Inspect Fireworks AI models, deployments, datasets and fine-tuning jobs. Hosted by usefulapi: connect it to Claude, ChatGPT, Cursor or any MCP client.
Turn on the Fireworks AI connector, then ask in plain words. The AI picks the tools.
For ML engineers and developers who run models and fine-tuning on Fireworks AI.
The AI lists the base and fine-tuned models, the deployments and the model-to-deployment bindings. You see what is serving in your account.
The AI lists supervised fine-tuning jobs and reads one job in detail. You see which jobs exist and how each one is going.
The AI lists the batch inference jobs in the account. You get an overview of what was submitted.
The AI lists datasets and reads one by id. It can also create a dataset metadata record; the data itself is uploaded separately.
Changes dataThe AI finds the deployment and deletes it. This stops serving that model and stops its billing, so check the id first.
Changes dataThe login page asks for your Fireworks API key.
Find it in the Fireworks dashboard → Settings → API keys. 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.
Team and Enterprise: an Owner adds the connector for the organization first.
No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"fireworks": {
"url": "https://fireworks.usefulapi.io/mcp"
}
}
} Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"fireworks": {
"type": "http",
"url": "https://fireworks.usefulapi.io/mcp"
}
}
} Run these commands. The second one opens the login page:
Windsurf, Cline, Zed and other MCP clients: add this URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser.
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 Fireworks 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.
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro | $9/mo · $90/yr | 10,000 tool calls / month |
| Pro+ | $39/mo · $390/yr | 100,000 tool calls / month |
Each paid plan covers this Fireworks AI server only. Ask your AI to run fireworks_upgrade and choose Pro or Pro+, billed monthly or yearly (it returns a Stripe Checkout link). If you already have Pro, ask to change it to Pro+. The change requires your confirmation, keeps your billing interval and charges the price difference for the rest of the period immediately. Cancel any time with fireworks_cancel_subscription: your paid plan continues to the end of the paid period, with no refund for the current period, and asking to resume the same plan with fireworks_upgrade before then undoes the cancel. Or write to [email protected].
fireworks_get_accountfireworks_list_modelsfireworks_get_modelfireworks_list_deploymentsfireworks_get_deploymentfireworks_list_deployed_modelsfireworks_list_datasetsfireworks_get_datasetfireworks_list_fine_tuning_jobsfireworks_get_fine_tuning_jobfireworks_list_batch_inference_jobsfireworks_list_usersfireworks_create_datasetfireworks_delete_deploymentfireworks_usage_statusfireworks_request_featurefireworks_upgradefireworks_cancel_subscriptionCheck which models and deployments are running. Track your fine-tuning jobs. Review your batch inference jobs. Look up datasets or add a dataset record. Shut down a deployment you no longer need. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by Fireworks AI. The server calls the Fireworks AI API with your own Fireworks AI 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 Fireworks 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 Fireworks 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 Fireworks AI 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 Fireworks AI.
Yes, if you approve it. 2 of the 14 Fireworks AI tools can create or change data. The other 12 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with 10,000 tool calls / month. Pro+ costs $39/mo or $390/yr, with 100,000 tool calls / month. Each subscription covers this Fireworks AI server only. Cancel any time: your paid plan then runs to the end of the paid period. Run fireworks_usage_status to see how many calls you used.
Ask the AI to run fireworks_upgrade and choose Pro or Pro+, billed monthly or yearly: it returns a Stripe Checkout link. If you already have Pro, ask to change it to Pro+. After you confirm, your existing subscription changes in place, keeps its billing interval and charges the price difference for the rest of the period immediately. To cancel, run fireworks_cancel_subscription. Your paid plan continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with fireworks_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.