# io.github.infoinlet-marketplace/mcp-browser-research (npm · @infoinlet/mcp-browser-research)

Web browsing & research for AI agents — fetch/read pages, structured extraction, Exa search.

- Trust score: 54/100 (low)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@infoinlet/mcp-browser-research`: 54/100 (this document), [markdown](https://verifymcp.io/servers/infoinlet-marketplace-mcp-browser-research/infoinlet-mcp-browser-research.md), [page](https://verifymcp.io/servers/infoinlet-marketplace-mcp-browser-research/infoinlet-mcp-browser-research)

## Channel facts

- Registry: `npm`
- Package: `@infoinlet/mcp-browser-research`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (131 of 133), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (131 of 133), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 6/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (UNLICENSED) isn't a recognized OSI-approved license.
  - Actively maintained (last published 65 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 210 tokens (~52/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 13% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add infoinlet-marketplace-mcp-browser-research -- npx -y @infoinlet/mcp-browser-research
```

### Codex

```bash
codex mcp add infoinlet-marketplace-mcp-browser-research -- npx -y @infoinlet/mcp-browser-research
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "infoinlet-marketplace-mcp-browser-research": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@infoinlet/mcp-browser-research"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add infoinlet-marketplace-mcp-browser-research --command npx --arg -y --arg @infoinlet/mcp-browser-research
```

### Hermes

```yaml
mcp_servers:
  infoinlet-marketplace-mcp-browser-research:
    command: "npx"
    args: ["-y", "@infoinlet/mcp-browser-research"]
```

### Other

```json
{
  "mcpServers": {
    "infoinlet-marketplace-mcp-browser-research": {
      "command": "npx",
      "args": [
        "-y",
        "@infoinlet/mcp-browser-research"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 54, +26)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] License: unverified → fail
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Schema quality: unverified → good
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: UNLICENSED

### 2026-08-01 (score 28, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 13, −23)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 36, +17)

- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 19, −17)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 36)

First indexed and scored.

## MCP tools (4)

### `browse_url` (~51 tokens)

Fetch a web page and return its title + clean readable main-content text. Works for static/SSR pages. Optionally include outbound links.

Input parameters:

- `include_links` (boolean)
- `url` (string, required)

### `extract_from_page` (~56 tokens)

Fetch a page and extract structured data from it as JSON, following your instruction (e.g. "extract the product name, price, and rating").

Input parameters:

- `instruction` (string, required): what to extract
- `url` (string, required)

### `web_search` (~46 tokens)

Semantic web search via Exa. Returns ranked results (title, url, snippet). Requires EXA_API_KEY.

Input parameters:

- `num_results` (number)
- `query` (string, required)

### `deep_research` (~57 tokens)

Multi-step research: search the web (Exa), read the top results, and synthesize an answer with [n] citations. Requires EXA_API_KEY.

Input parameters:

- `num_sources` (number)
- `question` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/infoinlet-marketplace-mcp-browser-research/infoinlet-mcp-browser-research#diagnostics

## Score history

- 2026-08-03: 54
- 2026-08-02: 54
- 2026-08-01: 28
- 2026-07-31: 13
- 2026-07-30: 36
- 2026-07-28: 19
- 2026-07-27: 36

## Links

- npm package: https://www.npmjs.com/package/@infoinlet/mcp-browser-research
- Socket report: https://socket.dev/npm/package/@infoinlet/mcp-browser-research
- Changelog RSS feed: https://verifymcp.io/servers/infoinlet-marketplace-mcp-browser-research/infoinlet-mcp-browser-research/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/infoinlet-marketplace-mcp-browser-research/infoinlet-mcp-browser-research/changelog.json
- HTML version of this page: https://verifymcp.io/servers/infoinlet-marketplace-mcp-browser-research/infoinlet-mcp-browser-research