# Deep Research (Tavily)

> Use this tool when you need to perform comprehensive web research and aggregate information from multiple sources to generate detailed technical documentation, whitepapers, or research reports. It solves problems of outdated information and tedious manual research by providing up-to-date web data through a customizable interface with configurable crawling parameters and output paths. The tool is ideal for AI assistants that require structured data for LLM consumption, particularly in contexts where generating detailed reports or documentation is necessary.

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

## Description

The Deep Research MCP Server enables AI assistants to perform comprehensive web research by leveraging Tavily's Search and Crawl APIs. Developed by PinkPixel, this TypeScript implementation aggregates information from multiple sources, extracts detailed content through configurable crawling parameters, and structures the data specifically for LLM consumption. The server features customizable documentation prompts, configurable output paths for research artifacts, and granular control over both search and crawl operations with memory usage optimization and hardware acceleration options. It's particularly valuable for users who need to generate detailed technical documentation, whitepapers, or research reports based on up-to-date web information without leaving their AI conversation context.

## 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:** browser-automation
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/pinkpixel-deep-research-tavily)
- **Repository:** <https://github.com/pinkpixel-dev/deep-research-mcp>

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

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