How to Use the Fireworks AI MCP in LlamaIndex

Q: How do I convert Fireworks AI tool outputs into LlamaIndex Document nodes?

You wrap the server's tools with McpToolSpec and call them within your ingestion pipeline. The text returned from chat or transcribe is automatically formatted as a Document node, ready for chunking.

Q: Can I use Fireworks AI embeddings for custom index retrieval in LlamaIndex?

Yes, you can route your queries through the embed tool to generate query vectors. LlamaIndex then uses these vectors to perform similarity searches against your local or cloud vector stores.

Q: Can I filter which tools are exposed to my query engine?

Yes, you can use the allowedtools filter in your client setup to control what the MCP Server exposes. This lets you restrict your query agent to only use chat and embed while hiding image generation tools.

Index live Fireworks AI outputs and audio transcriptions directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fireworks AI MCP to LlamaIndex

Create your Vinkius account to connect Fireworks AI to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Fireworks AI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live API data directly into LlamaIndex RAG

LlamaIndex thrives on fresh, structured data, but static documents only get you so far. Connecting this MCP Server allows your indexers to pull live text generations using `chat` and `completion` directly into your query engines. This setup lets you ground your index in real-time outputs instead of relying on stale files. Your query pipeline calls the server, retrieves the generated text, and immediately indexes it for subsequent semantic searches.

Index audio and visual assets semantically

Unstructured media usually requires manual pre-processing before it can enter a vector database. The `transcribe` and `image` tools let your LlamaIndex ingestion pipeline convert audio files to searchable text and generate visual assets on demand. By transforming raw audio into structured text nodes, your indexers can run semantic searches over spoken content. This turns voice recordings into fully queryable knowledge bases without leaving your index pipeline.

Generate embeddings for instant document chunking

High-performance retrieval requires fast chunk vectorization. The `embed` tool provides low-latency vector generation, letting your LlamaIndex pipeline process large document sets without hitting rate limits or slowing down ingestion. You can also call `list_models` to check which embedding or generation models are currently active. This ensures your indexer always matches its vector dimensions with the correct model configuration.

Setup guide

Set up Fireworks AI MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Fireworks AI MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Fireworks AI tools.",
)
response = await agent.run("List recent Fireworks AI data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Fireworks AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Fireworks AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Fireworks AI MCP in LlamaIndex

You wrap the server's tools with `McpToolSpec` and call them within your ingestion pipeline. The text returned from `chat` or `transcribe` is automatically formatted as a Document node, ready for chunking.

Yes, you can route your queries through the `embed` tool to generate query vectors. LlamaIndex then uses these vectors to perform similarity searches against your local or cloud vector stores.

The managed MCP Server handles connection pooling and request throttling under the hood. LlamaIndex can dispatch parallel embedding requests to the `embed` tool without dropping connections or failing tasks.

Yes, you can use the `allowed_tools` filter in your client setup to control what the MCP Server exposes. This lets you restrict your query agent to only use `chat` and `embed` while hiding image generation tools.

Your prompt strings and embedding vectors pass through isolated, ephemeral memory space that is destroyed immediately after execution. V8 isolation secures your connection with a single token, keeping your raw API credentials completely isolated from the indexing environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript