# Fireworks AI — MCP server on mcp.ai
> Connect your Fireworks AI account and use 9 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Fireworks AI provides APIs for serverless model inference, fine-tuning, deployments, datasets, evaluations, and account management.

By: mcp.ai · official
Page: https://mcp.ai/fireworks_ai

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_fireworks_ai?ms=1787293560000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/fireworks_ai/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/fireworks_ai/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/fireworks_ai/skill.md
Postman collection (v2.1): https://mcp.ai/fireworks_ai/postman.json

## Tools
- fireworks_ai_create_chat_completion(seed?: integer, stop?: string|string[], model: string, tools?: object[], top_p?: number, messages: object[], max_tokens?: integer, temperature?: number, tool_choice?: string|object, response_format?: object) — Generate one non-streaming OpenAI-compatible chat completion from role-based messages using a caller-supplied Fireworks model or deployment ID.
- fireworks_ai_create_embeddings(input: string|string[]|object|object[], model: string, normalize?: boolean, dimensions?: integer, prompt_template?: string) — Create embedding vectors for one or more caller-provided inputs using a caller-supplied Fireworks embedding model.
- fireworks_ai_generate_model_response(input: string|object[], model: string, store?: boolean, tools?: object[], top_p?: number, truncation?: string, temperature?: number, tool_choice?: string|object, instructions?: string, max_tool_calls?: integer, max_output_tokens?: integer, previous_response_id?: string) — Generate one non-streaming Responses API result, optionally continuing a stored response or using function, MCP, or SSE tools; storage is off by default.
- fireworks_ai_get_deployment(read_mask?: string, account_id: string, deployment_id: string) — Return configuration and serving status for one Fireworks deployment without scaling or modifying it.
- fireworks_ai_get_model(model_id: string, read_mask?: string, account_id: string) — Return metadata and status for one model resource in a Fireworks account; this does not test whether the model can serve inference.
- fireworks_ai_list_accounts(filter?: string, page_size?: integer, read_mask?: string, next_cursor?: string) — Return one page of Fireworks accounts accessible to the API key so an agent can obtain account IDs for model and deployment discovery.
- fireworks_ai_list_deployments(filter?: string, order_by?: string, page_size?: integer, read_mask?: string, account_id: string, next_cursor?: string, show_deleted?: boolean) — Return one page of deployment resources in a Fireworks account for deployment ID discovery and serving-capacity and status inspection.
- fireworks_ai_list_models(filter?: string, order_by?: string, page_size?: integer, read_mask?: string, account_id: string, next_cursor?: string) — Return one page of model resources in a Fireworks account for model-ID discovery and status inspection; availability for inference is not guaranteed.
- fireworks_ai_rerank_documents(task?: string, model?: string, query: string, top_n?: integer, documents: string[], return_documents?: boolean) — Rank a provided document list by relevance to a query using an optional caller-supplied Fireworks reranker model.

## Example prompts
- "What can I do in Fireworks AI?"
- "Show me a summary of my Fireworks AI account"

## Links
Docs: https://mcp.ai/docs/mcps/fireworks_ai
Website: https://mcp.ai/mcps/fireworks_ai