Browserbase API

Provides a local MCP server that exposes the OpenAPI-driven endpoints for agent interactions with configurable transport modes and security options.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "huazhengwang-browserbase-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "<CONFIG>",
        "SECURITY": "<SECURITY>",
        "CONFIG_PATH": "<CONFIG_PATH>"
      }
    }
  }
}

You can run and manage an MCP server that enables multi-agent conversations based on a defined OpenAPI schema. This server is written in Python and supports different transport modes, letting you host, configure, and use MCP-enabled clients against a consistent API surface.

How to use

To operate the MCP server from your environment, start the local stdio-based instance and connect your MCP client to it. You can also adapt the server to alternative transports if needed.

How to install

Prerequisites are Python 3.9+ and a way to run Python commands (pip and uv are commonly used). You will clone the project, install dependencies, and then run the server.

# 1. Clone the repository
git clone <repository-url>
cd mcp-server

# 2. Install dependencies (editable dev mode)
pip install -e ".[dev]"

# Alternatively, use the uv runner to install in editable mode
uv pip install --editable ".[dev]"

Configuration and startup notes

Configure how the server starts and what you expose to clients using environment variables. Common options include specifying a path to a configuration file or providing a JSON string directly. You can also enable security-related settings via environment variables.

Typical startup in stdio mode uses the Python entry point that launches the server with standard input/output. You can customize the run through the environment and by passing a config path or config string.

Development and quality tooling

Code quality and reliability rely on the following tools: Ruff for linting and formatting, Mypy for static type checking, and Pytest for testing. These tools are integrated into the development workflow.

# Linting
ruff check

# Formatting
ruff format

# Static analysis
./scripts/static-analysis.sh

# Run tests with coverage
./scripts/test.sh
./scripts/test-cov.sh

Available tools

ruff

Linting and formatting tool used to ensure code quality.

mypy

Static type checker to catch type errors before runtime.

pytest

Test runner used to execute unit tests.

pre-commit

Pre-commit hooks to enforce quality checks before commits.