How to Use the Cradl AI MCP in LangChain

Q: How do I use Cradl AI with LangChain?

Install langchain-mcp-adapters and langgraph. Pass the Vinkius endpoint to MultiServerMCPClient and hand the tools to your ReAct agent.

Q: Can LangChain agents track Cradl AI processing status?

Agents call gettaskstatus in a loop or scheduled chain until the document completes. They read the confidence scores directly from the output.

Q: How do I find specific Cradl AI models in LangChain?

Give your agent access to searchmodelsbyname. It queries the model registry dynamically before deciding which extraction schema to apply.

Build multi-step document extraction pipelines in LangChain using this Cradl AI 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 Cradl AI MCP to LangChain

Create your Vinkius account to connect Cradl AI 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 Cradl AI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain document parsing in LangChain

ReAct agents need structured inputs to make decisions. You give your agent the `extract_data_from_url` tool, and it pulls raw text from a PDF invoice. That output feeds directly into your next chain link. The agent checks the extraction results via `get_task_status`, pulling confidence scores to decide if human review is necessary.

Build complex MCP Server workflows

Complex document processing requires flow control. Your graph pulls flow configurations using `get_flow_details` to determine routing rules dynamically. LangSmith traces every single call. You see exactly how long `list_processing_tasks` takes and how many tokens your agent burns parsing the status payloads.

Manage extraction batches programmatically

Processing thousands of files means you need batch awareness. The agent calls `list_batches` to find pending jobs, then iterates through them. Digging deeper is just another tool call. Passing those batch IDs into `get_batch_details` returns processing summaries, letting your agent compile a final report for the end user.

Setup guide

Set up Cradl AI 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 Cradl AI 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({
    "cradl-ai-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 Cradl AI 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 Cradl AI. 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 Cradl AI 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 Cradl AI MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph`. Pass the Vinkius endpoint to `MultiServerMCPClient` and hand the tools to your ReAct agent.

Agents call `get_task_status` in a loop or scheduled chain until the document completes. They read the confidence scores directly from the output.

Tool inputs and outputs are fully observable. Every call to `extract_data_from_url` logs latency and payload data right in your LangSmith dashboard.

Give your agent access to `search_models_by_name`. It queries the model registry dynamically before deciding which extraction schema to apply.

Vinkius runs this integration in a V8 Isolate Sandbox. Raw document URLs and extracted key-value pairs pass through an ephemeral, zero-trust connection that leaves no persistent trace on 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