# Outset

Connects an AI agent to Outset for building studies, launching recruitment, and querying interview results. It uses a remote MCP server.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: Outset-AI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Outset-AI/outset-mcp
- Updated: 2026-07-02
- HTML: https://affpapa.org/en/nevibecode/mcp/outset

## What it does

Outset connects an AI agent to the Outset research platform through a remote MCP server. The agent can create and edit studies, including projects, sections, questions, screeners, display rules, quotas, and concepts. It can also request reports, answers, topline findings, category summaries, and highlight clips.

The server supports recruitment setup with sample size, reward, and demographic filters, then can launch the recruitment flow. Launching may incur fees and requires the separate `studies:launch` scope. OAuth scopes and organization roles are enforced on the server.

Nothing runs on your machine. The client connects to `https://api.outset.ai/mcp/` over Streamable HTTP and authenticates with OAuth 2.1 using PKCE. The repository contains directory and plugin manifests; the actual MCP server stays remote.

## Requirements
- Remote server: `https://api.outset.ai/mcp/`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://api.outset.ai/mcp/
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add outset --url https://api.outset.ai/mcp/
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "outset": {
            "url": "https://api.outset.ai/mcp/"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "outset": {
            "type": "http",
            "url": "https://api.outset.ai/mcp/"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http outset https://api.outset.ai/mcp/
```

## When to use it
- build a study with questions and screeners
- set recruitment filters and sample size
- launch participant recruitment with a reward
- query reports and topline findings
- inspect workspaces and project context

## Example prompts
- Create a study about the new product with sections, questions, and a screener.
- Set up recruitment with the required sample size, reward, and demographic filters.
- Query the report, answers, and topline findings for this study.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md