Bittlebits

by Unknown

Not rated
Website

About

Rewrite your web page to rank #1 on LLMs

Details

Author
Unknown
Categories
Developer Tools, Other, Marketing

Using Bittlebits with AI Agents Through Model Context Protocol (MCP)

Bittlebits has aModel Context Protocol (MCP)integration that lets you bring your GEO scores and rewrite suggestions directly into AI agents — whether you're using Claude Code in your terminal, Cursor or VS Code in your IDE, Codex, or an AI web app. Instead of copying content back and forth, your agent can read exactly what Bittlebits recommends and help you apply those changes, including writing them directly into your codebase.

There are three ways to connect, depending on your client and how much you want to run locally:

Every tool accepts either aurl(full page URL) or aurl_id(the Bittlebits internal ID, if you already have one). Results may take a few minutes on first run while Bittlebits fetches and processes the page.

Once connected, you can ask your agent things like:

- "Show me what Bittlebits wants to change on this page and explain why."
- "Rewrite my homepage copy applying the Bittlebits suggestions."
- "Which metrics are weakest and what should I fix first?"
- "Help me apply suggestion #3 without changing the tone."
- "Get the score for my landing page, then find and update the file in my codebase."

The@bittlebits.ai/mcppackage runs the Bittlebits MCP server locally over thestdiotransport. This is the recommended path for terminal and IDE agents — Claude Code, Cursor, VS Code, and Codex.

Run the setup command and follow the prompts:

No copy-pasting keys, no hand-editing JSON. Re-runningsetupis safe: it merges into existing config files, preserving your other MCP servers and only updating the Bittlebits entry.

Already have an API key? Skip the browser:npx @bittlebits.ai/mcp setup --api-key bb_your_key

Thesetupcommand also accepts client flags (--claude,--cursor,--vscode,--codex),--project/--globalfor scope, and-y/--yesfor non-interactive runs.

Already ransetup? Uselaunchto instantly open an AI session with Bittlebits pre-loaded — no manual config needed.

This detects which AI clients (Claude Code, Codex) are installed on your machine and opens a session. If both are found, you'll be asked to pick one.

npx @bittlebits.ai/mcp launch [options] -c, --client <name> Force a specific client: claude, codex -p, --prompt <text> Send an initial prompt (non-interactive / scripted use)
# Interactive session with auto-detected client npx @bittlebits.ai/mcp launch # Force Claude Code npx @bittlebits.ai/mcp launch --client claude # One-shot score in your terminal npx @bittlebits.ai/mcp launch --client claude --prompt "Get the GEO score for nike.com"

Prefer to wire it up yourself? Any client that supports the stdio transport works. Runnpx -y @bittlebits.ai/mcpwithBITTLEBITS_API_KEYset in the environment — find your key underSettings → API Keysatbittlebits.ai.

claude mcp add --transport stdio bittlebits -e BITTLEBITS_API_KEY=your_key -- npx -y @bittlebits.ai/mcp

Cursor / Claude Code (.cursor/mcp.jsonor.mcp.json):

{ "mcpServers": { "bittlebits": { "command": "npx", "args": ["-y", "@bittlebits.ai/mcp"], "env": { "BITTLEBITS_API_KEY": "your_key_here" } } } }
{ "servers": { "bittlebits": { "type": "stdio", "command": "npx", "args": ["-y", "@bittlebits.ai/mcp"], "env": { "BITTLEBITS_API_KEY": "your_key_here" } } } }
[mcp_servers.bittlebits] command = "npx" args = ["-y", "@bittlebits.ai/mcp"] [mcp_servers.bittlebits.env] BITTLEBITS_API_KEY = "your_key_here"
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.