Blueberry MCP
Blueberry includes a built-in MCP server that gives any AI coding agent full context over your entire workspace — your editor, terminal, preview browser, and pinned apps — all through a single connection.
What is Blueberry MCP?
Blueberry MCP is a local Model Context Protocol server that runs inside Blueberry. It exposes 10 tools that let AI coding agents see and interact with every panel in your workspace.
When you run an AI agent from a Blueberry terminal, the MCP server is automatically connected. The agent can then read your code, check terminal output, capture screenshots of your running app, and take actions — all without you copying, pasting, or switching windows.
This works with any MCP-compatible coding agent, including Claude Code, Codex, and Gemini CLI.
What Your AI Can See
When an AI agent runs from a Blueberry terminal, it has visibility into every part of your workspace:
Editor
- The currently open file and its contents
- All open tabs
- Cursor position and selection
- Active diff views
Terminal
- All terminal tabs and their output
- Running processes and server status
- Build errors and test results
Preview Browser
- The active URL and page content
- All preview tabs with their URLs and titles
- Console logs from the page
- Visual screenshots of your running app
Pinned Apps
- Your pinned web apps (GitHub, Vercel, PostHog, etc.)
- Their current content and state
Available Tools
Blueberry MCP provides 10 tools organized by panel:
| Tool | What it does |
|---|---|
blueberry_get_context | Get the full workspace state — open files, terminal tabs, preview URLs, pinned apps, and visibility |
blueberry_open_file | Open a file in the editor, optionally jumping to a specific line |
blueberry_open_preview | Open a URL in the preview browser |
blueberry_capture_webview_screenshot | Capture a PNG screenshot of a preview tab or pinned app |
blueberry_capture_webview_content | Get the text content of a preview tab or pinned app as a structured accessibility tree |
blueberry_get_console_logs | Read console logs from a preview tab, filterable by level |
blueberry_send_terminal_command | Send a command to a terminal tab |
blueberry_create_terminal | Create a new named terminal tab |
blueberry_get_terminal_logs | Read the output from a terminal tab |
blueberry_open_pinned_app | Open a pinned web app panel |
See the MCP Tools Reference for full parameter documentation.
How It Works
- Local MCP Server — Blueberry runs
blueberry-mcpas a local server alongside your workspace - Automatic Connection — When you start an AI agent in a Blueberry terminal, a session token is injected so the agent connects to the MCP server automatically
- Real-time State — Every tool call returns the current state of your workspace, not a stale snapshot
- Direct Actions — Agents can open files, run commands, navigate the preview browser, and interact with pinned apps
Why This Matters
No More Copy-Paste
Stop copying code snippets, error logs, and screenshots into chat. Your AI can see your workspace directly and pull the context it needs.
Better Responses
With full visibility into your editor, terminal, and preview, your AI understands the complete picture. It sees the error in your terminal, the code causing it, and the result in your browser — all at once.
Direct Actions
Your AI doesn’t just tell you what to do — it can do it. Open files, run commands, navigate your preview, and check your deployments without you lifting a finger.
Getting Started
- Open a terminal tab in Blueberry
- Start your AI agent (e.g.
claude,codex,gemini) - The agent automatically has access to all Blueberry MCP tools
See Getting Started for detailed setup instructions.
Learn More
- MCP Tools Reference — Full parameter documentation for all 10 tools
- Best Practices — Tips for getting the most out of AI agents in Blueberry