# Clevera

> Ask your agent for how-to videos, social clips and help articles made from your recordings, and keep your Clevera help center current.

Clevera's own MCP server lets your agent work in your Clevera workspace. Ask for a how-to video, a social clip or a help article, and Clevera's AI makes it from your screen recordings. Your agent can also draft, translate and publish pages on a Clevera doc site, so your help center keeps up with each release.

What you can do with it
- Turn a recording into a how-to video, a product demo, a cleaned-up or styled video, a social clip or a help article
- Translate videos and articles
- Export videos as MP4 at 1080p, 2K or 4K, and get embeds
- Browse your library: recordings, videos, articles and transcripts
- Draft and edit doc site articles, changelog entries, sections and site pages, and publish them when you allow it
- Read site insights: what readers searched for and didn't find, unanswered questions and page feedback

How it connects
Clevera hosts it at https://app.clevera.ai/mcp. In Claude or ChatGPT, add it as a custom connector and sign in with Clevera: you pick the workspace, the doc sites and the access it gets, and the connection lasts 30 or 90 days. Claude Code, Codex, Cursor and other agents can use a Clevera API token instead, sent as an "Authorization: Bearer" header. Agent access is on Clevera's Pro, Business and Custom plans.

Good to know
- Your agent acts as you, within your role, and sees only what you can see. Everything it does shows on the Activity tab.
- Paid work starts with a quote. A token spends credits within caps per job, day and month, and anything above your line waits for an owner or admin to approve it. Every paid start from a Claude or ChatGPT connector waits for approval.
- Without publishing rights it can't change what readers see; it submits drafts for review instead.
- The Read-only preset lets it read your doc sites for research, audits and translation checks.
- Agents can't yet run website research or recorded walkthroughs, or post videos to other platforms.

- Type: Plugin
- Made by: Clevera
- Category: Customer support
- Formats: Remote MCP
- Version: 1.0.0
- Website: https://www.clevera.ai/mcp
- Page: https://pluginboard.ai/plugins/clevera

## Works with

- ChatGPT
- Claude
- Muse
- Grok Bot
- Gemini
- Grok
- GitHub Copilot
- Cursor
- Claude Code
- Codex
- Antigravity
- Gemini CLI
- Replit
- OpenClaw
- OpenCode
- Hermes Agent

## Install

### ChatGPT

In ChatGPT on the web: Plugins → + → Add custom MCP server, then paste https://app.clevera.ai/mcp under Connection. Business and Enterprise plans; Pro can add read-only servers.

### Claude

In Claude (web or desktop): Customize → Connectors → Add custom connector, then paste https://app.clevera.ai/mcp

### Muse

In Muse: In a Muse chat, ask it to create a custom connector for the MCP server at https://app.clevera.ai/mcp. Then tap Connect on the card it shows and sign in, or add your key.

### Grok Bot

In Grok Bot: In a chat with your Bot, say "Add this MCP server: https://app.clevera.ai/mcp". It confirms the details with you and sets it up, and the tools are ready from your next message.

### Gemini

In Gemini: At gemini.google.com: Settings → Connected Apps → Add a custom app, then paste https://app.clevera.ai/mcp

### Grok

In Grok on the web: At grok.com/connectors: New Connector → Custom, then enter https://app.clevera.ai/mcp and sign in if it asks.

### GitHub Copilot

Add to VS Code: vscode:mcp/install?%7B%22name%22%3A%22clevera%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapp.clevera.ai%2Fmcp%22%7D

Copilot CLI:

```shell
copilot mcp add --transport http clevera https://app.clevera.ai/mcp
```

### Cursor

Add to Cursor: cursor://anysphere.cursor-deeplink/mcp/install?name=clevera&config=eyJ1cmwiOiJodHRwczovL2FwcC5jbGV2ZXJhLmFpL21jcCJ9

Add to .cursor/mcp.json:

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

### Claude Code

Run in your terminal:

```shell
claude mcp add --transport http clevera https://app.clevera.ai/mcp
```

### Codex

Run in your terminal:

```shell
codex mcp add clevera --url https://app.clevera.ai/mcp
```

### Antigravity

Add to ~/.gemini/config/mcp_config.json:

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

### Gemini CLI

Run in your terminal:

```shell
gemini mcp add --transport http clevera https://app.clevera.ai/mcp
```

### Replit

In Replit: At replit.com/integrations, open MCP Servers → + Add MCP server, paste https://app.clevera.ai/mcp (add any headers under Advanced settings), then click Test & save.

### OpenClaw

Run in your terminal:

```shell
openclaw mcp add clevera --url https://app.clevera.ai/mcp --transport streamable-http
```

If it needs a key or sign-in: For https://app.clevera.ai/mcp, add --header NAME=value for each header it needs, or --auth oauth and then run openclaw mcp login clevera.

### OpenCode

Run in your terminal:

```shell
opencode mcp add clevera --url https://app.clevera.ai/mcp
```

If it needs a key: For https://app.clevera.ai/mcp, add --header 'NAME=value' for each header it needs. Add --global to use it in every project.

### Hermes Agent

Run in your terminal:

```shell
hermes mcp add clevera --url https://app.clevera.ai/mcp
```

Add to ~/.hermes/config.yaml:

```json
{
  "mcp_servers": {
    "clevera": {
      "url": "https://app.clevera.ai/mcp"
    }
  }
}
```

If it signs in with OAuth: If https://app.clevera.ai/mcp asks you to sign in, add --auth oauth to the command, or auth: oauth to its entry.

---
From Pluginboard (https://pluginboard.ai).