do I update my vector store data using FlowiseAI?**
Simply tell your agent to push the data you want to update. It will handle the communication with your Flowise instance to update the vector store.

**Can I see the technical details of my flows?**
Yes. You can ask your agent to pull the technical structure and metadata for any specific flow to see exactly how it's built.

**How do I find my API Key in Flowise?**
Log in to your Flowise dashboard and click on the **API Keys** tab in the sidebar to generate or copy your unique token.

**Does this support multi-tenant instances?**
Yes! Ensure you provide the full Instance URL and the API Key corresponding to the specific environment you want to manage.

**Can I push documents to vector stores via AI?**
Absolutely. Use the `upsert_vector_data` tool by providing the `chatflow_id` and the JSON payload containing your document data.