Fetch BrowserSAFE
A powerful headless browser MCP server that enables AI agents to fetch web content and perform Google searches without requiring any API keys.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A powerful headless browser MCP server that enables AI agents to fetch web content and perform Google searches without requiring any API keys. Built with modern web standards and designed for seamless integration with AI platforms.
Features
- No API Keys Required: Uses a sophisticated headless browser approach to fetch content directly
- Smart Google Search:
- Extract structured results from Google searches
- Support for both web and news results
- Configurable number of results (1-100)
- Full content fetching of search results
- Automatic retry and error handling
- Universal Content Fetching:
- Support for any webpage or API endpoint
- Multiple output formats (HTML, JSON, Text, Markdown)
- Automatic content type detection
- Response size limits and timeout protection
- Rate limiting protection
- Format Conversion:
- Clean HTML to Markdown conversion
- Pretty-printed JSON responses
- Structured HTML output
- Plain text with proper formatting
Tools
1. Google Search Tool (google_search)
Executes Google searches and fetches full content of results:
{
query: "your search query",
responseType: "markdown", // or "json", "html", "text"
maxResults: 10, // 1-100 results
topic: "web" // or "news"
}2. URL Fetcher Tool (fetch_url)
Fetches content from any URL:
{
url: "https://example.com",
responseType: "markdown", // or "json", "html", "text"
timeout: 30000 // optional, in milliseconds
}Installation
Via Smithery
# For Claude npx -y @smithery/cli install @TheSethRose/fetch-browser --client claude # For Cursor npx -y @smithery/cli install @TheSethRose/fetch-browser --client cursor # For TypeScript npx -y @smithery/cli install @TheSethRose/fetch-browser --client typescript
Manual Installation
# Clone the repository git clone https://github.com/TheSethRose/fetch-browser.git cd fe
6276a8ab1504OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add fetch-browser -- npx -y [email protected]
{
"mcpServers": {
"fetch-browser": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (2)
1 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
fetch_url | read | Fetch content from a URL with proper error handling and response processing |
google_search | write | Execute a Google search and return results in various formats |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, @smithery/sdk, happy-dom, jsdom, zod, @types/jsdom, @types/node, concurrently
Gates applied: no_behavioural_pass.
6276a8ab1504full audit observations/trust-audit/mcp-server/thesethrose__fetch-browser.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 6276a8ab1504 | SAFE | B | 89 | first audit |
Questions
What is the Fetch Browser MCP server?
A powerful headless browser MCP server that enables AI agents to fetch web content and perform Google searches without requiring any API keys.
What tools does Fetch Browser expose?
2 in total: 1 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Fetch Browser safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Fetch Browser need?
No credential environment variables were found in its source, so it appears to need none.
How does Fetch Browser run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as fetch-browser at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (6276a8ab1504), read on 2026-10-09. The repository is watched and re-audited when it changes.