How to Use the Affinda MCP in LangChain

Build structured data extraction chains in LangChain using Affinda’s document parsing tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Affinda MCP to LangChain

Create your Vinkius account to connect Affinda 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 Affinda with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Document parsing with LangChain

Feed PDFs directly into your agents using `create_document`. The agent waits for the response, pulling structured JSON out of messy files without you writing custom regex patterns. Chain this output into your next node. Your LangChain logic handles the flow while this MCP server manages the heavy lifting of OCR and field mapping.

Manage your workspace documents

Use `list_documents` to pull a manifest of everything currently in your account. You can track processing status across your entire pipeline without leaving your code. This gives you a clear audit trail. If a document is stuck or finished, your agent knows exactly what to do next based on the status code returned.

Identify supported parsing models

Call `list_document_types` to see if your current workspace is configured for resumes, invoices, or passports. You avoid runtime errors by checking what the server expects before sending files. Your agent adapts to the account settings dynamically. It keeps your LangChain logic clean and focused on the task at hand.

Setup guide

Set up Affinda 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 Affinda 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({
    "affinda-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 Affinda 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 Affinda. 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 Affinda 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 Affinda MCP in LangChain

You use the langchain-mcp-adapters package to bridge the connection. Once you instantiate the client, you pass the tools directly into your agent definition.

Yes. Every tool call returns valid JSON that fits right into your existing chains. You can pass the output of `get_document` to any downstream function.

It does. Because the tool execution is synchronous, the agent waits for the parsing to finish before moving to the next step in your sequence.

They live in your Affinda account workspaces. You can view them all using the `list_workspaces` tool within your script.

Your files remain in your private workspace. The MCP server only acts as a pass-through for the parsing service, ensuring your document content is handled only for the requested extraction.

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