# Scite MCP server

> Search full-text scientific literature with Smart Citations to ground AI answers in real, evaluated sources.

- Listing: https://mcp.tc/i/scite
- Connect: use the server's own URL `https://api.scite.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: [Docs & Knowledge](https://mcp.tc/c/docs-knowledge)
- Vendor: Scite (Research Solutions)
- Homepage: <https://scite.ai/mcp>

## About

Scite connects an AI assistant to its scientific literature database and Smart Citations, which show whether later studies support or contradict a paper. You can search full-text literature, check claims against evidence, and access full-text articles, including through your institution's library holdings.

It runs as a hosted streamable HTTP endpoint at api.scite.ai/mcp. Users sign in with a Scite account through OAuth 2.0, and the Scite site says a free trial or account is required. It works with ChatGPT, Claude, Copilot and other MCP clients.

## What it can do

- Search full-text scientific literature
- Verify claims against supporting or contradicting evidence
- Read Smart Citation data for papers
- Access full-text articles
- Connect to library holdings for full-text access

## Example prompts

- "Find papers on CRISPR gene editing and show how they are cited"
- "Do later studies support or contradict this claim about intermittent fasting?"
- "Search the literature for recent work on solid-state batteries"
- "Give me sources with citation context for this paragraph"

## Install

### Claude Code

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

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

2. Start Claude Code, type `/mcp`, pick **scite** and choose **Authenticate**. A browser window opens for the Scite (Research Solutions) sign-in.

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

### Claude Desktop

1. Open **Settings → Connectors** and click **Add custom connector**.

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

```url
https://api.scite.ai/mcp
```

3. Click **Add**, then **Connect**, and sign in when Scite (Research Solutions) 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=Scite&connectorUrl=https%3A%2F%2Fapi.scite.ai%2Fmcp>) (opens connector settings)

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

3. Click **Connect** and sign in when Scite (Research Solutions) 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, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://api.scite.ai/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Scite (Research Solutions) to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=scite&config=eyJ1cmwiOiJodHRwczovL2FwaS5zY2l0ZS5haS9tY3AifQ%3D%3D>) (opens Cursor)

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

`mcp.json`:

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

Cursor shows **Needs login** next to the server. Click it to sign in.

### VS Code

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

Or from a terminal:

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

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "scite": {
      "type": "http",
      "url": "https://api.scite.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": {
    "scite": {
      "serverUrl": "https://api.scite.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 scite --url https://api.scite.ai/mcp
codex mcp login scite
```

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

`config.toml`:

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

### Gemini CLI

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

Then, inside Gemini CLI, run `/mcp auth scite` 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": {
    "scite": {
      "type": "http",
      "url": "https://api.scite.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://api.scite.ai/mcp`.

## Details

- Server version: 1.0.0
- Last checked: 2026-10-03 (reachable, asks for credentials)
- Listed: 2026-10-03
- Updated: 2026-10-03

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