Mem0 MCP connector for AI agents

CALL ANY TOOL

Mem0 MCP exposes tools for adding, searching, retrieving, updating, and deleting persistent memories, as well as managing entities and listing memory operation events — giving agents full control over long-term memory.

mem0mcp_add_memory

Add Memory

Store a new preference, fact, or conversation snippet. Requires at least one: user_id, agent_id, or run_id. Returns an event_id for async polling via get_event_status.

Parameters

Name

Type

Required

Description

text

string

Required

Plain sentence summarizing what to store.

agent_id

string

Optional

Optional agent identifier.

app_id

string

Optional

Optional app identifier.

messages

string

Optional

Structured conversation history with `role`/`content`. Use when you have multiple turns.

metadata

string

Optional

Attach arbitrary metadata JSON to the memory.

run_id

string

Optional

Optional run identifier.

source

string

Optional

Event source tag (defaults to MCP if omitted).

user_id

string

Optional

Override the default user scope for this write.

mem0mcp_delete_all_memories

Delete All Memories

mem0mcp_delete_entities

Delete Entities

mem0mcp_delete_memory

Delete Memory

mem0mcp_get_event_status

Get Event Status

mem0mcp_get_memories

Get Memories

mem0mcp_get_memory

Get Memory

mem0mcp_list_entities

List Entities

mem0mcp_list_events

List Events

mem0mcp_search_memories

Search Memories

mem0mcp_update_memory

Update Memory

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="mem0mcp")

mcp = MultiServerMCPClient({
    "mem0mcp": {
        "url": "https://mcp.scalekit.com/mem0mcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "mem0mcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/mem0mcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "mem0mcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/mem0mcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="mem0mcp")
# Connect to MCP at https://mcp.scalekit.com/mem0mcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Search & retrieve

Copy the prompt

Copied

What do you remember about my communication preferences?

Copy the prompt

Copied

Search my memories for anything related to my current project goals.

Store & manage

Copy the prompt

Copied

Remember that I prefer async communication and weekly summary emails.

Copy the prompt

Copied

Delete all memories from our last session and start fresh.

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

1

Authorize

Your user connects

Mem0 MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Mem0 MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Mem0 MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Mem0 MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

SALES

Outbound prospecting agent

Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.

Apollo

View agent

SALES

Sales call prep agent

Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.

Granola

Attio

View agent

ENGINEERING

Slack workflow agent (LangGraph)

LangGraph agent that drives multi-step Slack workflows: triggers, approvals, and follow-up actions per user identity.

Slack

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Mem0 MCP as the user or as a shared key?

Scalekit resolves a per-user credential for each call. The Mem0 MCP audit log shows the real user identity, not a shared service account.

Where is the Mem0 MCP token stored?

In Scalekit's AES-256 encrypted vault, isolated per tenant. Tokens are auto-refreshed before expiry and revocable from a single dashboard without code changes.

Can I limit what the agent is allowed to do in Mem0 MCP?

Pass a toolNames filter to listScopedTools. Scalekit enforces the allowed set before every API call — the agent cannot invoke tools outside the approved list.

What happens when a user revokes Mem0 MCP access?

The token is invalidated at the next tool call. The agent fails closed rather than falling back to a shared key. Other users are unaffected and the revocation event is logged with a timestamp.

Can the agent read or modify memories belonging to a different user?

No. Scalekit scopes every Mem0 MCP call to the credential of the authorizing user. Memory reads and writes are bound to that user's store at the token level, so cross-user access is blocked before the request reaches Mem0.

Mem0 MCP

Tools your AI agent reaches for on Mem0 MCP, scoped per user.