# Probe MCP server

> Allows coding agents to read machine learning experiment runs, metrics, and lineage to avoid repeating previous team efforts.

- Repository: https://github.com/prbe-ai/probe
- Page: https://hostedmcp.org/servers/prbe-ai/probe
- Transport: remote
- Stars: 0
- License: Apache-2.0
- Latest version: 1.0.1

## Install

### Claude Code

```sh
claude mcp add --transport http probe https://mcp.research.prbe.ai/mcp
```

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

```json
{
  "mcpServers": {
    "probe": {
      "url": "https://mcp.research.prbe.ai/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "probe": {
      "type": "http",
      "url": "https://mcp.research.prbe.ai/mcp"
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"probe","type":"http","url":"https://mcp.research.prbe.ai/mcp"}'
```

### Codex

```sh
codex mcp add probe --url https://mcp.research.prbe.ai/mcp
```

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

```toml
[mcp_servers.probe]
url = "https://mcp.research.prbe.ai/mcp"
```

### Gemini CLI

```sh
gemini mcp add -s user --transport http probe https://mcp.research.prbe.ai/mcp
```

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

```json
{
  "mcpServers": {
    "probe": {
      "url": "https://mcp.research.prbe.ai/mcp",
      "type": "http"
    }
  }
}
```

## FAQ

### What can coding agents do with Probe?

Coding agents can read your team's ML runs, metrics, and lineage to understand how results were achieved and avoid repeating previous experiments.

### How do I install Probe for a training script?

You can install the Python SDK using pip install probe-research.
