botrun-default-mcp 0.4.1

Botrun default MCP server (stdio)

botrun-default-mcp

A stdio-based MCP (Model Context Protocol) server providing PDF analysis, image analysis, web search, web scraping, and visualization tools. Designed to run via uvx with no server deployment needed.

Tools

Tool	Description
chat_with_pdf	Analyze local PDF files with Gemini (supports large files via chunked parallel processing)
chat_with_imgs	Analyze local image files with Gemini Vision
web_search	Search the web via Perplexity API (supports OpenRouter)
scrape	Scrape web pages to Markdown via ScraperAPI
create_html_page	Generate HTML pages and save to local files
create_plotly_chart	Generate interactive Plotly charts as local HTML files
create_mermaid_diagram	Generate Mermaid diagrams as local HTML files
current_date_time	Get current date/time in Asia/Taipei timezone

Installation

uvx botrun-default-mcp

Or install from source:

git clone https://github.com/sebastian-hsu/botrun_default_mcp_uv.git
cd botrun_default_mcp_uv
uv sync

Configuration

The server automatically loads environment variables from a .env file in the working directory. Just point cwd to the directory containing your .env file — no need to pass env in the MCP config.

Claude Desktop / Claude Code

Add to your MCP settings (claude_desktop_config.json or .claude.json):

{
  "mcpServers": {
    "botrun-default-mcp": {
      "command": "uvx",
      "args": ["botrun-default-mcp"],
      "cwd": "/path/to/directory/with/dotenv"
    }
  }
}

LangGraph

{
  "botrun-default-mcp": {
    "transport": "stdio",
    "command": "/path/to/uvx",
    "args": ["botrun-default-mcp"],
    "cwd": "/path/to/directory/with/dotenv"
  }
}

.env file example

GOOGLE_APPLICATION_CREDENTIALS_FOR_FASTAPI=/path/to/gcp-service-account.json
OPENROUTER_API_KEY=sk-or-v1-xxx
OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
SCRAPERAPI_API_KEY=your-scraperapi-key

Environment Variables

Variable	Required	Description
GOOGLE_APPLICATION_CREDENTIALS_FOR_FASTAPI	Yes (for PDF/image tools)	GCP service account JSON key for Gemini API
PPLX_API_KEY	Yes* (for web_search)	Perplexity API key
OPENROUTER_API_KEY	Yes* (for web_search)	OpenRouter API key (alternative to PPLX_API_KEY)
OPENROUTER_BASE_URL	With OpenRouter	OpenRouter base URL
SCRAPERAPI_API_KEY	Yes (for scrape)	ScraperAPI key
PDF_ANALYZER_MODEL	No	Gemini model for PDF analysis (default: gemini-flash-latest)
IMG_ANALYZER_MODEL	No	Gemini model for image analysis (default: gemini-flash-latest)

* Either PPLX_API_KEY or OPENROUTER_API_KEY + OPENROUTER_BASE_URL is required for web_search.

Development

# Setup
uv sync

# Run tests
uv run pytest tests/ -v

# Build
uv build

# Publish to PyPI
cd sh && bash seba_pypi.sh

License

MIT