Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/simonediroma/webfetch_mcp/webfetchgit clone --depth 1 https://github.com/simonediroma/webfetch_mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00210 |
| Opus 5 | $0.00000 | $0.00105 |
| Sonnet 5 | $0.00000 | $0.00042 |
| Haiku 4.5 | $0.00000 | $0.00021 |
Grade A, and why
webfetch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Ricorda le regole per usare il tool webfetch MCP in questo progetto:
- Usa SEMPRE
mcp__webfetch__fetch— mai il built-inWebFetch - NON passare
output_formata meno che l'utente non lo chieda esplicitamente - NON usare
extract_text=True— è deprecato e produce output con CSS noise - Il server è configurato con
output_format: trafilaturacome default — omettere il parametro significa usare trafilatura automaticamente - Puoi passare
extra_headerssolo se servono header aggiuntivi specifici per la richiesta
Esempio corretto:
mcp__webfetch__fetch(url="https://example.com")
Esempio sbagliato:
mcp__webfetch__fetch(url="https://example.com", output_format="raw")
mcp__webfetch__fetch(url="https://example.com", extract_text=True)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 19 lines · 0 tokens per session scan A effae7c53f18
webfetch is a command published in the GitHub repository simonediroma/webfetch_mcp (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 210 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
search
Web search (default for all search and research queries).
check-browser
Use Real Browser MCP to check what's currently showing in my browser.
browser
Verify a page or flow in a real browser via Cursor's chrome-devtools MCP. Read-only — Cursor reports; does not modify source files.
dev-in-browser
Use your browser to view https://verso.localhost which is tied to livereload dev server which is already running. You can inspect that page (including taking screenshots!) to validate that your changes fixed the issue.
reproduce-bug
Reproduce a React or browser bug with React-Sentinel before proposing a fix.
visbug-mcp-start
Запустить VisBug Bridge и выбрать проект для записи.