viznoir

Cinema-quality science visualization for AI agents — headless VTK via MCP.

Python Local Linux

★ 20 stars Last pushed 2026-11-03 License: MIT

View repository → Website →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

uvx viznoir

Or add to your MCP client config:

{
  "mcpServers": {
    "viznoir": {
      "command": "uvx",
      "args": [
        "viznoir"
      ]
    }
  }
}

Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.

Eight local research workflow tools for task setup, saved progress, stage guidance, configurable report review, and delivery checks.

MCP server for ITASCA PFC, FLAC3D, 3DEC, MPoint and MassFlow: search docs, run simulations, plot.

Checks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.

Deep research via the OpenAI Responses API or Open Deep Research (smolagents), with web search and code interpreter support.

Give your AI agent what web search doesn't reach: podcasts and videos, Chinese communities, papers.

Data from the Official MCP Registry