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

Q: Can LangChain search my Mem AI (Knowledge Workspace) semantically?

Yes. Your LangChain agent can run the searchmems tool to query your entire workspace using vector search, returning the most relevant notes directly into your chain step.

Feed your LangChain multi-step reasoning chains with context directly from your Mem AI knowledge base.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Live Context to LangChain Agents

This MCP Server lets your LangChain agent pull real-time workspace context using `get_mem` and `search_mems` to build dynamic prompts. Instead of hardcoding static documents, your reasoning chains query your actual knowledge base on the fly during execution. The output of a search tool call feeds directly into the next step of your chain. You can trace these multi-step tool calls directly in LangSmith to monitor latency and token usage. If an agent needs to verify a detail, it runs `list_collection_mems` and passes the resulting text block directly to a summarization prompt. This turns your static notes into active components of your LLM pipelines.

Automate Knowledge Capture in Chains

This MCP toolset enables your LangChain chains to write data back to your workspace using `create_mem` and `add_mem_to_collection`. When an agent finishes a complex reasoning task or summarizes a long conversation, it writes the final output directly to a new mem. You don't have to copy-paste results or manually log updates. The agent can also structure your workspace by running `create_collection` to group related outputs automatically. If a run fails or needs correction, the agent uses `update_mem` to modify the existing text. Every write operation is recorded in your LangSmith traces for debugging.

Purge and Update Workspace Records

This MCP Server gives your LangChain agents the power to clean up outdated notes using `delete_mem` and `update_mem`. When an agent processes a feed and detects duplicate information, it can replace the old text or remove the useless note entirely. This keeps your workspace clean without manual human intervention. Before modifying any data, the chain can run `get_mem` to verify the existing content and prevent accidental overwrites. You control exactly which tools the agent can access when configuring your setup. This ensures the agent only updates the collections you specify.

Setup guide

Set up Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) 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({
    "mem-ai-knowledge-workspace-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 Mem AI (Knowledge Workspace) 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 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 LangChain

Use the LangChain MCP adapter to initialize the client with your server URL. Call the get tools method and pass them directly to your agent constructor to start querying your workspace.

Yes. Your LangChain agent can run the `search_mems` tool to query your entire workspace using vector search, returning the most relevant notes directly into your chain step.

LangChain runs tool calls sequentially or in parallel depending on your graph design. It can invoke `create_mem` multiple times, but you should monitor rate limits during heavy runs.

LangSmith captures the failure, showing the exact input passed to `get_mem` or `update_mem`. You can handle the error in your chain logic to retry or skip.

This MCP server runs in a secure V8 isolate sandbox that handles authentication via a single endpoint token. Your raw markdown notes and collection structures never pass through third-party servers.

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