# Braintrust

```json
{
  "name": "Braintrust",
  "slug": "braintrust",
  "url": "https://composio.dev/toolkits/braintrust",
  "markdown_url": "https://composio.dev/toolkits/braintrust.md",
  "logo_url": "https://logos.composio.dev/api/braintrust",
  "categories": [
    "ai & machine learning"
  ],
  "is_composio_managed": false,
  "updated_at": "2026-10-04T14:44:11.495Z"
}
```

![Braintrust logo](https://logos.composio.dev/api/braintrust)

## Description

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Braintrust MCP or direct API to manage prompts, inspect experiments, query evaluations, and review production traces through natural language.

## Summary

Braintrust is an AI engineering platform for prompts, datasets, experiments, evaluations, observability, and production AI apps.
Use it to ship better AI systems with faster debugging, clearer evals, and tighter feedback loops.

## Categories

- ai & machine learning

## Toolkit Details

- Tools: 17

## Images

- Logo: https://logos.composio.dev/api/braintrust

## Authentication

- **Api Key**
  - Type: `api_key`
  - Description: Api Key authentication for Braintrust.
  - Setup:
    - Configure Api Key credentials for Braintrust.
    - Use the credentials when creating an auth config in Composio.

## Suggested Prompts

- Compare failed evaluations across recent experiments
- Create dataset from production failure logs
- Summarize latency spikes in Braintrust traces

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `BRAINTRUST_CREATE_DATASET` | Create Dataset | Create a named dataset under a Braintrust project, or return the existing dataset unchanged when its name already exists in that project. |
| `BRAINTRUST_CREATE_EXPERIMENT` | Create Experiment | Create an experiment under a Braintrust project. When its name already exists, Braintrust returns the existing experiment unchanged unless ensure_new is true, which creates an experiment with a unique name. |
| `BRAINTRUST_CREATE_PROJECT` | Create Project | Create a Braintrust project, or return the existing project unchanged when its name already exists. |
| `BRAINTRUST_CREATE_PROMPT` | Create Prompt | Upsert a versioned prompt configuration under a Braintrust project without invoking it. The same project and slug reuse the prompt ID but create a new version that replaces the stored prompt configuration with the submitted configuration. MCP attachments and tool-function bindings are unsupported. |
| `BRAINTRUST_DELETE_PROJECT` | Delete Project | Soft-delete a Braintrust project and return its deletion state. |
| `BRAINTRUST_DELETE_RESOURCE` | Delete Experiment, Dataset, or Prompt | Delete one Braintrust experiment, dataset, or prompt by UUID for explicit lifecycle cleanup. |
| `BRAINTRUST_FETCH_EVENTS` | Fetch Events | Fetch one newest-to-oldest page of project log, experiment, or dataset events. |
| `BRAINTRUST_GET_RESOURCE` | Get Braintrust Resource | Get one project, experiment, dataset, prompt, or function by UUID. |
| `BRAINTRUST_INSERT_DATASET_EVENTS` | Insert Dataset Events | Upsert a batch of examples into an existing Braintrust dataset. New or omitted IDs insert events; an existing supplied ID replaces that event's current values. |
| `BRAINTRUST_INSERT_EXPERIMENT_EVENTS` | Insert Experiment Events | Upsert a batch of result events into an existing Braintrust experiment. New or omitted IDs insert events; an existing supplied ID replaces that event's current values. |
| `BRAINTRUST_LIST_RESOURCES` | List Braintrust Resources | List and filter one page of projects, experiments, datasets, prompts, or functions visible to the connected Braintrust API key. |
| `BRAINTRUST_QUERY_DATA` | Query Braintrust Data | Run one bounded synchronous read-only BTQL query over Braintrust project logs, an experiment, or a dataset. The first-page query must end with a positive LIMIT; continue later pages by passing the returned next_cursor unchanged. |
| `BRAINTRUST_SUMMARIZE_RESOURCE` | Summarize Experiment or Dataset | Return metadata and optional aggregate summaries for one Braintrust experiment or dataset. |
| `BRAINTRUST_UPDATE_DATASET` | Update Dataset | Update the name, description, tags, or metadata of a Braintrust dataset. At least one non-null mutable field is required. |
| `BRAINTRUST_UPDATE_EXPERIMENT` | Update Experiment | Update selected metadata and linkage fields on a Braintrust experiment. At least one non-null mutable field is required. |
| `BRAINTRUST_UPDATE_PROJECT` | Update Project | Update selected fields of a Braintrust project. At least one non-null mutable field is required: name, description, or settings. |
| `BRAINTRUST_UPDATE_PROMPT` | Update Prompt | Update a Braintrust prompt's metadata or configuration without invoking it. At least one non-null mutable field is required. |

## Supported Triggers

None listed.

## Installation and MCP Setup

### Path 1: SDK Installation

#### Path 1, Step 1: Install Composio

Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
```python
pip install composio composio_openai openai
```

```typescript
npm install @composio/core @composio/openai openai
```

#### Path 1, Step 2: Create a Composio session

Initialize Composio with the OpenAI Responses provider and create a session scoped to Braintrust
```python
import json
from openai import OpenAI
from composio import Composio
from composio_openai import OpenAIResponsesProvider

composio = Composio(provider=OpenAIResponsesProvider())
client = OpenAI()

session = composio.create(user_id="your-user-id", toolkits=["braintrust"])
tools = session.tools()
```

```typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["braintrust"] });
const tools = await session.tools();
```

