About Cerebras MCP by usefulapi
Cerebras MCP by usefulapi is a hosted server for using a Cerebras account from MCP clients. It lists account models, returns model details, and sends chat completion requests using the user's API key.
Key features
- 01List account models
- 02Retrieve model details
- 03Send chat completion requests
Use cases
- 01Check which models are available
- 02Retrieve details for a selected model
- 03Send a message to a Cerebras model
MCP support
Exposes Cerebras model-listing, model-detail, and chat-completion tools to MCP clients through a hosted endpoint. Users connect with a Cerebras API key; no local installation is required.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://cerebras.usefulapi.io/mcpclaude mcp add --transport http io-usefulapi-cerebras https://cerebras.usefulapi.io/mcp{"mcpServers":{"io-usefulapi-cerebras":{"type":"http","url":"https://cerebras.usefulapi.io/mcp"}}}Open in Cursor{"servers":{"io-usefulapi-cerebras":{"type":"http","url":"https://cerebras.usefulapi.io/mcp"}}}Open in VS Code{"mcpServers":{"io-usefulapi-cerebras":{"type":"http","url":"https://cerebras.usefulapi.io/mcp"}}}{"mcpServers":{"io-usefulapi-cerebras":{"serverUrl":"https://cerebras.usefulapi.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMECerebras MCP by usefulapi
Use your Cerebras account from Claude, Cursor, or any MCP client. List the models on your account, read model details, and send chat messages to a model. Hosted, no local install: connect with your own credentials.
Live endpoint: https://cerebras.usefulapi.io/mcp · Homepage: https://usefulapi.io
Connect
- Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste
https://cerebras.usefulapi.io/mcp. - Claude Code:
claude mcp add --transport http cerebras https://cerebras.usefulapi.io/mcp, then run/mcpto log in. - VS Code: Add to VS Code.
- Cursor and other clients: add the URL as a remote MCP server:
{
"mcpServers": {
"cerebras": {
"url": "https://cerebras.usefulapi.io/mcp"
}
}
}
Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your Cerebras credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/cerebras/
On first connect you provide a Cerebras API key, which you create under API Keys in the Cerebras Cloud Console. The server validates it and stores it per user. No keys go in config files.
Tools
| Tool | Type | What it does |
|---|---|---|
cerebras_list_models | read | List models |
cerebras_get_model | read | Get a model |
cerebras_chat_completion | read | Chat completion |
cerebras_usage_status | meta | Usage status (free-tier meter) |
cerebras_request_feature | meta | Request a missing feature |
cerebras_upgrade | meta | Upgrade to Pro (unlimited*) |
cerebras_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
Pricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro (per user) | $9/mo or $90/yr (2 months free) | Unlimited* |
*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this server only. Subscribe with cerebras_upgrade (it returns a Stripe Checkout link). Cancel any time with cerebras_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running cerebras_upgrade before then undoes the cancel. Or write to [email protected].
License
MIT — see LICENSE. Documentation only; the server is hosted.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.