mcpField
O
Openai Deep Research Mcp

Openai Deep Research Mcp

Local
github.com/fbettagAI & Agents7Updated 68w ago
Repository

About Openai Deep Research Mcp

OpenAI Deep Research MCP Server connects MCP clients to OpenAI's Deep Research API for submitting research questions and retrieving cited results. It provides request creation, status checks, and result retrieval.

Key features

  1. 01Create research requests
  2. 02Check request status
  3. 03Retrieve results with citations

Use cases

  1. 01Submit complex research questions
  2. 02Track research task progress
  3. 03Retrieve completed findings and citations

MCP support

The MCP server exposes tools for creating OpenAI Deep Research requests, checking their status, and retrieving results.

#research#deep-research#web-search#openai#natural-language#report-generation#knowledge-synthesis#citations#real-time#automation#academic#analysis

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "openai-deep-research": {
      "command": "npx",
      "args": [
        "-y",
        "github:fbettag/openai-deep-research-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}
Run commandnpx -y github:fbettag/openai-deep-research-mcp
Environment variables to set
OPENAI_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmgithub:fbettag/openai-deep-research-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

OpenAI Deep Research MCP Server

A TypeScript MCP (Model Context Protocol) server that provides access to OpenAI's Deep Research API.

Features

  • openai_deep_research_create: Create new research requests
  • openai_deep_research_check_status: Check the status of research requests
  • openai_deep_research_get_results: Retrieve completed research results with citations

Quick Start

npx github:fbettag/openai-deep-research-mcp

Quick Setup with Claude CLI

claude mcp add openai-deep-research -s user npx github:fbettag/openai-deep-research-mcp -e OPENAI_API_KEY=sk-your-openai-api-key-here

Replace sk-your-openai-api-key-here with your actual OpenAI API key.

Claude Desktop Setup (Manual)

Add to your Claude Desktop configuration:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "openai-deep-research": {
      "command": "npx",
      "args": ["github:fbettag/openai-deep-research-mcp"],
      "env": {
        "OPENAI_API_KEY": "sk-your-openai-api-key-here"
      }
    }
  }
}

Available Functions

Create Research Request
openai_deep_research_create({
  query: "Your research question",
  system_message?: "Optional guidance",
  model?: "o3-deep-research-2025-06-26",
  include_code_interpreter?: false
})
Check Status
openai_deep_research_check_status({
  request_id: "req_123..."
})
Get Results
openai_deep_research_get_results({
  request_id: "req_123..."
})

Models

  • o3-deep-research-2025-06-26: Full research model (5-30 min)
  • o4-mini-deep-research-2025-06-26: Faster, lightweight model

Requirements

  • Node.js >= 18.0.0
  • OpenAI API key with Deep Research access

Development

npm install
npm run dev

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.