Log inSubmit server
Touch Browser logo

Touch Browser

by nangman-infra

Verifies web claims against page evidence, returning verdicts, confidence bands, snippets, citations, and session-level research results.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Touch Browser

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "nangman-infra-touch-browser": {
      "command": "npx",
      "args": [
        "-y",
        "@nangman-infra/touch-browser-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @nangman-infra/touch-browser-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1mo ago.

Overview

The nangman-infra/touch-browser MCP server gives AI agents page-grounded web research with claim verdicts, evidence snippets, confidence bands, and citations. It opens pages, builds structured snapshots, and evaluates whether the current page supports, contradicts, or fails to establish a claim. MCP clients use a session flow with `tb_session_create`, `tb_open`, and `tb_extract`, while multi-page work can be synthesized across opened tabs. Reach for it when answers need traceable source evidence and an explicit unresolved path instead of relying on raw page fetches.

Use cases

  • Verify a factual claim against a specific web page
  • Collect citation-linked snippets for an agent response
  • Compare evidence across multiple research pages
  • Route uncertain claims to further browsing or review

Key features

  • Page-local claim verdicts
  • Confidence bands and review recommendations
  • Citation URLs with retrieval timestamps
  • Reusable evidence snippets
  • Multi-page session synthesis
  • Headless browser research

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

17/21 checks healthy over the last 80d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · @nangman-infra/touch-browser-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars10Stargazers on the source repository.
npm downloads145Package downloads in the last 30 days.
Last commit4mo agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity4 viewsConfig copies, upvotes, and views on AllMCPs.

How Touch Browser works

What the nangman-infra/touch-browser MCP server does

The nangman-infra/touch-browser MCP server evaluates claims against the content of web pages. Rather than returning only raw HTML or converted Markdown, it opens a page, creates a structured snapshot, and maps each submitted statement to an evidence result. The result can indicate that the page supports the claim, contradicts it, lacks enough evidence, or requires another page.

Each claim outcome can include a confidence band, a review recommendation, support snippets, a verdict explanation, match signals, and citation details. Citations include the source URL and retrieval time. Reusable-claim indicators help an agent determine whether evidence may be passed into a later answer, while unresolved outcomes provide a safer alternative to presenting a weak match as fact.

The tool is evidence-grounded rather than fact-final. It records page-local support and provenance, but a model or human still needs to decide what is true across several pages or beyond the collected sources.

How it works

For MCP use, an agent creates a session, opens one or more pages, and extracts claim results. The documented sequence is tb_session_create → tb_open → tb_extract. Multi-page session synthesis aggregates grouped results from the pages opened in that session.

The extraction response exposes per-call claimOutcomes, along with grouped views for supported, contradicted, insufficient, and more-browsing-needed claims. An agent can first inspect verdict, then check reviewRecommended, read primarySupportSnippet when it needs an evidence line, and follow nextActionHint if the result does not resolve the question.

Browsing is headless-only and uses automatic search-engine selection. If a site presents a challenge, authentication step, or MFA flow, the documented behavior is a supervised recovery handoff rather than blind automation. The project also describes replayable, auditable multi-page research sessions.

Setup and configuration

The primary local MCP installation uses the public npm package @nangman-infra/touch-browser-mcp. A host such as Claude Desktop or Cursor can launch it with npx -y @nangman-infra/touch-browser-mcp. On first launch, the package downloads a matching standalone runtime from GitHub Releases, verifies its SHA-256 file, installs it under the user’s touch-browser npm runtime directory, and starts the MCP service.

The repository also provides standalone macOS and Linux bundles. These include the touch-browser command, the optimized runtime, a Node runtime, and the Playwright adapter. A bundle is installed with its install.sh script. The slim profile includes Playwright Chromium and downloads semantic or NLI models lazily; a full profile can include warm model caches for offline use.

Browser actions use the Playwright adapter by default. New CLI deployments can select the Rust CDP adapter with TOUCH_BROWSER_BROWSER_ADAPTER=cdp-rust; that path still requires Chrome or Chromium, and TOUCH_BROWSER_CDP_BROWSER can specify a nonstandard browser location.

Tools and capabilities

The nangman-infra/touch-browser MCP server supports:

  • Creating browser research sessions.
  • Opening pages for structured capture.
  • Extracting and classifying claim evidence.
  • Returning support snippets with stable references.
  • Reporting confidence bands and review recommendations.
  • Providing source URLs and retrieval timestamps.
  • Synthesizing evidence across pages in a session.
  • Handling browser-backed actions through Playwright or the optional Rust CDP path.

Use the standalone CLI for commands such as quickstart, doctor, and quick; MCP hosts do not expose the quick CLI command directly. The local diagnostics check the executable, runtime resources, data root, Node runtime, Playwright Chromium, MCP bridge entrypoint, and semantic model readiness.

Limitations and notes

Evidence is scoped to the pages that were opened and the claims submitted. An evidence-supported result does not establish universal truth, and an unresolved result may require another page or human review. Claims marked for review should not be reused without that review or a second verification pass.

The MCP path is intended for public documentation and research web content. Challenge, authentication, and MFA situations use supervised recovery handoff. The Rust CDP browser path requires Chrome or Chromium, while semantic and NLI models may be downloaded lazily depending on the bundle profile.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Touch Browser

Run it locally with `npx -y @nangman-infra/touch-browser-mcp`. On first launch, the package downloads and verifies its matching runtime bundle.

Yes.

It can return `evidence-supported`, `contradicted`, `insufficient-evidence`, or `needs-more-browsing`.

Claim outcomes can include a citation URL and retrieval timestamp, along with support snippets and stable references.

No. It collects and evaluates page-local evidence; a model or human still decides what is true across pages or the wider world.

Related MCP servers

All in Research All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewTouch Browser AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/nangman-infra-touch-browser?style=directory)](https://allmcps.com/mcp/nangman-infra-touch-browser)
HTML Embed
<a href="https://allmcps.com/mcp/nangman-infra-touch-browser"><img src="https://allmcps.com/api/badge/nangman-infra-touch-browser?style=directory" alt="Touch Browser on AllMCPs" /></a>