# DeepResearch

> Use this tool when you need to conduct thorough and efficient multi-step web research on complex topics. DeepResearch provides a structured approach to generating comprehensive reports, leveraging AI-powered web searches and analysis to solve problems of manual research management and citation gathering. It accepts research topics and parameters as input, and outputs detailed, citation-rich reports, making it ideal for use cases requiring in-depth information synthesis and analysis.

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

## Description

DeepResearch MCP Server provides AI assistants with a structured approach to conducting multi-step web research. It leverages Firecrawl for web searches and OpenAI's GPT-4 for analyzing findings and generating comprehensive reports. The server implements a stateful research process that iteratively explores topics at configurable depths, with each step analyzing previous findings to determine the next search query. Built with TypeScript and the Model Context Protocol, it features robust error handling, token optimization for large research sessions, and both step-by-step and one-shot research workflows. This implementation is particularly valuable for users who need thorough, citation-rich research reports on complex topics without manually managing the search and synthesis process.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/deep-research)
- **Repository:** <https://github.com/ameeralns/deepresearchmcp>

## 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": "deep-research"
    }
  }
}
```

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