# SciFig MCP server

> Generate, edit and convert scientific illustrations, data charts and flowcharts for research papers.

- Listing: https://mcp.tc/i/scifig
- Connect: use the server's own URL `https://mcp.scifig.ai/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [Design, Websites & CMS](https://mcp.tc/c/design)
- Vendor: SciFig
- Homepage: <https://scifig.ai/docs/api/mcp>
- Docs: <https://scifig.ai/docs/api/mcp>

## About

SciFig connects an assistant to the SciFig figure generator for researchers. The granted scopes cover generating, editing and converting images, generating charts and flowcharts, writing files, reading job status and checking credits.

It runs as a hosted streamable HTTP endpoint at https://mcp.scifig.ai/mcp. The endpoint accepts OAuth tokens and supports dynamic client registration. The vendor's documentation describes how to connect and which credentials are needed.

## What it can do

- Generate scientific illustrations from text
- Edit and convert generated images
- Generate data charts
- Generate flowcharts and diagrams
- Check job status and credit balance

## Example prompts

- "Create a graphical abstract showing lipid nanoparticle delivery to the liver."
- "Make a PRISMA flow diagram for my meta-analysis screening."
- "Generate a volcano plot from my RNA-seq results."
- "How many SciFig credits do I have left?"

## Install

### Claude Code

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

```bash
claude mcp add --transport http scifig https://mcp.scifig.ai/mcp
```

2. Start Claude Code, type `/mcp`, pick **scifig** and choose **Authenticate**. A browser window opens for the SciFig sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **SciFig** and paste this URL:

```url
https://mcp.scifig.ai/mcp
```

3. Click **Add**, then **Connect**, and sign in when SciFig asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=SciFig&connectorUrl=https%3A%2F%2Fmcp.scifig.ai%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://mcp.scifig.ai/mcp` and click **Add**.

3. Click **Connect** and sign in when SciFig asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://mcp.scifig.ai/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to SciFig to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=scifig&config=eyJ1cmwiOiJodHRwczovL21jcC5zY2lmaWcuYWkvbWNwIn0%3D>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "scifig": {
      "url": "https://mcp.scifig.ai/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=scifig&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.scifig.ai%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"scifig","type":"http","url":"https://mcp.scifig.ai/mcp"}'
```

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "scifig": {
      "type": "http",
      "url": "https://mcp.scifig.ai/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### 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": {
    "scifig": {
      "serverUrl": "https://mcp.scifig.ai/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add scifig --url https://mcp.scifig.ai/mcp
codex mcp login scifig
```

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

`config.toml`:

```toml
[mcp_servers.scifig]
url = "https://mcp.scifig.ai/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http scifig https://mcp.scifig.ai/mcp
```

Then, inside Gemini CLI, run `/mcp auth scifig` to sign in.

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

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "scifig": {
      "type": "http",
      "url": "https://mcp.scifig.ai/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.scifig.ai/mcp`.

## Details

- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-10-27
- Updated: 2026-10-27

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