About TabRunner
TabRunner is an MCP server for assigning browser tasks to an agent running in the user's Chrome, using its existing tabs and signed-in accounts. It is intended for Claude Code, Claude Desktop, Codex, and other MCP clients; the TabRunner extension provides the browser connection.
Key features
- 01Assign tasks in existing Chrome tabs
- 02Use accounts already signed in
- 03Follow task progress to its answer
- 04Interact with pages directly
- 05Check extension connection with health
Use cases
- 01Completing tasks on signed-in websites
- 02Continuing work in existing browser tabs
MCP support
The MCP server lets Claude Code, Claude Desktop, Codex, and other MCP clients delegate tasks to the TabRunner browser agent or interact with pages. It requires the TabRunner extension with its MCP bridge enabled.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y tabrunner-mcpTABRUNNER_BRIDGE_PORTThe localhost port the extension connects to. Must match Settings → MCP in TabRunner.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
23Saved tool list · updated 5d ago
This tool takes no parameters.
Details
From the project READMEtabrunner-mcp
The MCP server for TabRunner, the browser agent that works in your own Chrome, with your tabs and the accounts you're already signed in to. Claude Code, Claude Desktop, Codex or any other MCP client can give TabRunner a task and follow it to the answer, or click through a page itself.
It needs bun and the TabRunner extension, with the bridge turned on in Settings → MCP.
claude mcp add --scope user tabrunner -- bunx tabrunner-mcp@latest
Or install the plugin, which adds this server plus a skill that teaches the model how to use it:
claude plugin marketplace add tabrunner/tabrunner
claude plugin install tabrunner@tabrunner
Call health first: it says whether the extension is connected, and what to do if it isn't. The
tools and settings are in docs/mcp.md.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.