# Cerebrium Docs [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://github.com/CerebriumAI/cerebrium-skills  
**GitHub Stars:** 0  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/cerebrium-docs

## Description
Search and read the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Read-only.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "cerebrium-docs": {
    "command": "npx",
    "args": ["-y","skills"]
  }
}
```

## Documentation & README

# Cerebrium agent skills

Official [Agent Skills](https://agentskills.io) and hosted docs MCP for
[Cerebrium](https://www.cerebrium.ai), the serverless GPU and CPU platform for real-time AI
workloads. The skills teach a coding agent to write a valid `cerebrium.toml`, pick hardware and a
region, deploy, call the endpoint, and debug the result without leaving the terminal. The MCP
gives it live search over the documentation.

Works with Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, Cline and anything else that
reads the Agent Skills format.

## Install

Any agent (installs the skills into every detected harness):

```bash
npx skills add CerebriumAI/cerebrium-skills -g -y
npx add-mcp https://cerebrium.ai/docs/mcp -n cerebrium-docs -g -y
```

Claude Code (one plugin bundles the skills and the docs MCP):

```
/plugin marketplace add CerebriumAI/cerebrium-skills
/plugin install cerebrium@cerebrium
```

Codex:

```bash
codex plugin marketplace add CerebriumAI/cerebrium-skills
```

Gemini CLI (one extension bundles the skills and the docs MCP):

```bash
gemini extensions install https://github.com/CerebriumAI/cerebrium-skills
```

Cursor loads the repository directly as an [Agent Plugin](https://agent-plugins.org): the root
`plugin.json` and `mcp.json` are the open-standard manifests, so no Cursor-specific install step
is needed.

Or agent-driven: paste this into the agent of your choice.

```
Install the Cerebrium agent toolkit following instructions from
github.com/CerebriumAI/cerebrium-skills: use `npx skills add` and `npx add-mcp`,
global and auto-confirmed for all agents (-g -y).
```

Then create an account and authenticate the CLI once:

```bash
# create an account at https://dashboard.cerebrium.ai (also where API keys are created)
pip install cerebrium   # or: brew tap cerebriumai/tap && brew install cerebrium
cerebrium login
```

Compute is billed per second: see [pricing](https://www.cerebrium.ai/pricing) for current rates
and any starting credit.

In CI, skip `login` and set `CEREBRIUM_SERVICE_ACCOUNT_TOKEN` instead.

## What is in here

One skill, structured for progressive disclosure: agents load the ~120-line core
(`skills/cerebrium/SKILL.md`, the workflow, the safety rules, the endpoint shapes) when a
Cerebrium task appears, and pull in a reference file only when the task needs it.

| Reference | Loaded when the task involves |
| --- | --- |
| `references/cli.md` | Any `cerebrium` command: full surface, flags, non-interactive auth, CI/CD, which commands cost money. |
| `references/config.md` | `cerebrium.toml`: every key, the default the API applies when it is omitted, accepted ranges, rebuild triggers. |
| `references/hardware.md` | The 13 accepted `compute` identifiers, per-GPU and per-plan limits, preference lists, regional availability, storage. |
| `references/troubleshooting.md` | Failed builds, queueing, reverted settings, the cold-start playbook. |

The docs MCP (hosted at `https://cerebrium.ai/docs/mcp`) searches and reads the published
documentation, and accepts documentation feedback: `search_cerebrium`,
`query_docs_filesystem_cerebrium`, and `submit_feedback`. No account access, no key needed. It is declared twice on purpose, because the two
formats are not interchangeable: `.mcp.json` is the Claude Code convention, and `mcp.json` at the
repository root is the path the Agent Plugins standard requires, with that standard's
`streamable-http` transport name.

The plugin metadata is likewise declared per host: `.claude-plugin/` for Claude Code,
`.agents/plugins/` for Codex, root `plugin.json` for Agent Plugins clients such as Cursor, and
`gemini-extension.json` for the Gemini CLI. `server.json` is the MCP registry entry.

## Try it

- "Deploy this FastAPI app to Cerebrium on an H100 with auth enabled, then follow the logs."
- "My Cerebrium app queues requests under load. Work out why and fix the config."
- "Which GPU and region fit a 13B vLLM model on Cerebrium, and what should the cerebrium.toml be?"

## Related surfaces

- Any docs page as markdown: append `.md` to the URL
- Page index: `https://cerebrium.ai/docs/llms.txt`
- Runnable examples: [CerebriumAI/examples](https://github.com/CerebriumAI/examples)

## Accuracy

Every default, enum, flag and signature here was read out of the CLI source and the API
validator rather than copied from a docs page. See [CONTRIBUTING.md](https://github.com/CerebriumAI/cerebrium-skills/blob/HEAD/CONTRIBUTING.md) for where
to check each kind of claim, and keep it that way.

MIT licensed.