How to Use the DeepAI MCP in LangChain

Chain image generation and editing tasks directly into your LangChain agent pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepAI MCP to LangChain

Create your Vinkius account to connect DeepAI 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 DeepAI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build visual reasoning chains with LangChain

Your LangChain agent uses `generate_image` to create assets based on intermediate logic. It then pipes those results into other nodes to refine the output. This MCP Server lets you link visual tasks directly into your existing chains. You track every step of the process through LangSmith to monitor how your agent handles image inputs.

Batch process images via LangChain sequences

Use `super_resolution` to sharpen assets automatically after they pass through your data pipelines. You define the sequence once and let the agent manage the flow. Input data from your vector stores triggers these visual adjustments. The agent decides when to upscale based on the specific requirements of your current task.

Automated creative workflows for LangChain

Call `remove_background` or `colorize_image` as part of a larger autonomous loop. You set the criteria and the agent executes the operations in order. Everything stays within your code-based framework. You maintain control over the execution order while the tools handle the heavy lifting.

Setup guide

Set up DeepAI 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 DeepAI 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({
    "deepai-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 DeepAI 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 DeepAI. 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 DeepAI 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 DeepAI MCP in LangChain

You connect the server as a tool resource within your LangChain agent setup. It exposes specific functions that your code calls during execution.

Yes, you build a loop in your chain that iterates through your image list. The agent triggers the tool for each file until the task finishes.

LangChain stores tool outputs in your defined memory modules. You can reference past image generation results in later steps of your conversation.

Your images are processed transiently through the Vinkius sandbox. We do not store your source files or generated assets after the session ends.

Every request requires a unique Vinkius endpoint token. Your data stays isolated within an ephemeral environment that clears upon disconnection.

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

Mastra AI sdk-typescript

Start using the DeepAI MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started