How to Use the Braintrust MCP in LlamaIndex

Index your entire evaluation history into LlamaIndex for RAG-powered insights on model performance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Braintrust MCP to LlamaIndex

Create your Vinkius account to connect Braintrust 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 Braintrust with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Braintrust datasets with LlamaIndex

Use `list_datasets` to find your ground truth text banks and load them into your local vector store. This turns your static evaluation data into a searchable knowledge base for your RAG pipeline. You can then ask your agent questions about past model failures. It finds the specific test case that caused the issue, providing context that simple logs miss.

Ground LlamaIndex answers in Braintrust experiments

Call `list_experiments` to pull historical test scores into your index. Your agent uses this data to compare current model performance against previous benchmarks. It stops the model from hallucinating about its own accuracy. The agent sees the hard numbers from your last run and builds its next decision on that foundation.

Automate Braintrust project tracking with LlamaIndex

Run `list_projects` to catalog your active evaluation environments. You can map these project names to specific documentation sets in your index. This creates a unified view of your AI development. When a developer asks about the status of a specific model test, your agent already has the answer indexed.

Setup guide

Set up Braintrust 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 Braintrust 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 Braintrust tools.",
)
response = await agent.run("List recent Braintrust 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 Braintrust. 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 Braintrust 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 Braintrust MCP in LlamaIndex

It lets you index your evaluation results so your agent can reason over past performance. You stop guessing why a model failed and start querying your own history.

The server tools output raw JSON data from your datasets which your agent then ingests into the vector store. This keeps your knowledge base fresh with every run.

Yes, you use the retrieval tools to pull the datasets into your application. From there, you process the rows into searchable nodes for your index.

Your experiment results and prompt history are encrypted in transit. Only your authenticated client can reach into the server to pull data for your index.

It touches your historical evaluation logs, prompt templates, and dataset rows. We isolate these records so they only exist in your authorized application memory.

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