# touch-browser

> Use this tool when you need to automate web research workflows and extract reliable evidence from web pages. It solves problems related to information gathering, citation management, and risk assessment by providing AI agents with a server to search, extract, and synthesize web content into reports. With inputs of web page URLs and search queries, and outputs of citation-ready reports and evidence extracts, touch-browser is ideal for use cases requiring efficient and trustworthy web research.

Canonical page: https://skillsregistry.net/skills/nangman-infra-touch-browser  
JSON: https://api.skillsregistry.net/v1/skills/nangman-infra-touch-browser

## Description

touch-browser is an evidence-grounded MCP server for public docs and research web workflows. It helps AI agents search and open web pages, extract page-local evidence with citations and confidence bands, classify browsing risk, and synthesize multi-page sessions into citation-ready reports.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **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:** [Glama](https://glama.ai/mcp/servers/u4fdqqptl5)
- **Repository:** <https://github.com/nangman-infra/touch-browser>

## 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": "nangman-infra-touch-browser"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nangman-infra-touch-browser` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nangman-infra-touch-browser/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