How to Use the Cognita (RAG Framework) MCP in LangChain

Run multi-step Cognita (RAG Framework) pipelines inside your LangChain ReAct agents with full LangSmith tracing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognita (RAG Framework) MCP to LangChain

Create your Vinkius account to connect Cognita (RAG Framework) 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 Cognita (RAG Framework) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed LangChain pipelines with `rag_query` data

The `rag_query` tool pulls active arrays from rented transformation vectors straight into your LangChain run. This MCP Server setup means the output of your RAG search instantly becomes the prompt input for the next step in your custom agentic chain. You can trace this entire data flow in LangSmith to monitor latency and exact token usage. This setup keeps your multi-step reasoning pipelines fast and transparent without guessing which vector data got pulled.

Inspect Cognita models directly from your agent

The `list_models` tool inspects deep internal arrays to check picture constraints before your chain executes. LangChain agents use this check to choose the right model on the fly based on current pipeline constraints. No more hardcoded model names in your Python scripts. Your agent makes the decision dynamically, routing the payload based on what the server reports back.

Dynamic data ingestion in LangChain chains

The `ingest_data` tool provisions a JSON payload to generate new resource directories during active chain runs. LangChain passes raw inputs from previous steps directly to this tool, updating your knowledge base on the fly. Combining this with LangChain's multi-server MCP client aggregation lets you pull from one source and write to Cognita instantly. Your workflows stay completely autonomous.

Setup guide

Set up Cognita (RAG Framework) 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 Cognita (RAG Framework) 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({
    "cognita-rag-framework-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 Cognita (RAG Framework) 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 Cognita. 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 Cognita (RAG Framework) 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 Cognita (RAG Framework) MCP in LangChain

You configure LangSmith to monitor your chain. When the LangChain agent calls `rag_query` or `get_collection` on this MCP Server, the input, output, and execution latency show up instantly in your LangSmith dashboard. This gives you complete visibility into how your RAG pipeline behaves.

Yes. You register this MCP server alongside other LangChain integrations in your MultiServerMCPClient. The agent queries Cognita using `rag_query` and then writes those results directly to another store in a single execution loop.

The langchain-mcp-adapters package handles the underlying communication. If the connection drops, your LangChain run throws a standard tool execution error, allowing you to use native LangGraph retry policies.

You install langchain-mcp-adapters and langgraph via pip. Then, initialize the client using the HTTP transport pointing to your Vinkius endpoint.

Your active payloads and cloud logs stay inside the secure Vinkius V8 sandbox. We never store or inspect the data passing through `ingest_data` or `get_collection`. Everything runs in an ephemeral MCP environment that wipes clean as soon as your LangChain session ends.

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