Can I check the budget and rate limits for a specific proxy key?

Yes. Use the `get_key_info` tool with the specific Key ID. Your agent will retrieve the exact rate limits, budget constraints, and current RPM usage associated with that token.

How do I see the model fallback paths configured in my proxy?

The `get_model_info` tool allows your agent to extract the global model directory. You'll see the exact fallback chains (e.g., if OpenAI fails, use Anthropic) and the physical endpoints assigned to each model name.

Can my agent create a new team to track specific division costs?

Absolutely. Use the `create_team` tool and provide a JSON payload defining the team name and optional budget limits. Your agent will provision the new team identity in LiteLLM, allowing for precise organizational cost tracking.

LiteLLM (LLM Proxy & Spend Tracking) MCP Server for CrewAI 10 tools — connect in under 2 minutes

Name: LiteLLM (LLM Proxy & Spend Tracking)
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 10 Tools Framework

Connect your CrewAI agents to LiteLLM (LLM Proxy & Spend Tracking) through Vinkius, pass the Edge URL in the `mcps` parameter and every LiteLLM (LLM Proxy & Spend Tracking) tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="LiteLLM (LLM Proxy & Spend Tracking) Specialist",
    goal="Help users interact with LiteLLM (LLM Proxy & Spend Tracking) effectively",
    backstory=(
        "You are an expert at leveraging LiteLLM (LLM Proxy & Spend Tracking) tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in LiteLLM (LLM Proxy & Spend Tracking) "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 10 available tools "
        "and what they can do."
    ),
)

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

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About LiteLLM (LLM Proxy & Spend Tracking) MCP Server

Connect your LiteLLM Proxy instance to any AI agent and take full control of your LLM infrastructure, load balancing, and spend management through natural conversation.

When paired with CrewAI, LiteLLM (LLM Proxy & Spend Tracking) becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call LiteLLM (LLM Proxy & Spend Tracking) tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

What you can do

Key Orchestration — Generate and manage proxy API keys to isolate distinct microservices or teams, including precise budget and rate limit constraints directly from your agent
Model Routing Intelligence — Get detailed info on fallback paths (e.g., OpenAI -> Anthropic -> Groq) and verify exact routing endpoints assigned to your models
Real-time Spend Audit — Track total USD consumed by specific end-users or teams and monitor budget ceilings to ensure cost-effective AI deployments
Dynamic Model Control — Inject fresh routing endpoints (e.g., new AWS Bedrock or Azure OpenAI deployments) into your proxy runtime with zero downtime
Team & Organizational Isolation — Create and manage team profiles to track exact cost limits and operational boundaries per organizational division
Infrastructure Security — Instantly vaporize malicious or leaked keys and remove broken LLM deployments to prevent downstream 500 errors dynamically

The LiteLLM (LLM Proxy & Spend Tracking) MCP Server exposes 10 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

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

Follow these steps to integrate the LiteLLM (LLM Proxy & Spend Tracking) MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 10 tools from LiteLLM (LLM Proxy & Spend Tracking)

Why Use CrewAI with the LiteLLM (LLM Proxy & Spend Tracking) MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with LiteLLM (LLM Proxy & Spend Tracking) through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

LiteLLM (LLM Proxy & Spend Tracking) + CrewAI Use Cases

Practical scenarios where CrewAI combined with the LiteLLM (LLM Proxy & Spend Tracking) MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries LiteLLM (LLM Proxy & Spend Tracking) for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries LiteLLM (LLM Proxy & Spend Tracking), analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain LiteLLM (LLM Proxy & Spend Tracking) tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries LiteLLM (LLM Proxy & Spend Tracking) against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

LiteLLM (LLM Proxy & Spend Tracking) MCP Tools for CrewAI (10)

These 10 tools become available when you connect LiteLLM (LLM Proxy & Spend Tracking) to CrewAI via MCP:

create_model

Inject completely fresh routing endpoints (ex: new Bedrock Llama 4 endpoints)

create_team

Generate pristine organizational isolation tracking exact cost limits per division

create_user

Insert specific End-User identities bridging Vinkius with Proxy logs

delete_key

Delete an existing LLM proxy key entirely

delete_model

Delete explicitly routed LLM deployments preventing 500s dynamically

generate_key

Generate a new proxy API key isolating distinct microservices or teams

get_key_info

Get configuration and budget bounds for a specific LiteLLM API Key

get_model_info

Get array endpoints tracing exact Fallback paths like OpenAI -> Anthropic

get_team_info

Get internal logic bounds matching multiple routing users via Team UUID

get_user_info

Return precise End-User abstractions tracking total USD consumed natively

Example Prompts for LiteLLM (LLM Proxy & Spend Tracking) in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with LiteLLM (LLM Proxy & Spend Tracking) immediately.

"List all active model fallback paths in LiteLLM"

"Generate a new API key for the 'Customer-Service' team with a $50 monthly budget"

"How much has user 'alex_dev' spent on LLM tokens today?"

Troubleshooting LiteLLM (LLM Proxy & Spend Tracking) MCP Server with CrewAI

Common issues when connecting LiteLLM (LLM Proxy & Spend Tracking) to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

LiteLLM (LLM Proxy & Spend Tracking) + CrewAI FAQ

Common questions about integrating LiteLLM (LLM Proxy & Spend Tracking) MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.