How to Use the Vald MCP in LangChain

Q: Can I use Vald's vector data in my LangChain workflow?

Absolutely. You can retrieve raw vector data using getvectordetails. This allows your agent to inspect the underlying knowledge base before making a final conclusion.

Q: Is there any way to check Vald's current status when building a LangChain chain?

Yes, you call getengineinfo. This tool returns operational information and health checks on the entire database engine, helping you validate that the MCP Server is running correctly.

Q: If I need to delete data, what kind of data does Vald touch?

Vald manages dense vectors. The deletevector tool permanently removes a vector based on its ID. This process handles the underlying vector arrays and associated metadata.

Build complex reasoning chains with Vald and LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vald MCP to LangChain

Create your Vinkius account to connect Vald 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 Vald with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Vector Data within Your Agent Flow

The `insert_vector` tool lets your agent add new data points to the index. It requires a unique ID and the vector as a JSON array. This ensures that every piece of information generated during a multi-step chain remains traceable. The `update_vector` function handles changes to existing records. If you need to correct or supplement a stored fact, just call this tool with the original ID and the new vector data.

Execute Targeted Knowledge Searches using Vald

Need an answer right now? Call `search_vectors` and pass your query as a JSON array of floats. This executes a nearest-neighbor search, returning vectors that match the provided data pattern. LangChain uses this output to ground its decisions. Furthermore, you can check what's stored using `get_vector_details`. Supply an ID, and the tool pulls the raw vector data right out for inspection.

Maintain System State with Vald MCP Server

The `delete_vector` action permanently removes a record from the index; remember, this is irreversible. Use caution when calling it within your LangChain logic. Also available is `get_engine_info`. Running this checks the operational health of the entire Vald engine, letting you verify stability before proceeding with complex agent tasks.

Setup guide

Set up Vald 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 Vald 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({
    "vald-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 Vald 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 Vald. 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 Vald 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 Vald MCP in LangChain

The MCP Server acts as a decision point. When your ReAct agent determines it needs external, structured knowledge, it calls the relevant Vald tool (like `search_vectors`). The output of this call becomes an intermediate result that guides the next thinking step.

If you provide a unique ID, it inserts. If you try to insert with an ID that already exists, your agent needs to handle the conflict or call `update_vector` instead. The MCP Server expects clean, unique IDs for new vectors.

Absolutely. You can retrieve raw vector data using `get_vector_details`. This allows your agent to inspect the underlying knowledge base before making a final conclusion.

Yes, you call `get_engine_info`. This tool returns operational information and health checks on the entire database engine, helping you validate that the MCP Server is running correctly.

Vald manages dense vectors. The `delete_vector` tool permanently removes a vector based on its ID. This process handles the underlying vector arrays and associated metadata.

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