# Open Deep Research

> Use this tool when you need to leverage advanced language models and AI research capabilities through a Model Context Protocol (MCP) server. It solves problems related to natural language processing, information retrieval, and AI-assisted research by providing access to HuggingFace Open Deep Research project through MCP clients. The tool requires API keys from OpenAI, HuggingFace, and SERP API as input and outputs AI-driven research and language model capabilities.

Canonical page: https://skillsregistry.net/skills/microsoft-open-deep-research  
JSON: https://api.skillsregistry.net/v1/skills/microsoft-open-deep-research

## Description

This is a Model Context Protocol (MCP) server that wraps the HuggingFace Open Deep Research project, built on their smolagents library, making the project available for use with MCP clients, such as AI assistants.

This is an early work-in-progress, has limited testing, and requires access to API's that will be replaced in the near future. For now, the following API keys are required to be set in the environment or in a .env file (see .env.example):

OpenAI API Key: https://platform.openai.com/
HuggingFace API Key: https://huggingface.co/
SERP API Key: https://serpapi.com/

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/microsoft-open-deep-research)
- **Repository:** <https://github.com/microsoft/semanticworkbench/tree/HEAD/mcp-servers/mcp-server-open-deep-research>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "microsoft-open-deep-research"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/microsoft-open-deep-research` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/microsoft-open-deep-research/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt