How to Use the Mem0 MCP in LlamaIndex

Q: Can the agent fetch a complete list of user facts?

Use the getmemories tool to retrieve all stored facts associated with a user ID. This is useful for displaying a profile settings page or debugging what the agent has learned.

Ground your LlamaIndex RAG pipelines in persistent user preferences that survive across sessions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mem0 MCP to LlamaIndex

Create your Vinkius account to connect Mem0 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 Mem0 with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live preferences using `add_memory`

The `add_memory` tool saves extracted facts directly into the Mem0 database, allowing LlamaIndex to build a dynamic profile of the user. Instead of relying on static files, your query engine can now save conversational data on the fly. This integration ensures that every fact saved during a chat session is immediately searchable in subsequent index queries via the MCP standard.

Ground LlamaIndex queries with `search_memories`

The `search_memories` tool executes semantic searches across stored user facts to return the most relevant context for your current query using this MCP Server. LlamaIndex uses this tool to pull user-specific constraints before generating a response. By integrating this tool into your LlamaIndex query router, the agent can decide whether to search local documents or retrieve personal facts. This approach ensures responses are highly personalized without cluttering the main index.

Prune your LlamaIndex context using `delete_memory`

The `delete_memory` tool removes outdated facts by their unique ID, while `get_memories` retrieves the full list of stored facts for a specific user. Using these tools keeps your database clean and prevents obsolete preferences from affecting search results. LlamaIndex agents use these tools to maintain index hygiene. When a user updates their profile, the agent can fetch the full list, identify the old record, and delete it to prevent vector search noise.

Setup guide

Set up Mem0 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 Mem0 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 Mem0 tools.",
)
response = await agent.run("List recent Mem0 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 Mem0. 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 Mem0 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 Mem0 MCP in LlamaIndex

Use the BasicMCPClient to connect to the server, then wrap it with McpToolSpec. Convert them to a tool list using to_tool_list_async() and pass them to your LlamaIndex agent.

Yes, you can configure your LlamaIndex router to call search_memories for personal facts while querying a local vector store for document retrieval. This combines personal context with general knowledge.

The server uses semantic search to rank memories based on relevance to the user's query. LlamaIndex receives these ranked facts, which prevents the LLM from hallucinating outdated user information.

Use the get_memories tool to retrieve all stored facts associated with a user ID. This is useful for displaying a profile settings page or debugging what the agent has learned.

All user preferences and facts are processed within isolated Vinkius MCP sandboxes that wipe execution states instantly. Your data never touches shared storage, and access is restricted through a single secure endpoint token.

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