mcpField
F
Fireworks AI MCP by usefulapi

Fireworks AI MCP by usefulapi

Remote
usefulapi.ioAI & Agents0Updated today

About Fireworks AI MCP by usefulapi

Fireworks AI MCP by usefulapi is a hosted MCP server for Fireworks AI users to inspect models, deployments, datasets, and fine-tuning jobs from MCP clients. It also supports dataset creation and deployment deletion.

Key features

  1. 01Inspect account and model details
  2. 02List deployments and deployed models
  3. 03List and inspect datasets
  4. 04View fine-tuning and batch inference jobs
  5. 05Create datasets or delete deployments

Use cases

  1. 01Review models in a Fireworks AI account
  2. 02Check deployment and deployed model details
  3. 03Browse datasets and fine-tuning jobs
  4. 04Create datasets or remove deployments

MCP support

It exposes Fireworks AI inspection and management tools to MCP clients through a remote server. On first connection, users submit a Fireworks API key, which is validated and stored per user.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://fireworks.usefulapi.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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

14
ParameterTypeRequiredDescription
account_idstringNoFireworks account id. Overrides FIREWORKS_ACCOUNT_ID for this call.

Details

From the project README

Fireworks AI MCP by usefulapi

Inspect Fireworks AI models, deployments, datasets and fine-tuning jobs from Claude, Cursor, or any MCP client. Hosted, no local install — connect with your Fireworks API key.

Live endpoint: https://fireworks.usefulapi.io/mcp · Homepage: https://usefulapi.io/fireworks

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://fireworks.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http fireworks https://fireworks.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:
{
  "mcpServers": {
    "fireworks": {
      "url": "https://fireworks.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 Fireworks AI credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/fireworks/

On first connect you'll paste your Fireworks API key. It's validated, stored per-user, and scoped to you.

Tools

ToolTypeWhat it does
fireworks_get_accountreadGet account
fireworks_list_modelsreadList models
fireworks_get_modelreadGet model
fireworks_list_deploymentsreadList deployments
fireworks_get_deploymentreadGet deployment
fireworks_list_deployed_modelsreadList deployed models
fireworks_list_datasetsreadList datasets
fireworks_get_datasetreadGet dataset
fireworks_list_fine_tuning_jobsreadList fine-tuning jobs
fireworks_get_fine_tuning_jobreadGet fine-tuning job
fireworks_list_batch_inference_jobsreadList batch inference jobs
fireworks_list_usersreadList users
fireworks_create_datasetwriteCreate dataset
fireworks_delete_deploymentwriteDelete deployment
fireworks_usage_statusmetaUsage status (free-tier meter)
fireworks_request_featuremetaRequest a missing feature
fireworks_upgrademetaUpgrade to Pro (unlimited*)
fireworks_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$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 fireworks_upgrade (it returns a Stripe Checkout link). Cancel any time with fireworks_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running fireworks_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT — see LICENSE. Documentation only; the server is hosted.

Comments

Markdown supported

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.