How to Use the Wolai MCP in LangChain

Q: How does LangChain access Wolai page content?

Your agent uses getpage to pull down the full details of a specific Wolai page. It can then call listblocks on that page to see exactly what kind of content—text, embeds, or images—it contains.

Q: What if I need to check user roles?

You simply call listusers. The agent receives the full roster, allowing it to determine which specific permissions are needed before attempting a write or read operation on Wolai.

Q: Does LangChain handle complex workflows with Wolai?

Absolutely. By chaining tools like getdatabase and then querydatabase, you build automated processes that go far beyond simple single-tool calls.

Build multi-step reasoning agents with LangChain and Wolai's 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 Wolai MCP to LangChain

Create your Vinkius account to connect Wolai 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 Wolai with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

MCP Server: Complex, Multi-Step Operations

The `list_pages` tool lets your agent start by mapping out the entire structure of your knowledge base. After getting a list of pages, it can then decide which one needs more data and call `get_page` to pull the specific details. This chaining capability means you don't just run one query; your AI client builds an entire operational flow. The output from listing all Wolai databases feeds directly into calling `query_database`, letting you execute complex, multi-step tasks.

Agent Decision Making

The agent decides the exact sequence of actions needed to answer a user query. If the first attempt using `get_workspace_info` fails, the agent doesn't stop; it tries an alternative path like calling `list_users` instead. This allows you to build truly adaptive workflows where the system reasons about its own failures and adjusts the tool calls in real-time. It’s building a reliable pipeline with Wolai.

Structured Data Interaction

You can programmatically interact with both text and structured data types. For instance, you use `get_database` to understand the available schemas first. Then, your agent uses that knowledge to safely execute a precise `query_database` call. This process guarantees that every tool invocation is informed by the data structure itself, making your multi-server MCP Server calls predictable and safe.

Setup guide

Set up Wolai 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 Wolai 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({
    "wolai-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 Wolai 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 Wolai. 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 Wolai 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 Wolai MCP in LangChain

Your agent uses `get_page` to pull down the full details of a specific Wolai page. It can then call `list_blocks` on that page to see exactly what kind of content—text, embeds, or images—it contains.

Yes. Because the MCP Server handles many tools, you can combine Wolai's data with other APIs in a single chain. You aren't limited to just one type of information source.

You simply call `list_users`. The agent receives the full roster, allowing it to determine which specific permissions are needed before attempting a write or read operation on Wolai.

Absolutely. By chaining tools like `get_database` and then `query_database`, you build automated processes that go far beyond simple single-tool calls.

The Wolai MCP Server touches page content, database schemas, and user lists. All interactions are managed through the defined tools.

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