Get started with specloop

Quickstart

Three steps: sign in, add credits, ask. You'll get a request id back; pull the answer once an expert replies.

$ npm i -g @specloop/cli          # or call it with: npx @specloop/cli <command>
$ specloop login                   # GitHub device flow — opens a code to approve
$ specloop credits buy --pack starter   # prints a Stripe link (or redeem a voucher in the dashboard)

$ specloop ask \
    --query "What should I prompt my agent next for auth?" \
    --summary "B2B dashboard; added bearer middleware + /me route" \
    --tech "Next.js, Postgres, Cloudflare" \
    --tools "Stripe, GitHub OAuth"

$ specloop watch                   # desktop ping + clipboard when an expert answers
$ specloop get <request-id>        # the agent-ready prompt — paste it into your coding agent

Requires Node 18 or newer.

How it works

1. You send a question plus app context (overview, tech stack, tools, an optional snippet or URL).
2. A private, secret-stripped scratch pull request is created so a vetted human expert can review your context.
3. An available expert claims the request and replies. Internal targets: claim within 10 minutes, reply within 20.
4. Their guidance comes back as a synthesized, agent-ready prompt you paste straight into your coding agent.

Money-back guarantee. If no expert answers within 24 hours, your credits for that request are automatically refunded.

Install the CLI

Install globally, or skip the install and prefix any command with npx.

$ npm i -g @specloop/cli       # global: enables the `specloop` command
$ npx @specloop/cli --help     # or no install — run on demand

Sign in once with GitHub. Your token is saved to ~/.ai-review/config.json and reused by every command (and by the MCP server).

$ specloop login               # opens a GitHub device-flow code to approve

Get credits

Each guidance request costs 100 credits (about one request). Get them in either of two ways:

• Buy: specloop credits buy --pack starter prints a Stripe checkout link. Packs: starter (100), pro (500), team (1000).
• Voucher: redeem a code in your dashboard → Billing & Usage. (Same GitHub account as the CLI, so the credits show up there too.)

Check your balance any time with specloop credits.

Connect via MCP

The specloop MCP server lets your coding agent submit requests and pull answers directly — no copy-paste. It runs locally over stdio and works in any tool that supports MCP servers (Claude Code, Claude Desktop, Codex, Cursor, Windsurf, VS Code).

Sign in first so the server can authenticate:

$ specloop login

About the token. After specloop login, the MCP server reuses your saved token automatically (CLI v0.1.6+) — no extra config. On older versions, add it as an env var on the server: "env": { "SPECLOOP_TOKEN": "air_…" } (your token is in ~/.ai-review/config.json).

Claude Code

$ claude mcp add specloop -- npx -y @specloop/cli mcp

Claude Desktop

Add this to your claude_desktop_config.json (Settings → Developer → Edit Config), then restart Claude Desktop:

{
  "mcpServers": {
    "specloop": {
      "command": "npx",
      "args": ["-y", "@specloop/cli", "mcp"]
    }
  }
}

Codex

Add this to ~/.codex/config.toml:

[mcp_servers.specloop]
command = "npx"
args = ["-y", "@specloop/cli", "mcp"]

Cursor

Settings → MCP → Add new global MCP server (or create ~/.cursor/mcp.json for all projects, or .cursor/mcp.json inside one project):

{
  "mcpServers": {
    "specloop": {
      "command": "npx",
      "args": ["-y", "@specloop/cli", "mcp"]
    }
  }
}

Toggle the server on in Settings → MCP, then in Agent/Composer the specloop tools are available.

Remote MCP (web platforms)

For web-based tools that connect to an MCP server by URL instead of a local command, there's a hosted endpoint (Streamable HTTP):

URL:    https://specloop.dev/mcp
Header: Authorization: Bearer <your-token>

Add it wherever the platform lets you register a custom remote MCP server with an authorization header. Your token comes from specloop login (or your dashboard).

MCP tools

The server exposes these tools to your agent:

CLI command reference

For experts

Want to answer requests? Apply in your dashboard → Become an expert. Applicants are vetted by recent GitHub activity and approved by an admin. Once approved: