How to Use the Typesense Vector Search MCP in LangChain

Q: How do I query past data using Typesense Vector Search and LangChain?

You can run searchvectors against a specific collection, providing both the text query and the vector string. This lets your agent find semantically similar items from historical records.

Q: Can I update existing records in my knowledge base using Typesense Vector Search and LangChain?

Yeah, absolutely. You use the indexdocument tool, providing both the collection name and the updated JSON data. This either adds a new document or overwrites an old one.

Q: Does this MCP Server support listing all available search collections for LangChain?

Yes. The listvectorcollections tool lets you quickly see every collection configured in the Typesense instance, so you know exactly where your data lives.

Q: If I delete a document, what happens to that information within LangChain's context?

The deletedocument action is irreversible. It permanently removes the record from the collection itself, meaning it won't show up in future searches.

Connect complex reasoning chains to Typesense Vector Search with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Typesense Vector Search MCP to LangChain

Create your Vinkius account to connect Typesense Vector Search 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 Typesense Vector Search with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step search logic in LangChain.

The `search_vectors` tool lets your agent execute a vector similarity search combined with text filtering. It returns the top results directly, which you can immediately pass as context to another chain step. You'll use this capability when the answer isn't obvious; maybe the first result needs further validation against other data sources.

Manage search indices with LangChain.

Need to set up a new knowledge base? You run `create_collection` and define the exact schema needed for your searchable content. This ensures that when you eventually call `index_document`, the data fits perfectly. This structured setup lets you guarantee predictable search behavior, moving beyond simple keyword matching.

Maintain clean, up-to-date knowledge with LangChain.

If a document gets retired or updated, don't leave stale data in the system. You call `delete_document` to permanently remove it by ID. This granular control over your collection ensures that every search performed via this MCP Server uses only current records.

Setup guide

Set up Typesense Vector Search 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 Typesense Vector Search 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({
    "typesense-vector-search-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 Typesense Vector Search 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 Typesense Vector Search. 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 Typesense Vector Search 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 Typesense Vector Search MCP in LangChain

You can run `search_vectors` against a specific collection, providing both the text query and the vector string. This lets your agent find semantically similar items from historical records.

This MCP Server handles structured document data and associated vectors, which are defined by the schema you set up using `create_collection`.

Yeah, absolutely. You use the `index_document` tool, providing both the collection name and the updated JSON data. This either adds a new document or overwrites an old one.

Yes. The `list_vector_collections` tool lets you quickly see every collection configured in the Typesense instance, so you know exactly where your data lives.

The `delete_document` action is irreversible. It permanently removes the record from the collection itself, meaning it won't show up in future 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

Vercel AI SDK sdk-typescript