How to Use the Baseten MCP in LlamaIndex

Q: How do I configure LlamaIndex to use the Baseten MCP tools?

Pip install llama-index-tools-mcp and set up a BasicMCPClient. Wrap it with McpToolSpec and call totoollistasync() before passing it to your FunctionAgent.

Q: Does the LlamaIndex Baseten MCP integration support data filtering?

It supports the allowedtools filter. You restrict the agent to read-only tools if you want to prevent accidental inference runs during a query.

Index your Baseten model configurations and active deployments into searchable LlamaIndex knowledge bases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to LlamaIndex

Create your Vinkius account to connect Baseten to LlamaIndex 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 Baseten with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Baseten MCP Server Environments

Calling `list_models` via this MCP Server lets LlamaIndex build a semantic map of your infrastructure. Instead of just firing off actions, the framework ingests these active inference bounds right into a vector store. Your RAG application now answers questions based on live API data. When a developer asks which text model has the lowest latency, the agent queries the index and returns factual, grounded answers instead of hallucinating.

Grounded Inference Execution

The `predict` MCP tool executes serverless model inferences directly from your LlamaIndex agent. It formulates the explicit tensor shapes required by the deployed instance by looking up the requirements in its vector store. This creates a closed loop where the system knows exactly how to format the payload. You avoid broken requests because the agent cross-references the required dictionary structure before sending the prediction.

Secure Workspace Audits

You run `list_secrets` and `get_deployment` to document your current workspace setup. The agent pulls the explicit details of running deployments and indexes the metadata. Engineers query this knowledge base to audit configurations across the team. Because the secret values stay hidden, you safely share the resulting index with junior developers who need to understand the architecture.

Setup guide

Set up Baseten MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Baseten MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Baseten tools.",
)
response = await agent.run("List recent Baseten data")

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 Baseten. 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 Baseten 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 Baseten MCP in LlamaIndex

Pip install `llama-index-tools-mcp` and set up a `BasicMCPClient`. Wrap it with `McpToolSpec` and call `to_tool_list_async()` before passing it to your FunctionAgent.

Yes. The framework indexes the output from the deployment tools into your vector store. You query this data using natural language just like any other document.

It supports the `allowed_tools` filter. You restrict the agent to read-only tools if you want to prevent accidental inference runs during a query.

The agent calls the prediction tool when it determines a live model run is necessary to answer a prompt. Ensure `include_resources=True` is set so it reads the required input shapes.

Vinkius relies on a zero-trust architecture. The server manages your workspace tokens securely and only exposes secret names, never the actual keys. The ephemeral sandbox guarantees no data leaks after the session ends.

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