How to Use the Indy MCP in LangChain

Build complex freelance automation chains in LangChain using Indy to link lead intake, contracts, and invoicing directly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Indy MCP to LangChain

Create your Vinkius account to connect Indy 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 Indy with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Indy actions in LangChain

Feed the output of `list_forms` directly into your agent's decision logic to trigger follow-up tasks. You can map form IDs to specific client onboarding sequences without writing manual glue code. Your agent parses the JSON response from `list_records` to determine if a project is ready for invoicing. It creates a seamless pipeline where business data triggers actions in your LangGraph workflow.

Automate event-driven business logic

Use `create_webhook` to push real-time updates from Indy into your LangChain agent. This keeps your state machine updated whenever a client signs a contract or submits a new form. Your pipeline reacts instantly to incoming data. You avoid polling for changes because the server pushes updates directly to your agent's event loop.

Query Indy data within your MCP Server

Access client details with `get_user` or `get_record` to ground your agent's responses in actual business facts. You gain total visibility into account status without leaving your development environment. Every tool call provides structured data for your chains. Your agent makes decisions based on the exact state of your freelance business retrieved via this MCP Server.

Setup guide

Set up Indy 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 Indy 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({
    "indy-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 Indy 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 Indy. 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 Indy 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 Indy MCP in LangChain

Yes. You can use the MCP Server to fetch records and trigger invoice creation logic within your chain.

Install the required adapters and initialize the client using the server URL. Pass the Indy tools to your agent constructor to start executing business operations.

The server remains stateless, but you can maintain context by using the client session features. This allows your agent to remember previous tool interactions during long-running tasks.

Yes. Every tool execution is traced, allowing you to monitor latency and token usage for all business operations.

Your data is only accessed when your agent calls a specific tool. The server handles authentication tokens locally, ensuring your client details remain isolated.

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