Skip to content
MCP server

Cerebrium Docs

Search the Cerebrium docs and send documentation feedback from your coding agent

Pricing
Free
Platforms
API, CLI
Runs
Remotely
Version
0.1.1
Listing updated
1 day ago

About Cerebrium Docs

Cerebrium Docs is a free MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

This is the documentation server for Cerebrium, a serverless GPU and CPU platform billed by the second for real-time AI workloads. It needs no account or key and exposes live search over the published docs, plus a tool for submitting feedback on them. It is distributed alongside an agent skill that teaches a coding agent to write a valid cerebrium.toml, pick hardware and a region, deploy, call the endpoint and debug.

The skill's references cover CLI flags, every config key and default, the 13 accepted compute identifiers with limits and regional availability, and troubleshooting for failed builds and cold starts. Install paths cover Claude Code, Codex, Cursor and the Gemini CLI.

The platform itself has a free Hobby plan plus compute, and Standard at $100 a month plus compute, with GPU rates from $0.000164 per second for a T4 to $0.00167 for a B200.

Install

Run in a terminal

claude mcp add --transport http docs https://cerebrium.ai/docs/mcp

Add to Settings → Connectors → Add custom connector

https://cerebrium.ai/docs/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "docs": {
      "url": "https://cerebrium.ai/docs/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "docs": {
      "type": "http",
      "url": "https://cerebrium.ai/docs/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "docs": {
      "serverUrl": "https://cerebrium.ai/docs/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "docs": {
      "type": "http",
      "url": "https://cerebrium.ai/docs/mcp"
    }
  }
}

Tools this server provides (3)

Read directly from the server.

search_cerebrium
Search across the Cerebrium knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Cerebrium, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of
query_docs_filesystem_cerebrium
Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Cerebrium documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "g
submit_feedback
Report a problem with this documentation site so the docs team can fix it. Use when a documentation page is incorrect, outdated, confusing, incomplete, or has a broken example. This is for feedback about the documentation content itself — not for product support requests or feedback about this tool or assistant.

What it does

Docs search
Search and read the published Cerebrium documentation.
Feedback tool
Submit documentation feedback from the agent.
Agent skill
Teaches deployment workflow, config and safety rules.
Hardware reference
Compute identifiers, limits and region availability.
Multi-client install
Plugins for Claude Code, Codex, Cursor and Gemini CLI.

Good for

  • Write a cerebrium.toml for a vLLM model
  • Pick a GPU and region for an inference app
  • Debug queued requests under load
  • Look up scaling and concurrency settings

Pricing

Free

Docs server free, no key; platform billed per second

Prices change. Check cerebrium.ai before you buy.

Cerebrium Docs FAQ

Does the docs server need a key?

No. The README says no account access or key is needed.

Which tools does it expose?

search_cerebrium, query_docs_filesystem_cerebrium and submit_feedback.

How is the platform billed?

Compute is billed per second; Hobby is free plus compute and Standard is $100 a month plus compute.

How do I install the skills?

npx skills add CerebriumAI/cerebrium-skills -g -y and npx add-mcp https://cerebrium.ai/docs/mcp.

Is Cerebrium Docs free?

Yes. Cerebrium Docs is free to use.

How do I add Cerebrium Docs to Claude Code?

Run this command in your terminal: claude mcp add --transport http docs https://cerebrium.ai/docs/mcp

What are the best alternatives to Cerebrium Docs?

The closest alternatives to Cerebrium Docs are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Cerebrium Docs

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools