How to Use the Mem AI (Knowledge Workspace) MCP in LlamaIndex

Q: Can LlamaIndex index my Mem AI (Knowledge Workspace) notes?

Yes. LlamaIndex can run listmems to retrieve your raw notes and index them into a local vector store for semantic search.

Q: How does semantic search work with Mem AI (Knowledge Workspace) and LlamaIndex?

The agent can bypass local indexing and call searchmems directly. This uses the native vector search to find relevant notes instantly.

Q: Can LlamaIndex agents create new collections in my workspace?

Yes. By calling createcollection, the agent can set up new thematic groupings and then use addmemtocollection to organize notes.

Build knowledge-augmented LlamaIndex RAG pipelines that search, retrieve, and index your Mem AI workspace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mem AI (Knowledge Workspace) MCP to LlamaIndex

Create your Vinkius account to connect Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Workspace Data for RAG

This MCP Server feeds live data from your workspace into LlamaIndex vector stores using `list_mems` and `get_mem`. Instead of working with static local markdown files, your RAG applications query live notes directly from the API. The retrieved data is indexed on the fly to ground agent responses in actual facts. Your agent can run `search_mems` to find relevant context before answering a user query. This eliminates hallucinations by ensuring the LLM only references validated workspace documents. You get highly accurate answers based on the most up-to-date information in your account.

Build Searchable LlamaIndex Knowledge Bases

This MCP toolset lets your LlamaIndex agents organize retrieved notes using `list_collections` and `get_collection`. The agent reads the existing structure of your workspace to understand how your notes are grouped. This contextual metadata is then used to filter search results and improve retrieval precision. By calling `list_collection_mems`, the agent pulls all notes from a specific thematic group to build a focused index. You can restrict the agent's focus to a single collection during a query session. This keeps search results highly relevant to the task at hand.

Structure and Write Retrieved Context

This MCP Server allows your LlamaIndex pipelines to write new insights back to your workspace using `create_mem` and `add_mem_to_collection`. When your RAG pipeline synthesizes information from multiple sources, it can save the summary as a new note. This makes the generated knowledge immediately searchable for future queries. If the agent needs to update an existing summary, it runs `update_mem` to replace the old text with fresh data. The agent can also use `mem_it` for quick captures during a retrieval session. This creates a continuous feedback loop where your knowledge base grows smarter over time.

Setup guide

Set up Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) tools.",
)
response = await agent.run("List recent Mem AI (Knowledge Workspace) 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 Mem.ai. 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 Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) MCP in LlamaIndex

Initialize the LlamaIndex MCP client with the server URL and wrap it in the tool spec helper. Convert it using the async tool list method and pass the tools to your FunctionAgent.

Yes. LlamaIndex can run `list_mems` to retrieve your raw notes and index them into a local vector store for semantic search.

The agent can bypass local indexing and call `search_mems` directly. This uses the native vector search to find relevant notes instantly.

Yes. By calling `create_collection`, the agent can set up new thematic groupings and then use `add_mem_to_collection` to organize notes.

This MCP setup processes data locally in your runtime environment. Your private text blocks and collection lists are fetched directly from the API using an ephemeral token, ensuring no data is cached externally.

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