How to Use the LiteLLM (LLM Proxy & Spend Tracking) MCP in CrewAI

Q: How do I monitor LLM usage in CrewAI with LiteLLM (LLM Proxy & Spend Tracking)?

You give your agents access to getuserinfo. The crew can then check their own total USD consumption and adjust their activity level to stay within your constraints.

Q: Can LiteLLM (LLM Proxy & Spend Tracking) help my CrewAI agents avoid 500 errors?

Yes. By using getmodelinfo and createmodel, your agents can detect provider issues and reroute requests. This keeps your CrewAI workflows stable even during outages.

Q: Is it easy to provision keys for CrewAI using LiteLLM (LLM Proxy & Spend Tracking)?

It is simple. You use generatekey to create credentials for your agents and deletekey to revoke them. This allows your CrewAI setup to manage its own security posture.

Q: How do I isolate costs between different agent crews?

Use createteam to define separate groups for your crews. Each team tracks costs independently, making it easy to report on spend for different projects or departments.

Deploy autonomous agent crews that monitor their own LLM spending and model performance with this MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiteLLM (LLM Proxy & Spend Tracking) MCP to CrewAI

Create your Vinkius account to connect LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous spend monitoring for CrewAI

Assign a monitor agent in your crew to periodically call `get_user_info`. If spend crosses a threshold, the agent acts to notify the team or pause production tasks. It gives your agents the visibility they need to be responsible. You no longer have to watch the dashboard yourself because the crew keeps an eye on the budget.

Dynamic model failover for agents

Use `get_model_info` to allow your agents to check if a specific model path is active before attempting a task. If a provider is down, the agent can use `create_model` to point to a working alternative. This self-healing capability keeps your CrewAI operations running without human intervention. Your agents handle the infrastructure maintenance as part of their routine.

Granular key management for roles

Create specialized API keys for different agents using `generate_key`. A research agent gets a key with different budget bounds than an analysis agent, keeping your costs strictly controlled. Audit these roles with `get_key_info` at any time. You maintain total control over what each member of your crew can do and how much they can spend.

Setup guide

Set up LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent LiteLLM (LLM Proxy & Spend Tracking) 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="LiteLLM (LLM Proxy & Spend Tracking) Analyst",
        goal="Access and analyze LiteLLM (LLM Proxy & Spend Tracking) data via MCP.",
        backstory="Expert analyst with direct LiteLLM (LLM Proxy & Spend Tracking) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM. 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 LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) MCP in CrewAI

You give your agents access to `get_user_info`. The crew can then check their own total USD consumption and adjust their activity level to stay within your constraints.

Yes. By using `get_model_info` and `create_model`, your agents can detect provider issues and reroute requests. This keeps your CrewAI workflows stable even during outages.

It is simple. You use `generate_key` to create credentials for your agents and `delete_key` to revoke them. This allows your CrewAI setup to manage its own security posture.

Use `create_team` to define separate groups for your crews. Each team tracks costs independently, making it easy to report on spend for different projects or departments.

Your keys are stored within the gateway and managed via secure MCP tools. Access is restricted to authorized agents, and we never expose your full credentials through the logs.

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