priorrun-mcp

MCP server for Prior.Run — run focus-group rooms and deep tests on ad creatives and live pages from Claude Desktop, Claude Code, Codex, Gemini CLI, Cursor, Windsurf, Cline, Zed, or any MCP-compatible agent.

Install

Requires Python 3.11+. Install uv if you don't have it.

uvx priorrun-mcp

That's it — uvx fetches and runs the server on demand.

Configure

Grab an API key from prior.run/settings, then register the server with your agent host.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "prior-run": {
      "command": "uvx",
      "args": ["priorrun-mcp"],
      "env": {
        "PRIORRUN_API_KEY": "pr_live_xxxxxxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

Claude Code

~/.claude/mcp.json (global) or .mcp.json in a project root:

{
  "mcpServers": {
    "prior-run": {
      "command": "uvx",
      "args": ["priorrun-mcp"],
      "env": { "PRIORRUN_API_KEY": "pr_live_..." }
    }
  }
}

Codex (OpenAI)

~/.codex/config.toml — TOML, not JSON:

[mcp_servers.prior-run]
command = "uvx"
args = ["priorrun-mcp"]

[mcp_servers.prior-run.env]
PRIORRUN_API_KEY = "pr_live_..."

Gemini CLI

~/.gemini/settings.json:

{
  "mcpServers": {
    "prior-run": {
      "command": "uvx",
      "args": ["priorrun-mcp"],
      "env": { "PRIORRUN_API_KEY": "pr_live_..." }
    }
  }
}

Cursor

~/.cursor/mcp.json (global) or .cursor/mcp.json (per-project):

{
  "mcpServers": {
    "prior-run": {
      "command": "uvx",
      "args": ["priorrun-mcp"],
      "env": { "PRIORRUN_API_KEY": "pr_live_..." }
    }
  }
}

Windsurf / Cline / Zed / other MCP hosts

All modern MCP hosts share the same mcpServers JSON shape used by Claude Code. Drop the same block into the host's MCP config file — check the host's docs for the exact path.

Tools

Room-first, mirroring the web app: every deep run starts from a focus-group room. Flow: list_custom_audiences → persona_audience_panel (seats the members) → persona_audience_ask (fast) → deep-run via a create_* tool with custom_audience_id + panel_member_indices (the seated members, both required).

Image arguments accept local file paths, https:// URLs, or base64. Create tools default to wait=True — the agent gets the completed memo in one tool call.

Example prompts

The agent picks the right tool from your wording. Say "ad creative" / "creative compare" / name a platform (Meta/TikTok/Google) for the ads tools, or "live page" / "walk this URL" for the URL tools.

Ads compare — evaluates the creative as it would appear in-feed (scroll-stop, hook clarity, brand recall), platform-aware:

Run a Prior.Run ads compare on ~/desktop/creative-a.jpg vs
~/desktop/creative-b.jpg. Campaign context: Gen Z skincare awareness on TikTok.

→ agent calls create_ads_compare with run_platform="tiktok", ads-specific synthesis (scroll-stop, hook, brand recall, no landing-page critique).

Both return a completed memo (~90s) with verdict, audience quotes, and a memo URL.

Environment variables

Links

• Product: prior.run
• API docs: prior.run/docs/api
• MCP docs: prior.run/docs/mcp