Cerebras MCP by usefulapi

io.usefulapiPublished by usefulapi.ioOfficial publisherv1.3.4Updated Nov 7, 2026

List models, read model details and send chat messages in Cerebras.

The publisher's own server: Ably MCP by usefulapi

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Hosted MCP server that lets an assistant list Cerebras models, read model details and send chat completions to a Cerebras model.

What you can do
  • List the models available on your Cerebras account, with a note that model ids change
  • Read one model's id, object type, creation time and owner
  • Send a conversation to a Cerebras model and get the full reply with choices, message content and usage (non-streaming)
  • Check monthly tool-call usage, request a missing feature, and manage a Pro subscription
When to use it
Useful when you want to query Cerebras models or run prompts against them from Claude, Cursor, VS Code or another MCP client without writing API code, and are fine with a hosted third-party gateway and its call quotas.
Requirements
Remote streamable HTTP endpoint; no local install. Connect with the endpoint URL only and sign in via OAuth; the login page asks for a Cerebras API key created in the Cerebras Cloud Console, which the server validates and stores per user. A free plan allows 50 tool calls per month; paid plans are available.
Before you install
You hand your Cerebras API key to a third-party host, which stores it per user. Chat calls consume your Cerebras token limits and the server's monthly call quota. Subscription tools return Stripe Checkout links and can cancel Pro, with no refund for the current period. Model output is generated text, not human-written.

Installation

In SourceWeft

  1. Open Cerebras MCP by usefulapi in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.usefulapi%2Fcerebras/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

README

Cerebras 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 /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
json
{  "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

ToolTypeWhat it does
cerebras_list_modelsreadList models
cerebras_get_modelreadGet a model
cerebras_chat_completionreadChat completion
cerebras_usage_statusmetaUsage status (free-tier meter)
cerebras_request_featuremetaRequest a missing feature
cerebras_upgrademetaUpgrade to Pro or Pro+
cerebras_cancel_subscriptionmetaCancel 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

PlanPriceLimit
Free$050 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.

Source: servers/cerebras/README.md at commit 4046075

Tools

3

cerebras_list_models

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.

Takes no parameters.

cerebras_get_model

Get a model

Get one model by id: its id, object type, creation time and owner. Cerebras API: GET /v1/models/{model_id}.

Parametersmodel_idrequired

cerebras_chat_completion

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.

Parametersmodelrequiredtop_pmessagesrequiredtemperaturereasoning_effortmax_completion_tokens

Version history

6
  1. v1.3.4LatestNov 7, 2026
  2. v1.2.3Nov 5, 2026
  3. v1.2.2Nov 5, 2026
  4. v1.2.1Nov 4, 2026
  5. v1.2.0Nov 3, 2026
  6. v1.1.1Nov 3, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Usefulapi integrations

Ably MCP by usefulapi

io.usefulapiOfficial publisher

Ably MCP by usefulapi's hosted MCP server, published by usefulapi.io; no sign-in required; Streamable HTTP; 15 tools.

Streamable HTTPWeb executable
Communication & Collaboration15 toolsNov 7, 2026

Woffu MCP by usefulapi

io.usefulapiOfficial publisher

Hosted read-only MCP server that lets an assistant look up Woffu company users, employment contracts, departments and offices.

Streamable HTTPWeb executable
Business & Commerce5 toolsNov 7, 2026

White Label Loyalty MCP by usefulapi

io.usefulapiOfficial publisher

Hosted MCP server for White Label Loyalty: browse rewards, read a customer's points wallet and tier progress, and buy rewards with points.

Streamable HTTPWeb executable
Business & Commerce5 toolsNov 7, 2026

Weekdone MCP by usefulapi

io.usefulapiOfficial publisher

Hosted Weekdone connector that lets an assistant read weekly reports, teams, objectives and KPIs, and add report items, comments and KPI values.

Streamable HTTPWeb executable
Data & Analytics15 toolsNov 7, 2026

WebinarKit MCP by usefulapi

io.usefulapiOfficial publisher

Hosted read-only MCP server that lets an assistant list WebinarKit webinars, their dates, series, meetings and white-label sub-accounts.

Streamable HTTPWeb executable
Business & Commerce5 toolsNov 7, 2026