How to Use the FlowiseAI MCP in LangChain

Q: Can my LangChain agent trigger visual RAG pipelines in FlowiseAI?

Yes, your agent uses the executechatflowprediction tool to run any visual flow you have configured. You can also push fresh raw text into your vector stores using upsertvectordata during the chain execution.

Q: Does LangChain support passing variables to FlowiseAI flow templates?

Yes. Your agent can query active variables using listflowvariables and then pass those parameters when initiating a run. This keeps your runtime configurations completely dynamic.

Q: How do I debug visual flow failures within my LangChain code?

You can run getchatflowdetails to check the node structure and verify inputs. Since Vinkius handles the transport, you can also use LangSmith to trace the exact input and output payloads of each tool.

Q: How does Vinkius protect my FlowiseAI credentials data?

All API keys and environment variables used in listflowisecredentials run inside a zero-trust, ephemeral V8 isolate sandbox. Your connection token is never shared, and credentials are encrypted at rest, preventing any raw key exposure to your LLM agent.

Run visual FlowiseAI chatflows directly inside your LangChain reasoning loops using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FlowiseAI MCP to LangChain

Create your Vinkius account to connect FlowiseAI to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup FlowiseAI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain live predictions into LangChain loops

LangChain agents can fire off your visual pipelines on demand. Instead of rebuilding complex prompt chains in raw Python, you call `execute_chatflow_prediction` to run a visual flow you already built. This lets you combine drag-and-drop flexibility with code-level control. You can inspect the setup of any flow using `get_chatflow_details` before running it. This ensures your LangChain agent always passes the exact variables your visual flow expects, keeping your runtime execution error-free.

Manage vector pipeline updates via MCP Server tools

Keeping your vector databases fresh doesn't require separate ingestion scripts. Your LangChain agent can use `upsert_vector_data` to push new documents directly into your visual RAG pipelines. It keeps your knowledge base updated without manual intervention. Querying active setups lets your agent reference pre-configured visual architectures on the fly during complex multi-step chains by calling `list_marketplace_templates`.

Inspect active configurations and credentials

Your LangChain agent can query the system to see what assets are already configured. By calling `list_flowise_credentials` and `list_flow_variables`, the agent understands the environment limits and available keys before trying to run a heavy task. This MCP Server integration allows you to trace every tool call inside LangSmith. You see exactly when a credentials list was checked or when a variable was pulled, making debugging visual flows inside code-heavy chains incredibly straightforward.

Setup guide

Set up FlowiseAI MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes FlowiseAI tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "flowiseai-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent FlowiseAI transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by FlowiseAI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect FlowiseAI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about FlowiseAI MCP in LangChain

Install langchain-mcp-adapters and langgraph via pip. Initialize a MultiServerMCPClient pointing to the Vinkius endpoint, and then pass the tools from get_tools() directly into your agent constructor.

Yes, your agent uses the `execute_chatflow_prediction` tool to run any visual flow you have configured. You can also push fresh raw text into your vector stores using `upsert_vector_data` during the chain execution.

Yes. Your agent can query active variables using `list_flow_variables` and then pass those parameters when initiating a run. This keeps your runtime configurations completely dynamic.

You can run `get_chatflow_details` to check the node structure and verify inputs. Since Vinkius handles the transport, you can also use LangSmith to trace the exact input and output payloads of each tool.

All API keys and environment variables used in `list_flowise_credentials` run inside a zero-trust, ephemeral V8 isolate sandbox. Your connection token is never shared, and credentials are encrypted at rest, preventing any raw key exposure to your LLM agent.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript