Mcp Bun Fetch — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Bun Fetch (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server that fetches web content, converts HTML to Markdown, and processes it with Claude AI. This is meant to be a replacement for Claude's default WebFetch, that seems to get regularly blocked from servers. This works around that by not identifying itself as Claude.
No installation required. The MCP configurations below use bunx to run the package directly from GitHub.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"fetch": {
"command": "bunx",
"args": ["github:ScottPierce/mcp-bun-fetch#v1"]
}
}
}Run the following command:
claude mcp add fetch -- bunx github:ScottPierce/mcp-bun-fetch#v1Run without building:
bun run index.tsRun tests:
bun testBuild:
bun run buildTo use a local build instead of a published package:
{
"mcpServers": {
"fetch": {
"command": "bun",
"args": ["/absolute/path/to/mcp-fetch/dist/index.js"]
}
}
}Fetches a URL, converts HTML to Markdown, and processes with Claude.
Parameters:
url (required): URL to fetchprompt (required): What to extract or analyze from the page~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.