List models, read model details and send chat messages in Cerebras. For developers and teams who call open-weight models on their Cerebras account. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"cerebras": {
"url": "https://cerebras.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"cerebras": {
"type": "http",
"url": "https://cerebras.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
List the models on your Cerebras account, then read one model's details before you choose it.
cerebras_list_models cerebras_get_model
Send a chat conversation to a model you picked and read its reply with the token usage. Each call uses your Cerebras limits.
cerebras_list_models cerebras_chat_completion
Model ids change. Read one model by id before a batch job, to confirm the id still exists on your account.
cerebras_list_models cerebras_get_model
The login page asks for your Cerebras API key.
Find it in the Cerebras Cloud Console → API Keys (cloud.cerebras.ai). Your key is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
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: the login page asks for your Cerebras API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Cerebras connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
cerebras_list_models | read | List models List the models available to your Cerebras account (for example gpt-oss-120b, qwen-3.8-27b). Call this first, because model ids change. Cerebras API: GET /v1/models. |
cerebras_get_model | read | Get a model Get one model by id: its id, object type, creation time and owner. Cerebras API: GET /v1/models/{model_id}. |
cerebras_chat_completion | read | Chat completion Send a conversation to a Cerebras model and return its reply (the full API response: choices, message content, usage). Streaming is off. Output is model-generated text, not human-written. Each call uses tokens from your Cerebras limits. Cerebras API: POST /v1/chat/completions. |
cerebras_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
cerebras_request_feature | Request a missing feature Tell usefulapi that the user needs something the Cerebras tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
cerebras_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Cerebras (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $39/month or $390/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
cerebras_cancel_subscription | Cancel the Pro subscription Cancel the caller's Cerebras Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run cerebras_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this Cerebras 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].
See which models your account can use. Ask a model for a reply. Check a model id before a batch job. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by Cerebras. The server calls the Cerebras API with your own Cerebras access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Cerebras API key. See Before you connect for where to find it.
No. 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: the login page asks for your Cerebras API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Cerebras API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Cerebras.
All 3 Cerebras tools are marked read-only.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this Cerebras server only. Cancel any time: Pro then runs to the end of the paid period. Run cerebras_usage_status to see how many calls you used.
Ask the AI to run cerebras_upgrade: it returns a Stripe Checkout link. To cancel, run cerebras_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with cerebras_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.