> ## Documentation Index
> Fetch the complete documentation index at: https://supermemory.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents, skills and MCP

> Set up coding agents to integrate Supermemory — CLI, skill, and docs MCP.

This page is for **building with Supermemory** using coding agents: scaffolding a project, following the real API, and searching product docs.

It is **not** the consumer Memory MCP (give Claude/Cursor long-term memory about *you*). That is a separate product surface — see [Supermemory MCP](/docs/supermemory-mcp/mcp).

| Path         | How                                    | For                                          |
| ------------ | -------------------------------------- | -------------------------------------------- |
| **CLI**      | `npx supermemory`                      | Setup, smoke tests, agent-driven integration |
| **Skill**    | `npx skills add … --skill supermemory` | Teach the agent the real API surface         |
| **Docs MCP** | `https://supermemory.ai/docs/mcp`      | Search these docs while the agent codes      |

## CLI

Agents (and humans) can set things up from the terminal easily using our CLI

```bash theme={null}
npx supermemory
```

Useful for coding agents:

```bash theme={null}
npx supermemory setup              # detect project, launch/print integration flow
npx supermemory setup --prompt     # print integration prompt only
npx supermemory setup --json       # machine-readable output
npx supermemory help --json        # agent-readable command catalog
npx supermemory help --all
```

Also available for smoke tests against your key: `add`, `search`, `profile`, `docs`, `tags`, `config`, `whoami`. Auth via first-run credentials or `SUPERMEMORY_API_KEY`.

```bash theme={null}
npx supermemory add "User prefers TypeScript" --tag user_123
npx supermemory search "language preference" --tag user_123
npx supermemory profile --tag user_123
```

## Skill

Install the official skill so the agent uses the real endpoints, auth, and `containerTag` rules instead of hallucinating APIs:

```bash theme={null}
npx skills add https://github.com/supermemoryai/skills --skill supermemory
```

Source: [github.com/supermemoryai/skills](https://github.com/supermemoryai/skills).

<Tip>
  Best combo for coding agents: **skill** + **docs MCP** + **`npx supermemory setup`**.
</Tip>

## Docs MCP

Remote MCP that lets the agent **search Supermemory documentation** while it implements an integration.

Server URL:

```text theme={null}
https://supermemory.ai/docs/mcp
```

### Setup by client

<Tabs>
  <Tab title="Cursor">
    Add to `~/.cursor/mcp.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "supermemory-docs": {
          "url": "https://supermemory.ai/docs/mcp"
        }
      }
    }
    ```
  </Tab>

  <Tab title="Claude Code">
    ```bash theme={null}
    claude mcp add --transport http supermemory-docs https://supermemory.ai/docs/mcp
    ```

    Or project `.mcp.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "supermemory-docs": {
          "type": "http",
          "url": "https://supermemory.ai/docs/mcp"
        }
      }
    }
    ```
  </Tab>

  <Tab title="Codex">
    ```bash theme={null}
    codex mcp add supermemory-docs --url https://supermemory.ai/docs/mcp
    ```

    Or `~/.codex/config.toml`:

    ```toml theme={null}
    [mcp_servers.supermemory-docs]
    url = "https://supermemory.ai/docs/mcp"
    ```
  </Tab>

  <Tab title="OpenCode">
    ```json theme={null}
    {
      "mcp": {
        "supermemory-docs": {
          "type": "remote",
          "url": "https://supermemory.ai/docs/mcp",
          "enabled": true
        }
      }
    }
    ```
  </Tab>

  <Tab title="VS Code">
    Add to `.vscode/mcp.json`:

    ```json theme={null}
    {
      "servers": {
        "supermemory-docs": {
          "type": "http",
          "url": "https://supermemory.ai/docs/mcp"
        }
      }
    }
    ```
  </Tab>

  <Tab title="Other">
    ```json theme={null}
    {
      "mcpServers": {
        "supermemory-docs": {
          "url": "https://supermemory.ai/docs/mcp"
        }
      }
    }
    ```

    Stdio-only clients can proxy:

