How to Use the Activepieces MCP in LangChain

Q: How do I install the Activepieces MCP Server for LangChain?

Run pip install langchain-mcp-adapters langgraph. Then set up a MultiServer client pointing to your Vinkius endpoint. Call client.gettools() to inject the Activepieces tools into your agent.

Q: Can LangChain agents modify Activepieces project settings?

Yes. Your agent can call updateproject to change settings or createprojectrelease to push new versions. The MCP integration lets your agent handle the configuration state automatically.

Q: How do I pass Activepieces output to another tool in my chain?

ReAct agents handle this natively. The output from getflow returns as a string or JSON, which LangChain automatically formats as the input for your next tool call.

Build multi-step reasoning pipelines that manage Activepieces workflows directly from your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Activepieces MCP to LangChain

Create your Vinkius account to connect Activepieces 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 Activepieces with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Building Activepieces Flows in LangChain

Your ReAct agents need to build and modify automation paths on the fly. By connecting this MCP Server, your agent can call `create_flow` to set up a new sequence and immediately use the output to `apply_flow_operation` for adding specific actions. The agent decides the exact order of operations based on intermediate results. Everything gets tracked through LangSmith. You see exactly how long the agent took to `get_flow` or `delete_flow` during its reasoning loop. Passing these tools into a custom chain means your agent handles the entire lifecycle of an automation project without human input.

Managing Auth States Dynamically

Automations fail when credentials expire. You can build a LangChain pipeline that monitors connection health and uses `upsert_app_connection` to push new OAuth2 or basic auth tokens. The agent pulls the current list with `list_app_connections` and compares it against your internal database. Instead of manual updates, the agent handles the rotation. It grabs the expired connection ID, generates a new token via another tool in your chain, and updates the Activepieces backend. The flow never stops running.

Debugging Flow Runs Automatically

When a workflow fails, your agent can investigate the execution logs. It triggers `list_flow_runs` to find recent errors, then dives into the specifics with `get_flow_run`. The detailed execution data becomes context for the next step in your LangChain pipeline. The agent reads the error logs from the run, figures out which step failed, and can even alert your team or attempt a fix. You get a self-healing automation system built entirely on standard tool calls.

Setup guide

Set up Activepieces 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 Activepieces 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({
    "activepieces-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 Activepieces 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 Activepieces. 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 Activepieces 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 Activepieces MCP in LangChain

Run `pip install langchain-mcp-adapters langgraph`. Then set up a MultiServer client pointing to your Vinkius endpoint. Call `client.get_tools()` to inject the Activepieces tools into your agent.

Yes. Your agent can call `update_project` to change settings or `create_project_release` to push new versions. The MCP integration lets your agent handle the configuration state automatically.

ReAct agents handle this natively. The output from `get_flow` returns as a string or JSON, which LangChain automatically formats as the input for your next tool call.

LangSmith traces every single call. You will see exact token usage and execution times for operations like `list_records` or `apply_flow_operation`.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. When your agent calls `upsert_app_connection` to pass OAuth2 credentials, that sensitive auth data hits the Activepieces API and the sandbox is destroyed. Nothing persists in our infrastructure.

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