OpenAI

There are two ways to give an OpenAI model Corsair’s tools. Use the Agents SDK if you’re building with @openai/agents; use the Responses API if you’re calling the model directly over HTTP.

Agents SDK
Responses API

Use OpenAIAgentsProvider to connect Corsair to the OpenAI Agents SDK.

Install

npm install @openai/agents

Usage

agent.ts

import { OpenAIAgentsProvider } from '@corsair-dev/mcp';
import { Agent, run, tool } from '@openai/agents';
import { corsair } from './corsair';

const provider = new OpenAIAgentsProvider();
const tools = provider.build({ corsair, tool });

const agent = new Agent({
    name: 'corsair-agent',
    model: 'gpt-4.1',
    instructions:
        'You have access to Corsair tools. Use list_operations to discover available APIs, get_schema to understand required arguments, and run_script to execute them. When referencing resources (like channels), always use their ID, not their name.',
    tools,
});

const result = await run(agent, 'Setup corsair, then list all Slack channels.');
console.log(result.finalOutput);

OpenAIAgentsProvider.build() is async. It dynamically imports @openai/agents as an optional peer dependency. Pass the tool function from @openai/agents so the provider can wrap each Corsair tool in the correct format.

Use getOpenAIMcpConfig to connect Corsair to the OpenAI API over HTTP. You expose Corsair as an MCP server endpoint and pass the config to the OpenAI client.

Install

npm install openai

Server

Expose Corsair as an MCP HTTP endpoint using createBaseMcpServer and createMcpRouter.

server.ts

import express from 'express';
import { createBaseMcpServer, createMcpRouter } from '@corsair-dev/mcp';
import { corsair } from './corsair';

const app = express();
app.use(express.json());

app.use('/mcp', createMcpRouter(() => createBaseMcpServer({ corsair })));

app.listen(3000, () => console.log('MCP server running on :3000'));

Client

agent.ts

import OpenAI from 'openai';
import { getOpenAIMcpConfig } from '@corsair-dev/mcp';

const client = new OpenAI();

const response = await client.responses.create({
    model: 'gpt-4.1',
    tools: [
        {
            type: 'mcp',
            ...getOpenAIMcpConfig('http://localhost:3000/mcp'),
        },
    ],
    input: 'Setup corsair, then list all Slack channels.',
});

console.log(response.output_text);

getOpenAIMcpConfig returns the serverLabel and serverUrl fields expected by OpenAI’s mcp tool type.

Get Started

Frameworks

Adapters

Workflows (beta)

Reference

Install

Usage

Install

Server

Client

​Install

​Usage

​Install

​Server

​Client

Install

Usage

Install

Server

Client