    ```json theme={null}
    {
      "mcpServers": {
        "supermemory-docs": {
          "command": "npx",
          "args": ["-y", "mcp-remote", "https://supermemory.ai/docs/mcp"]
        }
      }
    }
    ```
  </Tab>
</Tabs>

### Starter prompt (docs + setup)

```text theme={null}
You are integrating Supermemory into my app.

- Use the supermemory-docs MCP (or https://supermemory.ai/docs/llms.txt) before inventing endpoints.
- Prefer `npx supermemory setup` / the supermemory skill for correct auth, containerTag, and SDK usage.
- Canonical writes: POST /v3/documents · search: POST /v4/search · profile: POST /v4/profile
- Auth: Authorization: Bearer $SUPERMEMORY_API_KEY only
- Always scope with containerTag (singular) on write and search
- For demos use dreaming: "instant" when memories must be ready right after status done
```

### Integrate prompt (optional)

If the skill is not installed, paste a fuller prompt so the agent asks the right product questions:

<Accordion title="Copy full integration prompt" icon="copy">
  ```
  You are integrating Supermemory into my application. Supermemory provides user memory, semantic search, and automatic knowledge extraction for AI applications.

  Note: You can always reference the documentation by using the **supermemory-docs MCP** or content on **supermemory.ai/docs**. Prefer `npx supermemory setup` / `npx supermemory help --json` when scaffolding.

  CANONICAL API SURFACE (use these, nothing else):

  - Auth header: `Authorization: Bearer $SUPERMEMORY_API_KEY` — the only supported auth header
  - Write content:     POST https://api.supermemory.ai/v3/documents
  - Search:            POST https://api.supermemory.ai/v4/search
  - Profile + search:  POST https://api.supermemory.ai/v4/profile
  - Settings:          PATCH https://api.supermemory.ai/v3/settings
  - Scoping:           `containerTag` (singular string) in the JSON body — never in a header
  - SDK:               `client.add()`, `client.search()`, `client.profile()`

  DO NOT USE — deprecated, undocumented, or fabricated:

  - Endpoints:  /v1/anything, /v3/memories, /v3/search   (use /v3/documents and /v4/search)
  - Headers:    x-supermemory-api-key, x-api-key, x-sm-user-id (for API auth)
  - Body keys:  containerTags (plural) on writes as the only scope, userId, spaces
  - Mixing:     `rerank` and `rewriteQuery` on /v4/search only — never on /v3/search

  SCOPING IS LOAD-BEARING. Every write and every search MUST include `containerTag`.

  Prefer for tutorials:
  - Ingest conversations with customId + dreaming: "instant" when you need memories immediately
  - Wait until document status is done before search
  - search with searchMode: "documents" for RAG, search (+ relatedMemories) for the graph, profile for always-on context

  STEP 1: Ask what I'm building, integration style (AI SDK / OpenAI / Direct SDK / API), data model (user/org/both), profiles yes/no.
  STEP 2: Install supermemory (npm/pip), set SUPERMEMORY_API_KEY from https://console.supermemory.ai
  STEP 3: Generate complete working code.

  DOCS: https://supermemory.ai/docs
  ```
</Accordion>

## Memory MCP (different product)

Want your **assistant** to remember you across chats (save/recall/profile in Claude, Cursor, etc.)? That is the **Memory MCP**, not the docs MCP:

→ [Supermemory MCP](/docs/supermemory-mcp/mcp)

## Next steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="play" href="/docs/quickstart">
    Conversation + document ingest, RAG, graph, profile, harness.
  </Card>

  <Card title="Memory MCP" icon="brain-circuit" href="/docs/supermemory-mcp/mcp">
    Persistent memory for assistants — separate from docs setup.
  </Card>

  <Card title="Plugins" icon="puzzle" href="/docs/integrations/openclaw">
    Claude Code, OpenClaw, Codex, Hermes, and more.
  </Card>

  <Card title="AI SDK" icon="triangle" href="/docs/integrations/ai-sdk">
    withSupermemory and memory tools in app code.
  </Card>
</CardGroup>