How to Use the Mem0 MCP in LangChain

Q: How does LangChain handle search scores from Mem0?

When the agent calls searchmemories, the server returns a ranked list of facts with relevance scores. LangChain feeds these records directly into the prompt context, letting the agent prioritize the most relevant facts.

Q: Can I delete specific facts if a user changes their mind?

Use the deletememory tool with the specific memory ID to clear out old data. The agent can trigger this during a conversation when a user explicitly contradicts a previously saved preference.

Give your LangChain agents a memory that actually sticks across runs instead of wiping the slate clean every time.

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 LangChain

Create your Vinkius account to connect Mem0 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 Mem0 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build persistent LangChain runs with `add_memory`

The `add_memory` tool extracts structured facts from LangChain chain outputs and commits them to long-term storage under a specific user ID. Every time a user tells your agent a preference, this tool intercepts the raw text, pulls out the actual data, and saves it. LangChain handles this by linking this MCP Server directly to your agent's decision loop. You don't have to write custom database code to track user preferences between different executions of your LangGraph workflows.

Search Mem0 inside your LangChain chains

The `search_memories` tool runs semantic queries against your stored Mem0 database to pull up relevant user context on demand via the MCP standard. Your LangChain agent calls this tool whenever it needs to recall past interactions or user-specific constraints. Because LangChain tracks every tool execution through LangSmith, you can watch exactly how the query matches past data. This visibility lets you debug how semantic search scores affect the choices your agent makes in real-time.

Audit agent knowledge with `get_memories`

The `get_memories` tool lists every single fact your agent has recorded about a user, allowing you to review their complete profile. If you need to wipe a stale fact, `delete_memory` handles the cleanup instantly. In LangChain, you can chain these tools to create admin workflows. For example, you can build a graph that fetches stored facts, presents them to a human, and deletes outdated preferences to keep the context clean.

Setup guide

Set up Mem0 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 Mem0 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({
    "mem0-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 Mem0 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 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 LangChain

Install the required adapter package first. Then, configure the MultiServerMCPClient with the server endpoint, fetch the tools using client.get_tools(), and pass them to your LangChain agent constructor.

Yes, if you pass the tool to your LangChain agent, it decides when to call add_memory based on the conversation flow. The agent automatically extracts relevant facts from user messages and stores them without manual code.

When the agent calls search_memories, the server returns a ranked list of facts with relevance scores. LangChain feeds these records directly into the prompt context, letting the agent prioritize the most relevant facts.

Use the delete_memory tool with the specific memory ID to clear out old data. The agent can trigger this during a conversation when a user explicitly contradicts a previously saved preference.

Your stored user preferences are kept in an isolated Vinkius MCP sandbox environment, protected by enterprise-grade transit encryption. No raw conversational data leaks outside your designated 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