How to Use the DeepInfra (Serverless LLM Inference) MCP in CrewAI

Q: How do I add DeepInfra (Serverless LLM Inference) tools to a CrewAI agent?

Pass your Vinkius endpoint URL directly into the mcps list when defining your CrewAI Agent. This registers the MCP Server automatically.

Q: Can I restrict which DeepInfra (Serverless LLM Inference) tools a CrewAI agent can use?

Yes, use MCPServerHTTP from crewai.mcp along with a toolfilter to expose only specific tools, like generateimage, to particular agents.

Deploy specialized teams of CrewAI agents that collaborate using DeepInfra serverless LLMs and image generation tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepInfra (Serverless LLM Inference) MCP to CrewAI

Create your Vinkius account to connect DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent tasks using DeepInfra models

CrewAI thrives when agents have specific roles. This MCP integration lets you assign one researcher agent to query `create_chat_completion` while an editor agent uses another LLM to refine the draft. By delegating tasks across a serverless pool, your crew avoids context bottlenecking. Each agent calls the exact model it needs for its specific task.

Generate assets and search vectors across your crew

Give your designer agent the `generate_image` tool via our MCP Server to create marketing assets autonomously. Meanwhile, a database agent can use `create_embedding` to index the research reports. This parallel execution lets your crew handle complex content creation pipelines. The output of one agent's tool call immediately feeds the memory of the next.

Equip CrewAI agents with specialized OCR and speech tools

When your crew needs to parse scanned documents or audio files, deploy `run_native_inference`. This lets specialized agents handle files that standard LLMs fail to process. This MCP Server exposes these tools directly to Python. Your agents can invoke native serverless models without you writing custom wrappers.

Setup guide

Set up DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent DeepInfra (Serverless LLM Inference) 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="DeepInfra (Serverless LLM Inference) Analyst",
        goal="Access and analyze DeepInfra (Serverless LLM Inference) data via MCP.",
        backstory="Expert analyst with direct DeepInfra (Serverless LLM Inference) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent DeepInfra (Serverless LLM Inference) 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 DeepInfra. 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 DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) MCP in CrewAI

Pass your Vinkius endpoint URL directly into the `mcps` list when defining your CrewAI Agent. This registers the MCP Server automatically.

Yes, the serverless endpoint supports concurrent requests. Different agents can call `create_chat_completion` simultaneously without blocking each other.

Yes, use `MCPServerHTTP` from `crewai.mcp` along with a `tool_filter` to expose only specific tools, like `generate_image`, to particular agents.

The integration supports stdio, SSE, and Streamable HTTP transports. You can configure this directly in your Python setup depending on your deployment needs.

All agent-generated prompts, intermediate reasoning steps, and vector inputs are processed in a secure, sandboxed V8 execution environment. No data is stored locally, ensuring your proprietary research remains confidential.

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