How to Use the Fireworks AI MCP in CrewAI

Q: Does CrewAI support Fireworks AI model switching?

Absolutely. You can use the listmodels tool to query for new versions and update your agent settings on the fly. It keeps your crew using the latest weights.

Deploy specialized agent crews with CrewAI using Fireworks AI for high-throughput, autonomous task execution.

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 CrewAI

Create your Vinkius account to connect Fireworks AI to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized Agent Roles

Assign `chat` and `completion` tools to specific agents in your crew to handle research or writing. Each agent manages its own context, ensuring the output remains focused on the assigned role. Your crew collaborates by sharing memory, allowing one agent to build on the work of another. The server provides the raw speed needed to keep the crew moving.

Autonomous Transcription Tasks

Equip your research agents with the `transcribe` tool for processing raw meeting audio. The agent takes the file, calls the tool, and summarizes the results for the next agent in the sequence. This reduces manual labor and speeds up your operational pipelines. You define the sequence, and the agents execute the work without human intervention.

Model Discovery for Crews

Use `list_models` to let your agents decide which model is best for a particular step in the process. Your crew can adapt its strategy based on the available capabilities. This makes your crew smarter and more flexible. It allows for dynamic task allocation based on current system conditions.

Setup guide

Set up Fireworks AI MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Fireworks AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Fireworks AI Analyst",
    goal="Access and analyze Fireworks AI data via MCP.",
    backstory="Expert analyst with direct Fireworks AI access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Fireworks AI transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Fireworks AI Analyst",
        goal="Access and analyze Fireworks AI data via MCP.",
        backstory="Expert analyst with direct Fireworks AI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Fireworks AI transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the server URL into your Agent configuration. You can use the tool filter to restrict which agents have access to specific Fireworks AI capabilities.

Yes, the server supports SSE and HTTP transports for stable, long-running agent sessions. It is built to handle the high volume of calls generated by autonomous crews.

Absolutely. You can use the `list_models` tool to query for new versions and update your agent settings on the fly. It keeps your crew using the latest weights.

The server logs every request and response cycle. You can inspect these logs in your terminal to see exactly what the agent sent and what the model returned.

The connection uses ephemeral sandboxing to protect your data. We do not store any task-specific information, and all communications are encrypted from end to end.

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