Connect an agent (MCP + CLI)

Sapient ships a Model Context Protocol (MCP) server and a CLI, both on npm. Point any agent at your sk_live_ key and it can scan video, audio, or text and read the per-second brain response itself, with no glue code. The MCP and CLI both let you pick the model: mary (the default, reads every modality) or qualia (the video specialist).

One-shot install (Claude Code)

A single command wires Sapient into Claude Code:

claude mcp add sapient --env SAPIENT_API_KEY=sk_live_… -- npx -y @thesapientcompany/mcp

Open a new Claude Code session and ask it to scan a video. Get your sk_live_ key from Settings → API at thesapientcompany.com.

Already inside a Claude Code session?

If you’re chatting in Claude Code right now and don’t want to drop to a terminal, paste this prompt and let Claude install it for you:

Install the Sapient brain-response MCP for me. Run this command:

  claude mcp add sapient --env SAPIENT_API_KEY=sk_live_YOUR_KEY -- npx -y @thesapientcompany/mcp

Then confirm the sapient server connected (run `claude mcp list` and check it shows
as connected), and tell me which tools it exposes. If it didn't connect, show me the
error and how to fix it.

Swap in your real sk_live_ key before sending. Claude will run the command, verify the server is connected, and report back, so you never leave the chat.

One-shot prompt (install and run a scan)

Drop this into Claude Code (or any MCP-capable agent) to install and run your first scan in one go. Fill in your key and a video URL:

Install the Sapient brain-response MCP, then scan a video for me.

1. Run this in the terminal:
   claude mcp add sapient --env SAPIENT_API_KEY=sk_live_YOUR_KEY -- npx -y @thesapientcompany/mcp
2. Using the Sapient run_scan tool with wait:true, scan this video:
   https://www.instagram.com/reel/XXXXXXXXX/
   Ask for all 7 lenses and include reasons.
3. Show me the per-second timeline (attention, emotion, and memory at each
   second), plus the moments and the summary. Tell me where attention peaks
   and where it drops.

CLI

Prefer a terminal? The CLI runs a scan and waits for the result:

SAPIENT_API_KEY=sk_live_… npx @thesapientcompany/cli scan "https://yourcdn.com/ad.mp4" --wait --reasons

Pick the model with --model mary or --model qualia (Mary is the default). Other commands: sapient get <scan_id>, sapient history, sapient intelligence -q "attention", sapient lenses.

Install in other tools

Sapient is a standard stdio MCP server, so it drops into any MCP-capable editor or agent. Each one is a single copy-paste. Pick yours:

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per-project), then reload:

{
  "mcpServers": {
    "sapient": {
      "command": "npx",
      "args": ["-y", "@thesapientcompany/mcp"],
      "env": { "SAPIENT_API_KEY": "sk_live_…" }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json, then refresh MCP servers:

{
  "mcpServers": {
    "sapient": {
      "command": "npx",
      "args": ["-y", "@thesapientcompany/mcp"],
      "env": { "SAPIENT_API_KEY": "sk_live_…" }
    }
  }
}

Add to ~/.codex/config.toml:

[mcp_servers.sapient]
command = "npx"
args = ["-y", "@thesapientcompany/mcp"]
env = { SAPIENT_API_KEY = "sk_live_…" }

Or do it in one command:

codex mcp add sapient --env SAPIENT_API_KEY=sk_live_… -- npx -y @thesapientcompany/mcp

Add to .vscode/mcp.json (Copilot, Cline, and Continue read MCP from here):

{
  "servers": {
    "sapient": {
      "command": "npx",
      "args": ["-y", "@thesapientcompany/mcp"],
      "env": { "SAPIENT_API_KEY": "sk_live_…" }
    }
  }
}

Add to your claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "sapient": {
      "command": "npx",
      "args": ["-y", "@thesapientcompany/mcp"],
      "env": { "SAPIENT_API_KEY": "sk_live_…" }
    }
  }
}

Add to your Zed settings.json:

{
  "context_servers": {
    "sapient": {
      "command": { "path": "npx", "args": ["-y", "@thesapientcompany/mcp"] },
      "settings": { "SAPIENT_API_KEY": "sk_live_…" }
    }
  }
}

Any client that reads the standard MCP JSON format takes this:

{
  "mcpServers": {
    "sapient": {
      "command": "npx",
      "args": ["-y", "@thesapientcompany/mcp"],
      "env": { "SAPIENT_API_KEY": "sk_live_…" }
    }
  }
}

Every tool runs the same command: npx -y @thesapientcompany/mcp with SAPIENT_API_KEY set. If your tool isn’t listed, use that command in its MCP config and it will work.

What the agent gets

Tool	What it does
`run_scan`	Submit content (`url` or `text`), pick the `model` (`mary` or `qualia`), choose `lenses` and `options`. With `wait: true` it polls to completion and returns the full result.
`get_scan`	Fetch one scan by `scan_id`: status while running, the full per-second result when complete.
`list_lenses`	The 7 selectable lenses with one-line descriptions.
`my_history`	The caller’s scan history.
`my_intelligence`	Cross-scan patterns and semantic recall over everything you’ve scanned.

It also exposes a resource, sapient://knowledge-base, with the full explanation of how the models work, the 7 networks, and how to read a scan, so the agent can ground its own interpretation.

The MCP server is a local stdio server: it runs on your machine and talks to the hosted Sapient API. Set SAPIENT_BASE_URL to point at a different API host.

​One-shot install (Claude Code)

​Already inside a Claude Code session?

​One-shot prompt (install and run a scan)

​CLI

​Install in other tools

​What the agent gets

One-shot install (Claude Code)

Already inside a Claude Code session?

One-shot prompt (install and run a scan)

CLI

Install in other tools

What the agent gets