Supermemory MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Supermemory MCP or direct API to ingest knowledge, organize memories, search context, and recall relevant facts through natural language.

Supermemory logoSupermemory
Api Key

Supermemory is a memory and context API for ingesting, organizing, searching, and recalling information. Use it to give apps durable, searchable context without rebuilding memory infrastructure.

86 Tools

Try Supermemory now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Supermemory
Try asking
TOOLS

Supported Tools

Every Supermemory action and event your agent gets out of the box.

Add Document

Ingest text or a public URL as a Supermemory document and return its document ID and initial processing status.

Add Documents

Add 1 to 600 documents in one request, with per-document metadata and processing options.

Add Namespace Document

Add text or a supported URL as searchable, evolving memory in an isolated namespace.

Add Namespace Documents

Ingest 1 to 600 text or URL documents in an isolated namespace.

Bulk Delete Documents

Deprecated provider v3 endpoint; shuts down December 31, 2026.

Configure Automatic Top-Ups

Deprecated legacy v3 API, scheduled to shut down December 31, 2026.

Configure Connection

Deprecated by the provider: the legacy v3 API shuts down December 31, 2026.

Count Namespace Document Memories

Count live memories in a namespace for up to 100 public document IDs.

Create Connection

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

Create Connector

Connect an external source to a namespace.

Create Memory

Deprecated by the provider; v3/v4 APIs shut down on December 31, 2026.

Create Scoped Key

Deprecated legacy v3 route; provider shutdown is December 31, 2026.

Delete Connection

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

Delete Connector

Disconnect a connector in a namespace and stop its webhooks.

Delete Container Tag

Deprecated by the provider: the legacy v3 API shuts down on December 31, 2026.

Delete Document

Permanently delete one document by ID.

Delete Namespace

Retire a namespace and permanently delete its documents and memories.

Delete Namespace Documents

Permanently delete 1 to 100 documents and their derived knowledge from a namespace by document ID or caller-defined ID.

Delete Namespace Profile Buckets

Remove 1 to 50 profile bucket categories created specifically for a namespace and return its updated effective bucket definitions.

Delete Provider Connection

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

Forget Matching Memories

Deprecated by Supermemory: legacy v3/v4 APIs shut down December 31, 2026.

Forget Memory

Deprecated by the provider; v3/v4 APIs shut down on December 31, 2026.

Forget Namespace Memories

Remove 1 to 500 exact memories from normal recall in a namespace by stable memory ID, preserving their audit history.

Forget Namespace Memories Semantically

Preview or forget memories in a namespace using a natural-language query.

Get Account Status

Return the connected Supermemory organization's plan, credit balance, high-level usage, and reset date.

Get Automatic Top-Ups

Deprecated legacy v3 API, scheduled to shut down December 31, 2026.

Get Billing Usage

Deprecated legacy v3 API; provider shutdown is December 31, 2026.

Get Billing Usage Events

Deprecated legacy v3 API, scheduled to shut down December 31, 2026.

Get Connection

Deprecated by the provider: this legacy v3 endpoint shuts down December 31, 2026.

Get Connector

Read a connector in a namespace, including its setup, selection, and latest sync status.

Get Container Tag

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

Get Container Tag Merge

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

Get Document

Get one document's content, metadata, source details, and processing status by document ID.

Get Document Chunks

Return the ordered extracted chunks for one processed document.

Get Document File URL

Deprecated by the provider: this legacy endpoint shuts down December 31, 2026.

Get Error Analytics

Deprecated legacy v3 endpoint scheduled to shut down December 31, 2026.

Get Namespace Settings

Read a namespace's supporting context and lifecycle timestamps.

Get Namespace Document

Retrieve a document's canonical content, metadata, and processing state by document ID or caller-defined ID within a namespace.

Get Namespace Memory

Retrieve one memory by ID within a namespace, including its text, metadata, version, and recall flags.

Get Namespace Profile

Read the continuously maintained profile of a namespace's subject without a search query.

Get Namespace Profile Buckets

Inspect the profile taxonomy active in a Supermemory namespace.

Get Organization

Read the connected organization's shared background that guides memory formation across all namespaces, together with its active namespace count.

Get Profile

Retrieve the static, dynamic, or bucketed profile learned for one container tag, optionally with matching search results.

Get Profile Buckets

Deprecated by the provider: this legacy v4 endpoint shuts down on December 31, 2026.

Get Provider Connection

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

Get Settings

Deprecated legacy v3 API, scheduled to shut down December 31, 2026.

Get Usage Analytics

Deprecated legacy v3 API, scheduled to shut down December 31, 2026.

Ingest Conversation

Deprecated by the provider: the v3/v4 API shuts down December 31, 2026.

List All Connectors

List one page of connectors across every namespace the API key can read, optionally filtered by provider.

List Connection Documents

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

List Connection Resources

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

List Connections

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

List Connectors

List one page of connectors that sync into a namespace, optionally filtered by provider.

List Container Tags

Deprecated by the provider: the legacy v3 API shuts down December 31, 2026.

List Documents

List documents, optionally filtered by containers, metadata, or filepath, one page at a time.

List Inferred Memories

List a namespace's inferred memories awaiting review.

List Invoices

Deprecated legacy v3 API, scheduled to shut down December 31, 2026.

List Memories

List extracted memory entries for one or more container tags, one page at a time.

List Namespace Resources

Browse one page of documents, extracted chunks, or learned memories in a namespace.

List Namespaces

List namespaces available to the caller, newest first, including their purpose, document and memory counts, and lifecycle timestamps.

List Processing Documents

Deprecated by the provider: the legacy v3 API shuts down December 31, 2026.

List Request Logs

Deprecated legacy v3 endpoint scheduled to shut down December 31, 2026.

