Humanloop MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Humanloop MCP or direct API to collect real user feedback, annotate model outputs, launch training jobs, and analyze AI performance—all through natural language.

Humanloop logoHumanloop
Api Key

Humanloop is a platform for building and refining AI applications through user feedback and data annotation. It helps teams iterate on language model performance for more accurate and effective AI solutions.

4 Tools

Try Humanloop now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Humanloop
Try asking
TOOLS

Supported Tools

Every Humanloop action and event your agent gets out of the box.

Create Project

Creates a new Humanloop project using a required name and optional description and directory ID.

Delete Project

This tool allows you to delete a specific project from your Humanloop organization.

List Experiments

Retrieves an array of experiments associated with a Humanloop project identified by a project ID starting with 'pr_'.

List Sessions

This tool retrieves a paginated list of sessions for a specific project in Humanloop.

SETUP GUIDE

Connect Humanloop MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

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

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["humanloop"],
  mcp: true,
});
Create a session scoped to Humanloop and read its MCP URL and headers
3

Connect your agent to the MCP server

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 all experiments for project pr_1234",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a Humanloop request
SETUP GUIDE

Connect Humanloop API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

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: ["humanloop"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Humanloop
3

Run Humanloop tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "List all experiments for project pr_1234" }],
});

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);
Send a request, execute the Humanloop tool calls through the session, and print the final answer

Why Use Composio?

AI Native Humanloop Integration

  • Supports both Humanloop MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for reading, writing, and querying your Humanloop data

Managed Auth

  • Built-in API key handling with secure storage
  • Central place to manage, scope, and revoke Humanloop access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Humanloop
  • Scoped, least privilege access to Humanloop resources
  • Full audit trail of agent actions to support review and compliance

Rolling this out across your team?

Give your team centralized access control across every framework with Composio’s MCP Gateway.

EXPLORE MCP GATEWAY
FAQ

Frequently asked questions

Start with Humanloop.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Humanloop tool your agent needs.Free to start.

Start building