Can the AI agent run a prediction directly against my hosted model?

Yes. By pushing a correctly formatted JSON payload to the 'predict' tool, the agent securely triggers inference on the GPU instances, returning the exact calculated response data transparently to your editor context.

Is my workspace and environmental secret data kept safe?

Baseten secret fetching natively obscures variable values. When you use 'list_secrets', the agent simply evaluates the key names and identifiers existing across your environment to verify configurations without exposing plaintext passwords.

How do I check auto-scaling configurations for an explicitly deployed model?

You can examine exactly how instances are managed by using 'get_deployment'. Tell the agent to target an active deployment ID and it maps the scaling limits, replica status, and container bounds out-of-the-box.

Baseten MCP Server for CrewAI 6 tools — connect in under 2 minutes

Name: Baseten
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 6 Tools Framework

Connect your CrewAI agents to Baseten through Vinkius, pass the Edge URL in the `mcps` parameter and every Baseten 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="Baseten Specialist",
    goal="Help users interact with Baseten effectively",
    backstory=(
        "You are an expert at leveraging Baseten 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 Baseten "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 6 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 Baseten MCP Server

Connect your Baseten account to any AI agent and track, deploy, and execute your machine learning models through natural conversation.

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

O que você pode fazer

Model Management — List managed models, fetch configurations, and understand active routing boundaries
Serverless Deployments — Inspect exact replica states, autoscaling configurations, and deployment versions
Inference Execution — Run direct predictions (predict) pushing tensor payloads or JSON directly to GPU weights
Workspace Secrets — Enumerate active environment secrets securely mapped inside the isolated orchestration ecosystem

Como funciona

1. Subscribe to this server
2. Enter your Baseten API Key
3. Gain complete ML-Ops control over your active inference nodes using Claude, Cursor, or your preferred agent

Scale unified AI infrastructure without bouncing between terminal windows. Your agent becomes a capable Machine Learning Operator tracking your GPU lifecycle.

Para quem é?

ML Engineers — execute test payloads to deployments instantaneously without spinning up local Python notebooks
DevOps/SREs — audit running deployment resources and verify replica states reliably from your core IDE
AI Researchers — inspect version schemas and manage inference pipeline architectures quickly

The Baseten MCP Server exposes 6 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 Baseten to CrewAI via MCP

Follow these steps to integrate the Baseten 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 6 tools from Baseten

Why Use CrewAI with the Baseten MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Baseten 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

Baseten + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Baseten MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Baseten 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 Baseten, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Baseten 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 Baseten against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Baseten MCP Tools for CrewAI (6)

These 6 tools become available when you connect Baseten to CrewAI via MCP:

get_deployment

Get explicit details of a running deployment

get_model

Get a specific Baseten model

list_deployments

List active inferences bounds matching a specific model

list_models

List Baseten managed models

list_secrets

List securely managed workspace secrets without showing values

predict

Formulate the explicit tensor shapes or dictionaries strictly matching the deployed instance. Invoke a serverless model inference prediction

Example Prompts for Baseten in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Baseten immediately.

"List standard machine learning models we currently host on Baseten."

"Run a prediction against the Sentiment model ID 12345 using this text input: 'The new feature completely broke my workflow.'"

"Check if our Baseten project has a secret scoped as 'OPENAI_API_KEY_FALLBACK'."

Troubleshooting Baseten MCP Server with CrewAI

Common issues when connecting Baseten 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.

Baseten + CrewAI FAQ

Common questions about integrating Baseten 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.