Merge Container Tags

Deprecated by the provider: the legacy v3 API shuts down December 31, 2026.

Replace Namespace File

Replace an existing document with a new file within an isolated namespace, keeping its stable document ID.

Reset Organization Data

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

Review Inferred Memory

Provider deprecation notice: legacy v3/v4 APIs are scheduled to shut down December 31, 2026.

Revoke Scoped Key

Deprecated by the provider: this legacy v3 endpoint shuts down on December 31, 2026.

Search Memory

Semantically search Supermemory memories, document chunks, or both, with optional container and metadata filters.

Search Documents

Deprecated by the provider: legacy v3/v4 APIs shut down December 31, 2026.

Search Namespace

Recall relevant learned context and source passages from an isolated namespace.

Send Feedback

Send a bug report, feature request, documentation problem, or other feedback to the Supermemory team.

Suggest Profile Buckets

Deprecated by the provider: the legacy v3 API shuts down December 31, 2026.

Sync Connection

Deprecated provider v3 API; shuts down December 31, 2026.

Sync Connector

Start a sync now for a connector in a namespace.

Update Connector

Change what a connector syncs in a namespace or its maximum document count.

Update Container Tag

Deprecated by the provider: the legacy v3 API shuts down December 31, 2026.

Update Document

Update the content, metadata, container, or processing configuration of one existing document.

Update Memory

Deprecated by the provider; v3/v4 APIs shut down on December 31, 2026.

Update Namespace

Update the background context used during ingestion and memory formation in an existing namespace.

Update Namespace Document

Partially update an existing document in an isolated namespace without changing its stable ID.

Update Namespace File

Partially update a file-backed document in an isolated namespace.

Update Organization

Update organization-wide background that guides content interpretation and memory formation across every namespace.

Update Settings

Deprecated by the provider: the legacy v3 API shuts down December 31, 2026.

Upload Document File

Deprecated by the provider: this legacy endpoint shuts down December 31, 2026.

Upload Namespace File

Upload a file into an isolated Supermemory namespace to form searchable knowledge and learned memory.

Add or Update Namespace Profile Buckets

Add or update namespace-owned profile bucket definitions that guide memory classification.

SETUP GUIDE

Connect Supermemory MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["supermemory"],
  mcp: true,
});
Create a session scoped to Supermemory and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Search Supermemory for notes about our Q3 roadmap and summarize the key decisions",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a Supermemory request
SETUP GUIDE

Connect Supermemory API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["supermemory"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Supermemory
3

Run Supermemory tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Search Supermemory for notes about our Q3 roadmap and summarize the key decisions" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the Supermemory tool calls through the session, and print the final answer

Why Use Composio?

AI Native Supermemory Integration

  • Supports both Supermemory MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable memory search, ingestion, and recall
  • Rich coverage for reading, writing, and querying your Supermemory data

Managed Auth

  • Secure API key handling so you don't hard-code Supermemory credentials in agent code
  • Central place to manage, scope, and revoke Supermemory access
  • Per user and per environment credentials for cleaner production deployments

Agent Optimized Design

  • Tools are tuned for AI agents, so memory ingestion and search feel natural through plain language
  • Structured inputs help agents store useful context instead of messy, one-off notes
  • Comprehensive execution logs so you always know what memory action ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Supermemory
  • Scoped, least privilege access to Supermemory resources
  • Full audit trail of agent memory actions to support review and compliance
FAQ

Frequently asked questions

Yes, Supermemory requires you to configure your own API key. Once set up, Composio handles secure credential storage and API request handling for you. For production, you can create an auth config with auth_configs.create() and link user accounts with connected_accounts.link().

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Yes. Composio is SOC 2 Type II compliant and is built to keep your Supermemory connection and credentials secure. OAuth tokens and API keys are encrypted, and sensitive customer data is protected at rest and in transit.

Composio also undergoes independent security testing and continuously monitors its systems for security threats. You can review the latest reports and policies in the Composio Trust Center.

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

Create the key in your Supermemory account settings, then paste it once on Composio's connection page. Composio stores it encrypted and uses it only for the Supermemory actions your agent runs. Nobody else in your workspace can read it, and you can revoke it inside Supermemory at any time.

When you connect a Supermemory account through Composio, every action runs under that account, so anything the agent creates, sends, or changes shows up in Supermemory as done by you. Keep an approval step in your prompt for actions with side effects, such as sending or deleting, and have the agent draft first.

Whatever the credentials you connect allow inside Supermemory. If Supermemory lets you scope a key to specific permissions, create a scoped one so the agent can only do what you intend. You can revoke the key inside Supermemory at any time.

Yes. Composio supports multiple connected accounts for the same app, and that works in Claude, ChatGPT, or any other assistant you connect through Composio. Give each Supermemory connection a name such as work or personal, and the assistant uses the one you mention in the request. Each account keeps its own credentials and nothing is merged.

The connection stops working the moment Supermemory rejects the old key. Create a new key in Supermemory and reconnect the account from the Composio dashboard or by asking your agent to reconnect Supermemory. Nothing else changes.

Composio's free Hobby plan includes 100,000 tool calls per month with no credit card, which covers most personal Supermemory use. Paid plans add higher limits and team features. Your Supermemory plan and its API limits still apply as usual.

Built-in connectors usually give one AI access to a limited set of apps. Many people use Composio because it lets their AI connect to more apps than it normally supports, or connect to multiple accounts for the same app (e.g. connect Claude to multiple Supermemory accounts).

With Composio, you connect Supermemory once and then use it across different AI assistants without setting it up separately in each one. Connect your apps to Composio once, then connect Composio to whichever AI you use, whether that's Claude, ChatGPT, Hermes, or your own custom assistant.

Start with Supermemory.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Supermemory tool your agent needs.Free to start.

Start building