# Fireworks AI MCP by usefulapi

> Fireworks AI MCP by usefulapi is a freemium MCP server for ai models and llm tooling. Hosted MCP server to inspect Fireworks AI models, deployments and fine-tuning jobs from AI. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $9 a month
- **Platforms:** API, Web, vscode, CLI
- **Website:** https://usefulapi.io/fireworks/
- **Repository:** https://github.com/m190/usefulapi-mcp/tree/HEAD/servers/fireworks
- **MCP Registry name:** io.usefulapi/fireworks
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-18

## About

The server gives Claude, ChatGPT, Cursor and other MCP clients read access to the models, deployments, datasets, fine-tuning jobs and batch inference jobs in a Fireworks AI account. You ask in plain language and the assistant picks the matching tool, so you can see what is currently serving without opening the Fireworks dashboard.

It runs remotely over Streamable HTTP and signs you in with OAuth, where the login page asks for your Fireworks API key. Nothing is installed locally. The README and site say the server calls the Fireworks API with your own access and only sees what your account can see.

Two of the 18 tools can change data: creating a dataset metadata record and deleting a deployment, which stops serving and billing for that model. The rest are read-only, and the site notes that most MCP clients ask for approval before a tool call runs. The service is an independent usefulapi product, not affiliated with Fireworks AI.

## Features

- **Model and deployment overview:** Lists base and fine-tuned models, serving deployments and the model-to-deployment bindings in the account.
- **Fine-tuning job tracking:** Lists supervised fine-tuning jobs and reads individual jobs by id to check their status.
- **Batch inference review:** Lists batch inference jobs submitted to the account.
- **Dataset lookup:** Lists datasets and reads one by id, including when it was created.
- **Deployment shutdown:** Deletes a deployment you no longer need, which also stops its billing.
- **Usage metering:** Reports calls used against the monthly plan limit of the free or paid tier.

## Good for

- Check which fine-tuned models are currently serving in a Fireworks account
- Monitor the status of supervised fine-tuning jobs from a chat assistant
- Review batch inference jobs submitted to the team account
- Find and shut down an idle deployment to stop its billing
- List team members on a Fireworks account

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http fireworks https://fireworks.usefulapi.io/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://fireworks.usefulapi.io/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "fireworks": {
      "url": "https://fireworks.usefulapi.io/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "fireworks": {
      "type": "http",
      "url": "https://fireworks.usefulapi.io/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "fireworks": {
      "serverUrl": "https://fireworks.usefulapi.io/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "fireworks": {
      "type": "http",
      "url": "https://fireworks.usefulapi.io/mcp"
    }
  }
}
```

## Tools

- `fireworks_get_account`: Get the Fireworks account record (display name, state, etc.).
- `fireworks_list_models`: List models in the account (base + fine-tuned).
- `fireworks_get_model`: Get a single model by id.
- `fireworks_list_deployments`: List deployments (serving instances) in the account.
- `fireworks_get_deployment`: Get a single deployment by id.
- `fireworks_list_deployed_models`: List deployed models (model-deployment bindings).
- `fireworks_list_datasets`: List datasets in the account.
- `fireworks_get_dataset`: Get a single dataset by id.
- `fireworks_list_fine_tuning_jobs`: List supervised fine-tuning jobs in the account.
- `fireworks_get_fine_tuning_job`: Get a single supervised fine-tuning job by id.
- `fireworks_list_batch_inference_jobs`: List batch inference jobs in the account.
- `fireworks_list_users`: List account members (users).
- `fireworks_create_dataset`: Creates a dataset metadata record in Fireworks.
- `fireworks_delete_deployment`: Deletes (shuts down) a Fireworks deployment.
- `fireworks_usage_status`: Report the caller's current usage and plan limit.
- `fireworks_request_feature`: Send a request for a missing feature to usefulapi.
- `fireworks_upgrade`: Get a paid plan for Fireworks AI.
- `fireworks_cancel_subscription`: Cancel the Pro subscription at the end of the paid period.

## FAQ

### Is this an official Fireworks AI product?

No. usefulapi is an independent service and is not affiliated with or endorsed by Fireworks AI.

### Do I need to install anything?

No. The server is hosted. You add its URL to your MCP client and log in with your Fireworks API key.

### Can the AI change my Fireworks AI data?

Yes, if you approve it. Two of the 18 tools can create or change data, and the other tools are read-only.

### What does it cost?

The Free plan includes 50 tool calls per month. Pro is $9/mo or $90/yr for 10,000 calls, and Pro+ is $39/mo or $390/yr for 100,000 calls.

### Is Fireworks AI MCP by usefulapi free?

Fireworks AI MCP by usefulapi has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.

### How do I add Fireworks AI MCP by usefulapi to Claude Code?

Run this command in your terminal: claude mcp add --transport http fireworks https://fireworks.usefulapi.io/mcp

### What are the best alternatives to Fireworks AI MCP by usefulapi?

The closest alternatives to Fireworks AI MCP by usefulapi are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

## Where this comes from

- Description: written from the project's README, the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [signafAIde](https://ai-powered.com/mcp/signafaide): signafAIde is a freemium MCP server for security.
- [Toolkien](https://ai-powered.com/mcp/toolkien): Toolkien is an open-source MCP server for ai models and llm tooling.
- [Lugh](https://ai-powered.com/mcp/lugh): Lugh is an open-source MCP server for ai models and llm tooling.
- [HypePaper](https://ai-powered.com/mcp/hypepaper): HypePaper is a freemium MCP server for ai models and llm tooling.
- [Agent Data Tools: Compact (find, describe, run)](https://ai-powered.com/mcp/agent-data-tools-compact-find-describe-run): Agent Data Tools: Compact (find, describe, run) is a freemium MCP server for developer tools.
- [Angel Agent Guard: pre-purchase check + prompt-injection scan](https://ai-powered.com/mcp/angel-agent-guard-pre-purchase-check-prompt-injection-scan): Angel Agent Guard: pre-purchase check + prompt-injection scan is a freemium MCP server for ai models and llm tooling.
- [Mizan Calibration](https://ai-powered.com/mcp/mizan-calibration): Mizan Calibration is a free MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/fireworks-ai-mcp-by-usefulapi
