About Figviz
Figviz is an MCP server for generating labeled science and math diagrams through the Figviz API. It is aimed at STEM education and visual learning, and returns hosted image URLs with configurable quality and aspect ratio.
Key features
- 01Generate diagrams from text descriptions
- 02Covers science and math topics
- 03Produces labeled images
- 04Choose image quality and aspect ratio
Use cases
- 01Create science visuals for lessons
- 02Generate math and optics diagrams
- 03Make lab setups or graphic organizers
MCP support
The server exposes a generate_diagram tool to MCP clients. It accepts a diagram description and quality and aspect-ratio options, then returns a hosted image URL.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEFigviz MCP server
Generate clear, labeled science & math diagrams (biology, chemistry, physics, K-12 math, lab setups, graphic organizers) straight from your AI assistant, via the Figviz API.
Works with any Model Context Protocol client — Claude Desktop, Cursor, Cline, Windsurf, and more.
What it does
Exposes one tool:
generate_diagram— describe a diagram in plain text and get back a hosted image URL. Options:quality(1k/2k/4k) andaspectRatio(e.g.16:9,1:1).
Example prompts:
- "labeled plant cell cross-section for 8th grade"
- "convex lens ray diagram, object between F and 2F"
- "acid–base titration setup for high school chemistry"
- "KWL chart graphic organizer, blank"
Get an API key
Create a free key (includes 3 credits) at https://figviz.com/settings/api. Figviz is pay-as-you-go — no subscription, credits never expire.
Install
Run it with npx (no install needed):
FIGVIZ_API_KEY=fvk_xxx npx -y @figviz/figviz-mcp
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"figviz": {
"command": "npx",
"args": ["-y", "@figviz/figviz-mcp"],
"env": { "FIGVIZ_API_KEY": "fvk_xxx" }
}
}
}
Cursor / Cline / Windsurf
Add the same server entry to your client's MCP config (mcp.json or the MCP
settings UI):
{
"mcpServers": {
"figviz": {
"command": "npx",
"args": ["-y", "@figviz/figviz-mcp"],
"env": { "FIGVIZ_API_KEY": "fvk_xxx" }
}
}
}
Then ask your assistant: "Use figviz to generate a labeled animal cell diagram for 7th grade."
Environment variables
| Variable | Required | Default | Description |
|---|---|---|---|
FIGVIZ_API_KEY | yes | — | Your fvk_… key from figviz.com |
FIGVIZ_API_BASE | no | https://figviz.com | Override the API host (advanced) |
Credits & pricing
Each diagram costs 1 credit (4k costs 1.5). Buy credit packs at https://figviz.com/pricing. The MCP shares the same balance as your Figviz account.
License
MIT
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.