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

Q: Can I filter which Cognita (RAG Framework) tools LlamaIndex can access?

Yes. The MCP client supports an allowedtools filter. You restrict your LlamaIndex agent to only use ragquery and listcollections while blocking ingestion tools.

Q: Does LlamaIndex support resource loading from Cognita (RAG Framework)?

Yes, by setting includeresources=True during your initialization of the MCP tool spec. This lets your LlamaIndex agent read the underlying RAG structures directly as document nodes.

Index Cognita (RAG Framework) outputs into LlamaIndex vector stores for hallucination-free querying.

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 LlamaIndex

Create your Vinkius account to connect Cognita (RAG Framework) to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index `search_chunks` into LlamaIndex memory

The `search_chunks` tool exports active presets by enumerating structured rules directly into your LlamaIndex knowledge base. Your agent immediately indexes this live API data, turning temporary RAG results into a searchable memory store. This process prevents your LlamaIndex agent from hallucinating when querying historical runs. It grounds every response in the exact structured rules returned by the MCP Server.

Track routing limits with `list_collections`

The `list_collections` tool identifies bounded routing spaces inside the headless Cognita RAG limit for your LlamaIndex query engine. This check happens before any semantic search runs, ensuring your agent never queries empty space. LlamaIndex maps these routing spaces directly to its internal query routers. This keeps your search operations highly targeted and prevents waste.

Map data sources to LlamaIndex indexers

The `list_data_sources` tool extracts structural properties driving active buckets so your LlamaIndex documents stay aligned with the backend. Your agent reads these properties to discover which buckets need indexing. You don't have to manually configure data paths anymore. The agent queries this tool, grabs the bucket layout, and updates the local vector index automatically.

Setup guide

Set up Cognita (RAG Framework) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Cognita (RAG Framework) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Cognita (RAG Framework) tools.",
)
response = await agent.run("List recent Cognita (RAG Framework) data")

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 LlamaIndex

You use McpToolSpec from llama-index-tools-mcp to load the tools. When your agent calls `search_chunks`, you can feed the resulting presets directly into your LlamaIndex vector store indexer.

Yes. The MCP client supports an allowed_tools filter. You restrict your LlamaIndex agent to only use `rag_query` and `list_collections` while blocking ingestion tools.

Yes, by setting include_resources=True during your initialization of the MCP tool spec. This lets your LlamaIndex agent read the underlying RAG structures directly as document nodes.

You need to install llama-index-tools-mcp via pip. This package gives you the BasicMCPClient which connects directly to the Vinkius HTTP endpoint.

Your active buckets and structured rules are isolated within the Vinkius zero-trust sandbox. No data is stored on our servers, and all transactions are encrypted in transit. Once your LlamaIndex session disconnects, the ephemeral MCP environment is destroyed.

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