#### Path 1, Step 3: Run Braintrust tools with your agent

Send a request, execute the Braintrust tool calls through the session, and print the final answer
```python
response = client.responses.create(
    model="gpt-5.6-sol",
    tools=tools,
    input=[{"role": "user", "content": "List recent Braintrust experiments and summarize failed evaluations"}],
)

while True:
    tool_calls = [o for o in response.output if o.type == "function_call"]
    if not tool_calls:
        break
    results = composio.provider.handle_tool_calls(response=response, session=session)
    response = client.responses.create(
        model="gpt-5.6-sol",
        tools=tools,
        previous_response_id=response.id,
        input=[
            {"type": "function_call_output", "call_id": call.call_id, "output": json.dumps(results[i])}
            for i, call in enumerate(tool_calls)
        ],
    )

print(response.output_text)
```

```typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "List recent Braintrust experiments and summarize failed evaluations" }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
```

### Path 2: MCP Server Setup

#### Path 2, Step 1: Install Composio

Install the Composio SDK and your agent framework
```python
pip install composio claude-agent-sdk
```

```typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
```

#### Path 2, Step 2: Create a session with MCP enabled

Create a session scoped to Braintrust and read its MCP URL and headers
```python
from composio import Composio

composio = Composio()
session = composio.create(user_id="your-user-id", toolkits=["braintrust"], mcp=True)
```

```typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["braintrust"],
  mcp: true,
});
```

#### Path 2, Step 3: Connect your agent to the MCP server

Pass the session's MCP URL and headers to your agent and run a Braintrust request
```python
import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions, AssistantMessage, TextBlock

options = ClaudeAgentOptions(
    mcp_servers={
        "composio": {
            "type": "http",
            "url": session.mcp.url,
            "headers": session.mcp.headers,
        }
    },
    system_prompt="You are a helpful assistant with access to Braintrust tools.",
    tools=[],
    allowed_tools=["mcp__composio__*"],
)

async def main():
    async with ClaudeSDKClient(options=options) as client:
        await client.query("List recent Braintrust experiments and summarize failed evaluations")
        async for message in client.receive_response():
            if isinstance(message, AssistantMessage):
                for block in message.content:
                    if isinstance(block, TextBlock):
                        print(block.text)

asyncio.run(main())
```

```typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "List recent Braintrust experiments and summarize failed evaluations",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
```

## Why Use Composio?

### 1. AI Native Braintrust Integration

- Supports both Braintrust MCP and direct API based integrations
- Structured, LLM-friendly schemas for reliable prompt, dataset, and experiment workflows
- Rich coverage for reading, writing, and querying your Braintrust AI engineering data

### 2. Managed Auth

- Secure API key handling without hard-coding Braintrust credentials in your agent code
- Central place to manage, scope, and revoke Braintrust access
- Per user and per environment credentials, so staging and production stay cleanly separated

### 3. Agent Optimized Design

- Tools are tuned for language models, so agents can inspect experiments and evaluations with fewer broken calls
- Clear tool schemas help agents understand Braintrust resources like prompts, datasets, logs, and traces
- Comprehensive execution logs so you always know what ran, when, and on whose behalf

### 4. Enterprise Grade Security

- Fine-grained RBAC so you control which agents and users can access Braintrust
- Scoped, least privilege access to Braintrust projects, experiments, and observability data
- Full audit trail of agent actions to support review, debugging, and compliance

## Use Braintrust with any AI Agent Framework

Choose a framework you want to connect Braintrust with:

- [ChatGPT](https://composio.dev/toolkits/braintrust/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/braintrust/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/braintrust/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/braintrust/framework/atomic-agent)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [AltTextLab](https://composio.dev/toolkits/alt_text_lab) - AltTextLab is an AI service that generates accessible, SEO-aware alt text for images. It helps teams make image content easier to understand, index, and publish.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apiframe](https://composio.dev/toolkits/apiframe) - Apiframe is an API platform for generating and managing AI images, videos, music, uploads, assets, jobs, and custom LoRAs. It gives developers one clean API for creative AI workflows without juggling multiple model providers.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Arize AX](https://composio.dev/toolkits/arize_ax) - Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality.
- [Artificial Analysis](https://composio.dev/toolkits/artificial_analysis) - Artificial Analysis is an independent benchmarking platform for AI models and API providers. Use it to compare model intelligence, coding, math, pricing, latency, throughput, and arena rankings.
- [AssemblyAI](https://composio.dev/toolkits/assemblyai) - AssemblyAI is a speech-to-text and audio intelligence API for uploaded or hosted media. Use it to turn audio and video into accurate transcripts, summaries, and insights.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Avoma](https://composio.dev/toolkits/avoma) - Avoma is an AI meeting assistant for recording, transcribing, analyzing, and managing meetings, calls, notes, scorecards, and conversation intelligence. It helps teams turn conversations into searchable notes, follow-ups, coaching insights, and revenue intelligence.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Black Forest Labs](https://composio.dev/toolkits/bfl) - Black Forest Labs provides hosted FLUX models for generating and editing images and videos. It offers fast, flexible media creation with asynchronous processing and fine-tuning support.
- [Bland AI](https://composio.dev/toolkits/bland_ai) - Bland AI is a conversational AI platform for building voice agents, phone calls, messaging, and communication workflows. Use it to automate calling, evaluate conversations, and run voice operations at scale.

## Frequently Asked Questions

### Do I need my own developer credentials to use Braintrust with Composio?

Yes, Braintrust requires you to configure your own API key. Once set up, Composio handles secure credential storage and API request handling for you.

### Can I use multiple toolkits together?

Yes! Composio's Tool Router enables agents to use multiple toolkits. [Learn more](https://docs.composio.dev/tool-router/overview).

### Is Composio secure?

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. [Learn more](https://trust.composio.dev).

### What if the API changes?

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)