Quick start

Three levels of integration — from exploring in the portal to connecting your own AI app

Meko has three levels of integration. Each gives you more control over how your agents use memory, knowledge, and conversation history. Start at level 1 and work up, or skip ahead.

Level	What you connect	What you get
1. WorkbenchLM	Our chat agent, in the portal	Simplest. See memory and knowledge work before installing anything.
2. Your AI client	Cursor, Claude Code, Claude Desktop, Codex, VS Code	Daily driver. Use your own coding tools against your datapacks.
3. Your AI app	Your own agent or framework	Full control. Build Meko into the apps you ship. Under development.

Before you start, request access and sign in to the Meko portal. You land on the Welcome to Meko page with a default datapack already created for you.

Note

Meko itself is not an AI agent — it's the data layer (shared knowledge, collective memory, decision traces) that your agents connect to. WorkbenchLM is an embedded chat agent so you can try Meko in the portal without installing anything; it's not the daily-use surface.

Try Meko in WorkbenchLM

The simplest way to see Meko in action. WorkbenchLM runs in the portal against your default datapack, with sample knowledge loaded and live memory traces visible as you chat. Nothing to install.

In the portal sidebar, open WorkbenchLM.
Ask about the sample knowledge, or share something about your project for Meko to remember.
Watch the Memory and Decision traces panels update as the conversation moves.

See WorkbenchLM for what's loaded, when to use it versus a real coding agent, and the limits of the embedded experience.

Connect your AI client

External AI clients (Cursor, Claude Code, Claude Desktop, Codex, VS Code, etc.) connect to Meko through one shared MCP endpoint:

https://mcp.mekodata.ai/mcp

You don't need a different URL per datapack. Your agent picks the datapack at call time by passing a datapack_id (or datapack name) into MCP tool calls. API keys and the MCP connection are scoped to your account, not to a single datapack — once connected, your agent can see and act on every datapack you own.

There are three ways to connect. Pick the one that fits your workflow.

Recommended for Cursor, Claude Code, and Claude Desktop.

The portal gives you a one-line npx command per client. It registers the Meko MCP server and installs an agent behavioral skill that teaches your agent when to use Meko tools automatically — saving conversations, capturing memories, and searching knowledge without you having to ask each time. In harnesses that support it (e.g., Claude Code), the skill also hooks into session lifecycle events to capture context at session start and end.

Generate an API key from Settings > API Keys. Name it for the client that will use it (e.g., laptop/claude-desktop). The key starts with mko_tkn_ and is shown exactly once — copy or download before closing.
Open the Connect dialog on any datapack, or go to the Connect page in the sidebar. Select your client tab (Claude Code, Claude Desktop, or Cursor).

Run the install command shown. It looks like this:

npx @yugabytedb/meko-mcp --client <client> --url "https://mcp.mekodata.ai/mcp" --api-key <paste-your-api-key>

Replace <client> with claude-code, claude-desktop, or cursor.

Restart your client if the new MCP server doesn't show up automatically.

The portal also has a Manual MCP Install tab for other clients — it walks through nvm, mcp-add, and the skills package step by step.

See @yugabytedb/meko-mcp on npm for what the installer does under the hood.

For Claude Desktop and other clients with a custom-connector flow.

If your client supports adding a custom remote MCP connector, you can connect Meko by URL with no API key and no installer. The client opens a browser for OAuth; your Meko portal login is the identity.

In your client, add a custom MCP connector pointing at https://mcp.mekodata.ai/mcp.
Complete the OAuth handshake when the browser opens.
The MCP server returns its tool list to the client automatically.

With OAuth alone, your agent interacts with Meko on demand — you need to mention "Meko" in your prompt (e.g., "save this to Meko," "search my Meko knowledge base") for the agent to call the tools. The agent won't proactively save conversations or capture memories unless you ask.

To get automatic behavior, use the Automated install tab instead, or write your own skills to teach your agent when to call Meko tools.

For any MCP-compatible client — no npx, no installer.

Add the Meko MCP server directly to your client's config file with your API key. This gives you the same on-demand MCP tools as OAuth, but authenticated with a long-lived key instead of a browser handshake.

Go to Settings > API Keys and click Generate API key. Name it for the client that will use it (e.g., laptop/cursor). The full key is shown exactly once — Copy or Download .txt before closing.

Edit your client's MCP config to add the Meko server. For example, in Cursor's mcp.json:

{
  "mcpServers": {
    "meko": {
      "url": "https://mcp.mekodata.ai/mcp",
      "headers": {
        "API_KEY": "<paste-your-api-key>"
      }
    }
  }
}

Restart your client.

Like OAuth, this is on demand — your agent calls Meko tools when you ask. For per-client config paths and examples (Claude Desktop, Claude Code, Codex, VS Code), see Connect to an AI agent.

For API key generation, revocation, and limits, see API keys.

Verify the connection

Ask your agent to list your datapacks.
```
List my datapacks in Meko.
```
It should call the datapack_list tool and return the names you see in the portal. If it doesn't, see Troubleshooting.

Connect your AI app

Under development. Programmatic integration patterns for agent frameworks (LangChain, LlamaIndex, custom Python or TypeScript agents) are coming. See Connect programmatically for the current state and what's planned.

Explore Meko

Add knowledge to your datapack and create memories.