# Cerebrium Docs

Connects your coding agent to Cerebrium documentation for serverless deployments and GPU selection. Helpful when writing a cerebrium.toml configuration.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: CerebriumAI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/CerebriumAI/cerebrium-skills
- Updated: 2026-09-04
- HTML: https://affpapa.org/en/nevibecode/mcp/cerebrium-docs

## What it does

The MCP server interfaces with a remote endpoint hosted at `https://cerebrium.ai/docs/mcp` via HTTP. It gives the assistant three tools: `search_cerebrium`, `query_docs_filesystem_cerebrium`, and `submit_feedback`. The agent looks up container specs, deployment steps, and hardware catalogs directly during a session.

No Cerebrium account or API token is needed to query the documentation. It acts purely as a reference reader. You will only need account credentials when running the standalone `cerebrium` CLI to deploy workloads.

## Requirements
- Remote server: `https://cerebrium.ai/docs/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http docs https://cerebrium.ai/docs/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add cerebrium-docs --url https://cerebrium.ai/docs/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "cerebrium-docs": {
            "url": "https://cerebrium.ai/docs/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "cerebrium-docs": {
            "type": "http",
            "url": "https://cerebrium.ai/docs/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http cerebrium-docs https://cerebrium.ai/docs/mcp
```

## When to use it
- verify schema rules and default fields for `cerebrium.toml`
- check supported GPU types and regional limits before launching instances
- diagnose cold starts and request queues using official guides
- submit corrections to documentation pages via `submit_feedback`

## Example prompts
- Search Cerebrium documentation for recommended compute configs to run a 13B model.
- Check the Cerebrium docs for all configuration keys supported in `cerebrium.toml`.
- Look up the troubleshooting guide for container build failures on Cerebrium.

## Similar
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902
- [Coder](https://affpapa.org/en/nevibecode/mcp/coder.md) — MCP server · ★ 17191
- [firebase-mcp](https://affpapa.org/en/nevibecode/mcp/firebase-mcp.md) — MCP server · ★ 4482
- [Radar Kubernetes MCP Server](https://affpapa.org/en/nevibecode/mcp/radar-kubernetes-mcp-server.md) — MCP server · ★ 3918
- [Supabase](https://affpapa.org/en/nevibecode/mcp/supabase.md) — MCP server · ★ 2974
- [Microsoft Fabric MCP Server](https://affpapa.org/en/nevibecode/mcp/microsoft-fabric-mcp-server.md) — MCP server · ★ 3804

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md