# Omnara MCP server

> Launch and manage durable AI agents on the open-source Omnara managed-agent platform from your MCP client.

- Listing: https://mcp.tc/i/omnara
- Connect: use the server's own URL `https://app.omnara.com/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: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: omnara-ai
- Homepage: <https://www.omnara.com>
- Repository: <https://github.com/omnara-ai/omnara>

## About

Omnara is an open-source managed agent platform that runs AI agents on any model and any machine, with tools, secrets, permissions and streaming built in. This MCP server lets a client launch and manage Omnara agents.

The hosted endpoint is at app.omnara.com/mcp over streamable HTTP. Users sign in through the browser with OAuth, so no tokens need to be pasted. Omnara can also be self-hosted under Apache 2.0.

## What it can do

- Launch Omnara agents from an MCP client
- Manage running agents
- Works with Claude Code, Codex, Cursor and other OAuth-capable clients

## Example prompts

- "Launch an Omnara agent to report free disk space on my machine"
- "Show the agents currently running in my Omnara project"
- "Send a follow-up message to my Omnara machine assistant agent"

## Install

### Claude Code

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

```bash
claude mcp add --transport http omnara https://app.omnara.com/mcp
```

2. Start Claude Code, type `/mcp`, pick **omnara** and choose **Authenticate**. A browser window opens for the omnara-ai 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 **Omnara** and paste this URL:

```url
https://app.omnara.com/mcp
```

3. Click **Add**, then **Connect**, and sign in when omnara-ai 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=Omnara&connectorUrl=https%3A%2F%2Fapp.omnara.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://app.omnara.com/mcp` and click **Add**.

3. Click **Connect** and sign in when omnara-ai 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://app.omnara.com/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to omnara-ai 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=omnara&config=eyJ1cmwiOiJodHRwczovL2FwcC5vbW5hcmEuY29tL21jcCJ9>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "omnara": {
      "url": "https://app.omnara.com/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=omnara&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapp.omnara.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"omnara","type":"http","url":"https://app.omnara.com/mcp"}'
```

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "omnara": {
      "type": "http",
      "url": "https://app.omnara.com/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": {
    "omnara": {
      "serverUrl": "https://app.omnara.com/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 omnara --url https://app.omnara.com/mcp
codex mcp login omnara
```

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

`config.toml`:

```toml
[mcp_servers.omnara]
url = "https://app.omnara.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http omnara https://app.omnara.com/mcp
```

Then, inside Gemini CLI, run `/mcp auth omnara` 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": {
    "omnara": {
      "type": "http",
      "url": "https://app.omnara.com/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://app.omnara.com/mcp`.

## Details

- Server version: 0.1.0
- Last checked: 2026-10-25 (reachable, asks for credentials)
- Listed: 2026-10-25
- Updated: 2026-10-25

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