Which AI clients can use this Braintrust MCP?

You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

Do I need to write code to run evaluations?

No. Once connected, your agent uses the capabilities to run experiments and query datasets through natural language.

How does this handle prompt versioning?

The MCP allows your agent to pull specific, version-controlled prompts from Braintrust, ensuring you use the exact text templates you need.

Can I add new data to my datasets?

Yes. You can use the insert_dataset_row capability to append new test cases to your existing matrices.

Is my Braintrust data secure?

Yes. Vinkius hosts the MCP and manages your credentials, allowing you to connect your API keys securely to your agent.

Can I insert new test data dynamically tracking specific limits?

Yes. Utilizing the insert_dataset_row method, you can effortlessly inject exact JSON tracking payload mapping strings directly inside the text corpus evaluating the final results.

Does it pull out original Prompt definitions stored securely?

Certainly. The get_prompt command isolates and returns perfectly version-controlled bounding parameters slicing literal templates natively hosted under the Braintrust database.

How deeply can it inspect test regressions or scoring limits?

Using the robust list_experiments call, you can branch full arrays separating LLM version behaviors over massive iterations tracking the performance anomalies accurately.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Braintrust to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run model benchmarks and manage prompts directly from your agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Braintrust.

01
Create project
Use this to set up a new project environment for tracking your datasets and evaluations.
02
Create experiment
This capability establishes a new historical experiment trace to record your LLM pipeline tests.
03
List env vars
This capability probes your Braintrust AI Gateway configurations to check model API key management.
04
List experiments
This capability pulls all your evaluation experiments, including their specific model test scores and metrics.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Braintrust.

05
Get dataset
This capability retrieves a specific dataset and its associated schemas for LLM outputs.
06
Get prompt
Use this to get the exact variable contexts and literal text templates for a specific prompt.
07
Insert dataset row
Use this to add new test cases into a dataset matrix for specific evaluations.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Braintrust.

08
List projects
This capability retrieves a full list of your AI evaluation projects stored in Braintrust.
09
List prompts
This capability fetches your version-controlled system prompts that are isolated in Braintrust.
10
List datasets
This capability lists your Ground Truth text banks used for automated scoring.

Real work

What teams actually run

Prompt Regression Testing

Compare how a new prompt version performs against a baseline using existing experiment traces.

Dataset Expansion

Add new test cases to your evaluation matrices through natural language commands.

Real-time Monitoring

Check project analytics and model scores to see how recent changes affected performance.

Configuration Auditing

Verify Braintrust AI Gateway settings and environment variables through your agent.

Automate a task

Put Braintrust to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Braintrust works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Braintrust to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

850ms average. Fast in production.

Braintrust is checked daily against the live service.

Daily averagePeak 1082ms

Oct 3Today

Fastest day: 672ms
Slowest day: 1082ms
14-day trend: Stable+3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Braintrust, so you can see the experience inside your AI.

It does not authenticate your account with Braintrust. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Braintrust Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_cr8T7CpPGy155EtBgklGtlDgFsTWLRLYfzKoHIOF/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Braintrust capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "braintrust-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_cr8T7CpPGy155EtBgklGtlDgFsTWLRLYfzKoHIOF/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Braintrust in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Braintrust owners hand off.

This MCP is built for technical teams building and monitoring production AI applications.

01
AI Developers
They hand off Ground Truth datasets to the agent to test prompt variations on the fly.
02
Machine Learning Engineers
They use the agent to track variable distributions and remote regressions.
03
Data Scientists
They instruct the agent to build matrices and evaluate test runs without writing manual scripts.

FAQ

Questions Braintrust owners ask.

01
Which AI clients can use this Braintrust MCP?
You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.
02
Do I need to write code to run evaluations?
No. Once connected, your agent uses the capabilities to run experiments and query datasets through natural language.
03
How does this handle prompt versioning?
The MCP allows your agent to pull specific, version-controlled prompts from Braintrust, ensuring you use the exact text templates you need.
04
Can I add new data to my datasets?
Yes. You can use the insert_dataset_row capability to append new test cases to your existing matrices.
05
Is my Braintrust data secure?
Yes. Vinkius hosts the MCP and manages your credentials, allowing you to connect your API keys securely to your agent.
06
Can I insert new test data dynamically tracking specific limits?
Yes. Utilizing the insert_dataset_row method, you can effortlessly inject exact JSON tracking payload mapping strings directly inside the text corpus evaluating the final results.
07
Does it pull out original Prompt definitions stored securely?
Certainly. The get_prompt command isolates and returns perfectly version-controlled bounding parameters slicing literal templates natively hosted under the Braintrust database.
08
How deeply can it inspect test regressions or scoring limits?
Using the robust list_experiments call, you can branch full arrays separating LLM version behaviors over massive iterations tracking the performance anomalies accurately.

Explore

More in Brain Trust

Connect Braintrust to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Create project

Create experiment

List env vars

List experiments

05-07

Get dataset

Get prompt

Insert dataset row

08-10

List projects

List prompts

List datasets

What teams actually run

Prompt Regression Testing

Dataset Expansion

Real-time Monitoring

Configuration Auditing

Building your own app? The connector is yours to use.

Braintrust Connector

Claude Desktop

AI Developers

Machine Learning Engineers

Data Scientists

Which AI clients can use this Braintrust MCP?

Do I need to write code to run evaluations?

How does this handle prompt versioning?

Can I add new data to my datasets?

Is my Braintrust data secure?

Can I insert new test data dynamically tracking specific limits?

Does it pull out original Prompt definitions stored securely?

How deeply can it inspect test regressions or scoring limits?

Datadog AI (LLM Observability) AI Connector

LangSmith (LLM Observability & Hub) AI Connector

Katalon TestOps (AI Test Management) AI Connector

Langfuse (LLM Tracing & Evals) AI Connector

Suggestions

Data Pipeline Prover AI Connector

Chi-Square Test Engine AI Connector

Humanloop (LLM Prompt Management API) AI Connector

Hevo Data (ETL & Data Pipeline) AI Connector