# RobotTraining.jobs MCP server

> Search open robot training jobs and see advertised hourly pay and job market counts by kind of work and employer

- Listing: https://mcp.tc/i/robottraining-jobs
- Connect: use the server's own URL `https://robottraining.jobs/api/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [Search & Web Data](https://mcp.tc/c/search-web)
- Vendor: RobotTraining.jobs
- Homepage: <https://robottraining.jobs/>

## About

Connects to RobotTraining.jobs, a listing of open robot training jobs such as teleoperation, demonstration and video data collection, data annotation, robot QA, fleet operations, and autonomous vehicle and drone operation. Jobs come from about 60 employers and programs and are read daily from the employers' own job feeds. You can search roles, check what each kind of work pays, and see how many roles are open.

Runs as a hosted streamable HTTP endpoint. No sign-in or API key is needed. All tools are read-only, and results include links that open the role on RobotTraining.jobs, where the user applies. Some programs pay the site a referral fee, which does not change the pay figures.

## What it can do

- Search open robot training jobs with optional filters
- Filter by kind of work, employer, country and minimum hourly pay
- See median and typical hourly pay by kind of work
- Count open roles by kind of work and employer
- See how many jobs were listed in the last 7 days
- Scope market counts to one country

## Tools (3)

- `search_robot_training_jobs`: Search open robot training jobs with title, employer, kind of work, pay, location and apply link. (read-only)
- `get_robot_training_pay`: Get median and typical hourly pay range by kind of work from advertised rates. (read-only)
- `get_robot_training_market`: Get open and recent job counts by kind of work and employer, optionally for one country. (read-only)

## Example prompts

- "Find remote robot teleoperation jobs paying at least $25 an hour"
- "What does egocentric video recording work pay per hour?"
- "How many robot training jobs are open in the US right now?"
- "Which employers have the most fleet operations roles open?"

## Install

### Claude Code

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

```bash
claude mcp add --transport http robottraining-jobs https://robottraining.jobs/api/mcp
```

2. Start Claude Code and type `/mcp`. **robottraining-jobs** should show as connected.

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 **RobotTraining.jobs** and paste this URL:

```url
https://robottraining.jobs/api/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

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=RobotTraining.jobs&connectorUrl=https%3A%2F%2Frobottraining.jobs%2Fapi%2Fmcp>) (opens connector settings)

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

3. Turn it on in a chat from the tools menu.

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://robottraining.jobs/api/mcp` as the server URL, then for authentication choose **No authentication**.

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=robottraining-jobs&config=eyJ1cmwiOiJodHRwczovL3JvYm90dHJhaW5pbmcuam9icy9hcGkvbWNwIn0%3D>) (opens Cursor)

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

`mcp.json`:

```json
{
  "mcpServers": {
    "robottraining-jobs": {
      "url": "https://robottraining.jobs/api/mcp"
    }
  }
}
```

### VS Code

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

Or from a terminal:

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

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

`.vscode/mcp.json`:

```json
{
  "servers": {
    "robottraining-jobs": {
      "type": "http",
      "url": "https://robottraining.jobs/api/mcp"
    }
  }
}
```

### 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": {
    "robottraining-jobs": {
      "serverUrl": "https://robottraining.jobs/api/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

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

### Codex

```bash
codex mcp add robottraining-jobs --url https://robottraining.jobs/api/mcp
```

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

`config.toml`:

```toml
[mcp_servers.robottraining-jobs]
url = "https://robottraining.jobs/api/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http robottraining-jobs https://robottraining.jobs/api/mcp
```

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": {
    "robottraining-jobs": {
      "type": "http",
      "url": "https://robottraining.jobs/api/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://robottraining.jobs/api/mcp`.

## Recent changes

- 2026-10-30 11:46 UTC: 1 tool changed. Server instructions changed. Source: automatic check. Worth a look: new server instructions. Changed: search\_robot\_training\_jobs.
- 2026-10-26 14:45 UTC: 3 tools changed. Source: automatic check. Changed: get\_robot\_training\_market, get\_robot\_training\_pay, search\_robot\_training\_jobs.
- 2026-10-20 13:35 UTC: 2 tools changed. Server instructions changed. Source: automatic check. Worth a look: new server instructions. Changed: get\_robot\_training\_pay, search\_robot\_training\_jobs.
- 2026-10-15 19:20 UTC: Tracking started: 3 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/robottraining-jobs#history (Atom feed: https://mcp.tc/i/robottraining-jobs/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.0.0
- MCP protocol version: 2026-07-28
- Last checked: 2026-11-18 (reachable)
- Listed: 2026-10-15
- Updated: 2026-10-30

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