What is safe-fetch-mcp-server CLAUDE.md?

A project guide for safe-fetch-mcp-server, an MCP server that retrieves web pages and returns clean Markdown text. It documents security rules for blocking unsafe requests to private or internal network addresses.

Use it when modifying URL fetching, request validation, redirects, DNS resolution, or other security-sensitive parts of this server.

It helps agents preserve protections against server-side request forgery, DNS changes during a request, unsafe redirects, and disguised IP addresses.

How Sanoy24/safe-fetch-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Sanoy24/safe-fetch-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Sanoy24/safe-fetch-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Sanoy24/safe-fetch-mcp-server

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sanoy24/safe-fetch-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/sanoy24/safe-fetch-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sanoy24/safe-fetch-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sanoy24/safe-fetch-mcp-server/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sanoy24/safe-fetch-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sanoy24/safe-fetch-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,386 This file is loaded in full into every session.

When invoked 1,386 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01386	$0.01386
Opus 5	$0.00693	$0.00693
Sonnet 5	$0.00277	$0.00277
Haiku 4.5	$0.00139	$0.00139

Measured 9d ago against content hash 2da03b99bdae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

safe-fetch-mcp-server CLAUDE.md scanned grade B with 1 finding 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 9d 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

1. Write the failing test first (e.g. a fetch of `http://169.254.169.254/` must be refused).

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

CLAUDE.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — safe-fetch-mcp-server

Context for Claude Code (and humans) working in this repo. Read this before writing code.

What this project is

An MCP server that fetches web content for an agent and returns clean markdown. Its reason to exist is security correctness: it must be safe-by-default against SSRF, DNS rebinding, redirect-to-internal, and encoding bypasses — the exact classes that produced real 2026 CVEs in other fetch servers. "Has SSRF protection" is not the bar; "provably correct, verified by the OWASP MCP Top 10 and public scanners" is.

The one rule that matters most

Every outbound request MUST pass through the security/ guard. No code path may fetch a URL without it. The most common real-world failure (a 2026 CVE) was a poller that re-fetched a URL and bypassed the guard applied on first load. Do not introduce a second fetch path. If you need to fetch, call the single hardened fetch function.

Non-negotiable security invariants

Validate the resolved IP, never the hostname string. IP encodings are infinite; hostname blocklists fail.
Pin the connection to the resolved IP (resolve once, connect to that IP) to defeat DNS rebinding.
Re-validate every redirect hop with the full guard — a 302 to 127.0.0.1 must be rejected.
Scheme allowlist: http and https only. Reject file:, gopher:, ftp:, etc.
Strip/reject URL userinfo (user:pass@).
Enforce max response bytes and connect/idle/total timeouts.
Block on the resolved IP: loopback 127.0.0.0/8 + ::1, private RFC-1918, link-local 169.254.0.0/16 (metadata!), ULA fc00::/7, and IPv4-mapped IPv6 loopback (::ffff:127.0.0.1).
Default SAFE_FETCH_ALLOW_LOCAL=false. Local access is opt-in only.

See .claude/skills/secure-fetch-ssrf/SKILL.md for the full checklist and threat matrix.

Architecture

Agent → MCP client → fetch_url tool → security guard → pinned fetch → markdown → result

src/index.ts — entrypoint, chooses transport (stdio default, HTTP if TRANSPORT=http).
src/server.ts — McpServer + tool registration.
src/tools/fetchUrl.ts — the fetch_url tool.
src/security/ — urlPolicy, ipGuard, resolveAndPin, redirects. The guard lives here.
src/content/toMarkdown.ts — HTML → clean markdown.
src/config.ts — env parsing + defaults.
test/ — one spec per threat-matrix row.

Read the full file on GitHub · 113 lines

Changes

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.

9d ago First seen · 113 lines · 1,386 tokens per session scan B 2da03b99bdae

Subscribe to this mod's changes

safe-fetch-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Sanoy24/safe-fetch-mcp-server (1 stars, last pushed 29d ago), licensed MIT. It adds 1,386 tokens to every session, about $0.0069 per session on Opus 5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

safe-fetch-mcp-server: Instructions file for Claude Code