# Markaestro MCP server

> Lets AI agents schedule, publish, and review social media posts and brand analytics through the Markaestro API.

- Repository: https://github.com/markaestro/markaestro-agents
- Page: https://hostedmcp.org/servers/markaestro/mcp
- Transport: stdio, remote
- Stars: 0
- License: MIT
- Latest version: 0.5.0

## Install

### Claude Code

```sh
claude mcp add --env 'MARKAESTRO_API_KEY=<YOUR_MARKAESTRO_API_KEY>' mcp -- npx -y @markaestro/mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@markaestro/mcp"
      ],
      "env": {
        "MARKAESTRO_API_KEY": "<YOUR_MARKAESTRO_API_KEY>"
      }
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@markaestro/mcp"
      ],
      "env": {
        "MARKAESTRO_API_KEY": "<YOUR_MARKAESTRO_API_KEY>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@markaestro/mcp"],"env":{"MARKAESTRO_API_KEY":"<YOUR_MARKAESTRO_API_KEY>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@markaestro/mcp"
      ],
      "env": {
        "MARKAESTRO_API_KEY": "<YOUR_MARKAESTRO_API_KEY>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add mcp --env 'MARKAESTRO_API_KEY=<YOUR_MARKAESTRO_API_KEY>' -- npx -y @markaestro/mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@markaestro/mcp"]

[mcp_servers.mcp.env]
MARKAESTRO_API_KEY = "<YOUR_MARKAESTRO_API_KEY>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'MARKAESTRO_API_KEY=<YOUR_MARKAESTRO_API_KEY>' mcp npx -- -y @markaestro/mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@markaestro/mcp"
      ],
      "env": {
        "MARKAESTRO_API_KEY": "<YOUR_MARKAESTRO_API_KEY>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `MARKAESTRO_API_KEY` | yes | yes | Workspace API key (mk_live_ or mk_test_) from Settings, API Access. Covers one brand or all brands in the workspace. |
| `MARKAESTRO_READ_ONLY` | no | no | Set to 1 to register only the reading tools. |

## Tools (18)

- `list_products`
- `list_destinations`
- `get_brand_profile`
- `create_post`
- `update_post`
- `publish_post`
- `mark_post_posted`
- `delete_post`
- `bulk_posts`
- `create_posts`
- `upload_media`
- `get_analytics`
- `list_post_analytics`
- `get_post_analytics_history`
- `refresh_analytics`
- `suggest_post_times`
- `get_channel_rules`
- `get_tiktok_posting_options`

## FAQ

### Can the AI agent delete published posts?

No, the agent cannot delete published posts, take them down from a platform, or archive an Evergreen queue; those actions must be done by the user.

### How does the server handle duplicate posting requests?

The server sends an Idempotency-Key on every mutation so that retried requests replay the original action instead of creating a duplicate post.

### Is there a way to use the server in a read-only mode?

Yes, you can send the `x-markaestro-read-only: 1` header to receive only the reading tools.

### Does the server support local file uploads?

Yes, running the server locally over stdio allows the upload_media tool to read files from your local machine.
