holoviz-mcp
by MarcSkovMadsen
Overview
Enables AI assistants to build interactive dashboards and data visualizations with HoloViz libraries like Panel, hvPlot, Lumen, and Datashader, by providing intelligent access to documentation, component information, and a display server.
Installation
docker run -it --rm -p 8000:8000 -e HOLOVIZ_MCP_TRANSPORT=http -v ~/.holoviz-mcp:/root/.holoviz-mcp ghcr.io/marcskovmadsen/holoviz-mcp:latestEnvironment Variables
- DISPLAY_DB_PATH
- JUPYTER_SERVER_PROXY_URL
- HOLOVIZ_MCP_USER_DIR
- HOLOVIZ_MCP_DEFAULT_DIR
- HOLOVIZ_MCP_LOG_LEVEL
- HOLOVIZ_MCP_SERVER_NAME
- HOLOVIZ_MCP_TRANSPORT
- HOLOVIZ_MCP_HOST
- HOLOVIZ_MCP_PORT
- ANONYMIZED_TELEMETRY
- UPDATE_DOCS
Security Notes
The server includes a `holoviz_display` tool that executes arbitrary Python code provided via the API or UI (e.g., using `exec()` in `display_mcp/utils.py`), which is a significant security risk. The `README.md` explicitly warns about this. The `take_screenshot` tool uses Playwright to visit arbitrary URLs, which could pose SSRF risks if the URL is not sanitized. While the default MCP server transport is STDIO, it can be configured for HTTP and exposed externally (e.g., via Docker on `0.0.0.0`), increasing network attack surface. No obvious hardcoded secrets were found in the truncated source.
Similar Servers
ha-mcp
Provides AI agents with complete control over Home Assistant via REST and WebSocket APIs, offering a comprehensive suite of tools for smart home management, automation, and debugging.
gis-mcp
A Model Context Protocol (MCP) server that provides AI agents and LLMs with comprehensive GIS capabilities, enabling geospatial analysis, data gathering, and transformations through natural language.
mcpcat-python-sdk
An analytics and observability SDK for Multi-modal Conversational Platform (MCP) servers, capturing user behavior and tool interactions for product development and debugging.
luma-mcp
Provides multi-model vision understanding capabilities to AI assistants that lack native image understanding.