How to Use the Ada MCP in LangChain

Q: Can my LangChain agent read Ada articles?

Yes. The listarticles tool returns your entire help catalog. Your agent parses this array to determine if the bot needs updated training data.

Build complex reasoning chains for your Ada support data using LangChain and this managed MCP endpoint.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ada MCP to LangChain

Create your Vinkius account to connect Ada 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 Ada with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Ada knowledge base updates

The `create_article` tool lets your LangChain ReAct agents write directly to your Ada knowledge base. Your agent decides when a customer query lacks documentation, drafts the text, and pushes the update as a single reasoning step. You track the exact token usage and latency of this MCP Server interaction through LangSmith. If an agent hallucinates a title, the trace shows exactly what inputs went into the tool call.

LangChain agents reading support chats

Calling `list_conversations` feeds active and past Ada bot interactions straight into your evaluation chains. The output of this tool becomes the input for a sentiment analysis node further down your pipeline. Developers string together hundreds of integrations alongside this data. You pull a transcript, check the customer sentiment, and trigger an alert if the bot failed to resolve the issue.

Pull end user profiles dynamically

The `get_end_user` tool pulls custom metavariables for specific profiles so your agent has context before deciding its next move. You pass the End User ID and the node outputs raw JSON into your prompt template. Combining this with MultiServerMCPClient means you cross-reference Ada profiles with your internal billing database in the same graph. The agent aggregates data from both sources before generating a final response.

Setup guide

Set up Ada 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 Ada 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({
    "ada-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 Ada 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 Ada. 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 Ada 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 Ada MCP in LangChain

Run pip install langchain-mcp-adapters langgraph in your terminal. Use MultiServerMCPClient with the Vinkius HTTP transport URL to load the tools. Call client.get_tools() and pass them to your create_agent function.

Yes. The list_articles tool returns your entire help catalog. Your agent parses this array to determine if the bot needs updated training data.

Every request to the MCP Server logs automatically in LangSmith. You see the exact inputs sent to create_article and the latency of the API response.

LangChain agents are stateless by default. You need to call client.session() to keep the connection persistent when fetching multiple conversation histories.

End user IDs and conversation transcripts process inside a V8 Isolate Sandbox. The managed environment is completely zero-trust and ephemeral. We wipe the memory the moment your API request finishes.

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