Skip to content
MCP server

Cerebras MCP by usefulapi

Hosted MCP server to list, inspect and chat with Cerebras-hosted models from AI clients

Install
Pricing
Freemium
Platforms
Web, API, CLI
Runs
Remotely
Version
1.7.1
Listing updated
today

About Cerebras MCP by usefulapi

Cerebras MCP by usefulapi is a freemium MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.

The README says this is a hosted connector that lets Claude, Cursor or another MCP client work with a Cerebras account without installing anything locally. Once connected, the assistant can enumerate the models available to your account, read the details of a single model by id, and send a conversation to a model to get its reply along with token usage.

Access works through OAuth: the login page asks for a Cerebras API key, which the server uses to call the Cerebras API on your behalf and to derive a private account id for usage metering. The server exposes three read-only Cerebras tools and four usefulapi tools for checking usage, managing a Pro subscription and sending feature requests.

It suits developers and small teams who already call open-weight models on Cerebras and want to query or test them from an AI assistant. The service is an independent product run by usefulapi and is not affiliated with or endorsed by Cerebras.

Install

Run in a terminal

claude mcp add --transport http cerebras https://cerebras.usefulapi.io/mcp

Add to Settings → Connectors → Add custom connector

https://cerebras.usefulapi.io/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

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

Add to .vscode/mcp.json

{
  "servers": {
    "cerebras": {
      "type": "http",
      "url": "https://cerebras.usefulapi.io/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "cerebras": {
      "serverUrl": "https://cerebras.usefulapi.io/mcp"
    }
  }
}

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

{
  "mcpServers": {
    "cerebras": {
      "type": "http",
      "url": "https://cerebras.usefulapi.io/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (7)

Taken from the project documentation; the running server may differ.

cerebras_list_models
List the models available to your Cerebras account.
cerebras_get_model
Get one model by id: its id, object type, creation time and owner.
cerebras_chat_completion
Send a conversation to a Cerebras model and return its reply and usage.
cerebras_usage_status
Report the caller's current usage against the plan limit.
cerebras_request_feature
Send usefulapi a request for a capability the Cerebras tools lack.
cerebras_upgrade
Get a Pro or Pro+ paid plan link or change an existing Pro plan to Pro+.
cerebras_cancel_subscription
Cancel the Pro subscription at the end of the paid period.

What it does

List available models
Lists the models on your Cerebras account, such as gpt-oss-120b or qwen-3.8-27b.
Read model details
Fetches one model by id, including its id, object type, creation time and owner.
Chat completion requests
Sends a conversation to a chosen model and returns the full API response with usage counts.
OAuth login with API key
Signs in through a login page that accepts your Cerebras API key, so no keys go in client config.
Usage and plan tools
Reports calls used against the monthly limit and supports upgrading or cancelling a paid plan.

Good for

  • Check which Cerebras models are available before picking one for a project
  • Test a prompt against a specific model from inside Claude or Cursor
  • Confirm a model id still exists before running a batch job
  • Monitor how many tool calls remain on the monthly plan

Pricing

Freemium, from $9 a month

Free plan with 50 tool calls/month; Pro from $9/mo or $90/yr

Prices change. Check usefulapi.io before you buy.

Cerebras MCP by usefulapi FAQ

Is this an official Cerebras product?

No. usefulapi is an independent service and is not affiliated with or endorsed by Cerebras. The server calls the Cerebras API with your own access.

What do I need to connect?

The login page asks for a Cerebras API key, which you can create in the Cerebras Cloud Console under API Keys.

Which AI clients can I use?

Any client that supports remote MCP servers over Streamable HTTP with OAuth login, including Claude, ChatGPT, Claude Code, Cursor, VS Code and Codex.

What does it cost?

The Free plan gives 50 tool calls per month. Pro is $9 per month or $90 per year for 10,000 calls, and Pro+ is $39 per month or $390 per year for 100,000 calls. Each subscription covers this server only.

Is Cerebras MCP by usefulapi free?

Cerebras MCP by usefulapi has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.

How do I add Cerebras MCP by usefulapi to Claude Code?

Run this command in your terminal: claude mcp add --transport http cerebras https://cerebras.usefulapi.io/mcp

What are the best alternatives to Cerebras MCP by usefulapi?

The closest alternatives to Cerebras MCP by usefulapi are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

Where this comes from

  • Description: written from the project's README, the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers

Alternatives to Cerebras MCP by usefulapi

  1. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  2. signafAIde

    MCP server

    Local MCP server to set up, verify and check coverage of signed agent action records

    Runs locally
    • 5 tools
    • Freemium
    • Security
  3. Toolkien

    MCP server

    One MCP gateway for all your MCP servers, with code mode, permissions and audit

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • AI models and LLM tooling
  4. Lugh

    MCP server

    Write, check and dry-run Lugh agent programs with policy, budgets and approvals

    Runs locally
    • 5 tools
    • Open source
    • AI models and LLM tooling
  5. HypePaper

    MCP server

    Research papers, benchmarks, citations and topic experts for AI assistants

    • 58 tools
    • Remote
    • Freemium
    • AI models and LLM tooling