How to Use the Cognee MCP in LlamaIndex

Q: How do I register the Cognee MCP Server tools inside a LlamaIndex agent?

Install the MCP tool package using pip install llama-index-tools-mcp first. Next, pass the Vinkius endpoint to BasicMCPClient and convert the tools using McpToolSpec for your agent.

Q: Can LlamaIndex query Cognee using standard natural language?

Yes, your agent calls cogneesearch with natural language queries. The tool traverses the graph and returns context-rich nodes directly to your LlamaIndex pipeline.

Q: How do I limit which Cognee tools my LlamaIndex agent can access?

You can use the allowedtools filter when initializing your McpToolSpec. This prevents the agent from running write operations when it only needs search capabilities.

Index live Cognee graph data into your LlamaIndex vector stores for hallucination-free RAG apps with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognee MCP to LlamaIndex

Create your Vinkius account to connect Cognee 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 Cognee with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build queryable indexes with this MCP Server

`cognee_add_data` ingests unstructured text directly from your LlamaIndex data loaders into the Cognee graph database. Your LlamaIndex pipeline feeds raw documents straight to this tool to prepare them for deep semantic indexing. This integration bypasses complex database configurations. You simply load your files, hand them to the tool, and let the background database handle storage.

Generate structured graph embeddings for LlamaIndex RAG

`cognee_cognify` structures your raw ingested data into a searchable knowledge graph with vector embeddings. LlamaIndex uses this tool to map out complex entity connections that standard vector search tools overlook. Once processed, your index gains deep contextual awareness. Your RAG agents query this graph structure to retrieve highly accurate answers grounded in actual, mapped facts.

Retrieve deep relational insights with LlamaIndex agents

`cognee_get_insights` extracts structured entity relationships and hidden connections from your custom knowledge base. Your LlamaIndex agent invokes this tool to understand the broader context of your data before generating answers. This process eliminates hallucinations by forcing the agent to rely on verified graph nodes. You get clean, factual responses based on actual relationships instead of probabilistic guesses.

Setup guide

Set up Cognee 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 Cognee 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 Cognee tools.",
)
response = await agent.run("List recent Cognee 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 Cognee. 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 Cognee 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 Cognee MCP in LlamaIndex

Install the MCP tool package using `pip install llama-index-tools-mcp` first. Next, pass the Vinkius endpoint to `BasicMCPClient` and convert the tools using `McpToolSpec` for your agent.

Yes, your agent calls `cognee_search` with natural language queries. The tool traverses the graph and returns context-rich nodes directly to your LlamaIndex pipeline.

Combining both systems gives you the best of both worlds. While vector stores handle simple similarity, Cognee maps complex entity relationships that LlamaIndex queries to resolve deep, multi-hop questions.

You can use the `allowed_tools` filter when initializing your `McpToolSpec`. This prevents the agent from running write operations when it only needs search capabilities.

Vinkius runs this service in an ephemeral sandbox, meaning your raw documents and generated graph data are never stored permanently on shared servers. Your private data remains completely isolated and secure.

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