# Tavotto MCP server

> Edit, journal-check and export scientific matplotlib figures from your AI agent.

- Listing: https://mcp.tc/i/tavotto
- Connect: this is a local (stdio) server; install it on your machine (see Install). The listing link is a page, not an MCP endpoint.
- Type: local (stdio)
- Auth: no API key needed
- Category: [Developer Tools](https://mcp.tc/c/developer-tools)
- Vendor: Tavotto
- Homepage: <https://www.tavotto.com>
- Repository: <https://github.com/Tavotto/Tavotto>
- Package: pypi `tavotto`

## About

Tavotto connects an AI assistant to a figure editor for matplotlib. It opens figures drawn by a script or an AI, lets you adjust titles, legends, curves and layout, arrange multi-panel pages in millimetres, and check them against a publication profile (font floor, column width, dpi) before export to PDF, PNG, TIFF or SVG. Scripts stay untouched unless you ask for a write-back.

It runs locally as a PyPI package started with uvx over stdio, alongside the Tavotto desktop app or the pip-installed version. Rendering, layout and export run on your machine. The MCP server itself has no documented sign-in or API key; the optional built-in assistant panel can use your own model subscription or API key.

## What it can do

- Edit titles, legends, ticks and curves on matplotlib figures
- Lay out multi-panel pages in millimetres
- Check figures against journal publication profiles before export
- Export PDF, PNG, TIFF and SVG at 300 to 1200 ppi
- Keep original scripts untouched with edits saved as overrides
- Restore earlier layouts from a timeline

## Example prompts

- "Open Fig1.py in Tavotto and move the legend to the top left at 7 pt."
- "Check my figure against the journal profile before export."
- "Arrange these three panels in a row with (a)(b)(c) labels."
- "Export the page as a 600 ppi TIFF."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport stdio tavotto -- uvx tavotto mcp
```

2. Start Claude Code and type `/mcp`. **tavotto** should show as connected.

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Developer → Edit Config**. It opens `claude_desktop_config.json`. Add:

`claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "tavotto": {
      "command": "uvx",
      "args": [
        "tavotto",
        "mcp"
      ]
    }
  }
}
```

2. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=tavotto&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJ0YXZvdHRvIiwibWNwIl19>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "tavotto": {
      "command": "uvx",
      "args": [
        "tavotto",
        "mcp"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=tavotto&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22tavotto%22%2C%22mcp%22%5D%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"tavotto","type":"stdio","command":"uvx","args":["tavotto","mcp"]}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "tavotto": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "tavotto",
        "mcp"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "tavotto": {
      "command": "uvx",
      "args": [
        "tavotto",
        "mcp"
      ]
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add tavotto -- uvx tavotto mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.tavotto]
command = "uvx"
args = ["tavotto", "mcp"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add tavotto uvx tavotto mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients that start local servers accept this shape:

```json
{
  "mcpServers": {
    "tavotto": {
      "command": "uvx",
      "args": [
        "tavotto",
        "mcp"
      ]
    }
  }
}
```

Zed puts servers under `context_servers` in its settings, with the same `command`, `args` and `env` fields.

Needs uv (Python) on your computer.

## Recent changes

- 2026-11-14 14:23 UTC: Tracking started: version 0.21.2. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/tavotto#history (Atom feed: https://mcp.tc/i/tavotto/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 0.21.2
- Last checked: 2026-11-14
- Listed: 2026-11-14
- Updated: 2026-11-14

---
Source: https://mcp.tc/i/tavotto (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
