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 skills add NimbleBrainInc/mcp-webfetch --skill mcp_webfetchgit clone --depth 1 https://github.com/NimbleBrainInc/mcp-webfetchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nimblebraininc/mcp-webfetch/mcp_webfetch)<a href="https://agentmods.dev/skills/nimblebraininc/mcp-webfetch/mcp_webfetch"><img src="https://agentmods.dev/badge/skills/nimblebraininc/mcp-webfetch/mcp_webfetch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nimblebraininc/mcp-webfetch/mcp_webfetch"><img src="https://agentmods.dev/badge/skills/nimblebraininc/mcp-webfetch/mcp_webfetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00449 |
| Opus 5.5 | $0.00000 | $0.00180 |
| Sonnet 5.5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
mcp_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 1mo 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
WebFetch
When to Use (and When Not To)
| Situation | Tool |
|---|---|
| Have a specific URL, want to understand its content | web_fetch |
| Need to find URLs on a topic | Use a web search tool first, then web_fetch on results |
| Want raw HTML or markdown | Don't use this, it returns an LLM summary |
| URL points to PDF, image, JSON API | Don't use this, it only handles HTML pages |
Writing Effective Prompts
The prompt is sent to an LLM along with the page's markdown. Specific prompts get better results.
| Weak | Strong |
|---|---|
| "Summarize this page" | "Extract the pricing tiers and format as a table" |
| "What is this?" | "What problem does this product solve and who is the target audience?" |
| "Tell me about it" | "List the API endpoints documented on this page with their HTTP methods" |
For large pages, say what section you care about: "Focus on the installation instructions" or "Only look at the FAQ section."
URL Handling
- No scheme? Auto-prepended with
https://("example.com" becomes "https://example.com") - HTTP? Auto-upgraded to HTTPS
- Cross-host redirect? Returns an error with the redirect URL. Call
web_fetchagain with that new URL.
Caching
Fetched pages are cached for 15 minutes. Multiple questions about the same URL are cheap because only the LLM step re-runs, not the HTTP fetch. Use this to your advantage:
web_fetch(url="https://example.com/docs", prompt="What authentication methods are supported?")
web_fetch(url="https://example.com/docs", prompt="What are the rate limits?") ← cache hit, no re-fetch
Limitations
- HTML only. Non-HTML content types (PDF, JSON, images) return an error.
- Pages requiring JavaScript rendering may return incomplete content.
- Content over 180K characters is truncated. Be specific in your prompt for large pages.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 44 lines · 0 tokens per session scan A c068cbb469b6
mcp_webfetch is a skill published in the GitHub repository NimbleBrainInc/mcp-webfetch (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 449 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 skills, from other repositories
mcp_finnhub
Follow-up questions ("what's the market cap?", "what do analysts say?") should use data from earlier tool responses before making new calls. If you already fetched a company profile or financials, surface that data directly.
mcp_ipinfo
Follow-up questions ("this IP", "that one", "is it a VPN?") → reuse IP from prior result.
web-research-workflow
Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and available API keys. Includes competitor page tracking, snapshot diffing, and change alerting. Use when researching web content, scraping, extracting raw markdown…
mcp_granola
All tools that accept meeting identifiers use meetingid (not docid, id, or documentid). The meetingid value comes from the id field in search results and meeting lists.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.