How to Use the Mem0 MCP in CrewAI

Q: Does Mem0 enable better collaboration in CrewAI?

Yes. It allows agents to leave notes for each other via addmemory, so subsequent agents in the workflow have full context.

Q: How do I limit Mem0 access for specific CrewAI agents?

Use the toolfilter in the MCP configuration to restrict which agents can call deletememory or addmemory.

Give your CrewAI crew a shared memory bank. Let Mem0 handle context across agents for smarter collaborative operations.

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 CrewAI

Create your Vinkius account to connect Mem0 to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Shared memory for CrewAI agents

Agents in a crew often struggle with context consistency. The `add_memory` tool allows any agent to store facts that the rest of the crew can access later. This creates a unified knowledge base for your autonomous operations. One agent can research, while another reads the stored facts to perform the final action.

Agent-to-agent memory search

The `search_memories` tool enables your agents to query past interactions independently. If an agent needs a preference from a previous session, it just asks the server. This removes the need for agents to maintain their own internal state. They share a single, searchable source of truth.

Managing memory lifecycle in crews

The `get_memories` tool lets a moderator agent review what the crew has learned about a user. You can use this to audit the quality of the stored facts. If the information becomes obsolete, you can use `delete_memory` to clear it out. Your crew stays efficient and focused on the current objective.

Setup guide

Set up Mem0 MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Mem0 tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Mem0 Analyst",
    goal="Access and analyze Mem0 data via MCP.",
    backstory="Expert analyst with direct Mem0 access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Mem0 transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Mem0 Analyst",
        goal="Access and analyze Mem0 data via MCP.",
        backstory="Expert analyst with direct Mem0 access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Mem0 transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can add the Mem0 server to your agents using the MCP integration. This lets them store and recall facts shared across the entire crew.

Yes. It allows agents to leave notes for each other via `add_memory`, so subsequent agents in the workflow have full context.

Use the `tool_filter` in the MCP configuration to restrict which agents can call `delete_memory` or `add_memory`.

It stores text-based facts, preferences, and context. These are indexed semantically to ensure retrieval is fast and accurate.

The memory lives on the server, not in the agent process. It persists indefinitely until you explicitly delete the records.

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

Mastra AI sdk-typescript

Start using the Mem0 MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started