How to Use the Weaviate MCP in LangChain

Q: How do I use Weaviate with LangChain for vector search?

You call the searchnearvector tool, passing in your target collection and the query vector. The agent then uses the results—the nearest neighbors—to proceed with its task.

Q: Can I check the full Weaviate schema using LangChain?

Yep. Just invoke getfullschema. This tool gives you a map of every collection in your instance, helping your agent know what data sources are available.

Q: What is the best way to check object metadata with Weaviate and LangChain?

Use getinstancemetadata. This tool gives you operational info about the entire Weaviate cluster, letting your agent confirm if the database itself is running correctly before attempting a query.

Q: Does Weaviate support pagination with LangChain?

Yes. The listobjects tool handles basic pagination via limit. You can build logic into your chain to loop through results if you need more than the initial set of data.

Build complex reasoning agents with LangChain and Weaviate.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Weaviate MCP to LangChain

Create your Vinkius account to connect Weaviate 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 Weaviate with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search vectors for agent decisions

The `search_near_vector` tool runs a nearest neighbor search across your collection. Your agent uses the returned object details to make its next decision, forming a reliable step in the reasoning chain. This lets you build multi-step pipelines where the output of one query becomes the input for another. The agent decides which specific Weaviate tools it needs and what order to call them.

Inspect database structure

Need to know what data exists before building the flow? Call `get_full_schema` to grab every collection definition. This lets your agent validate its understanding of the backend data model. The `get_class_schema` tool is more granular; it pulls the exact schema for a single class, so you can pass that structure directly to another part of your LangChain workflow.

Retrieve specific object metadata

`get_object_details` fetches all data attached to a known UUID. This gives the agent everything it needs about one record, so it doesn't have to guess what information is relevant. If you just need proof that an object exists and its basic info, `list_objects` lets your agent paginate through available records within a specific class.

Setup guide

Set up Weaviate 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 Weaviate 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({
    "weaviate-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 Weaviate 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 Weaviate. 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 Weaviate 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 Weaviate MCP in LangChain

You call the `search_near_vector` tool, passing in your target collection and the query vector. The agent then uses the results—the nearest neighbors—to proceed with its task.

Yep. Just invoke `get_full_schema`. This tool gives you a map of every collection in your instance, helping your agent know what data sources are available.

Use `get_instance_metadata`. This tool gives you operational info about the entire Weaviate cluster, letting your agent confirm if the database itself is running correctly before attempting a query.

Yes. The `list_objects` tool handles basic pagination via limit. You can build logic into your chain to loop through results if you need more than the initial set of data.

This server primarily deals with schema definitions, UUIDs for object identification, and floating-point arrays for vector similarity searches.

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