Borrowing it
Nothing to install: this file belongs to simonediroma/webfetch_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/simonediroma/webfetch_mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/simonediroma/webfetch_mcpWrote 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/instructions/simonediroma/webfetch_mcp/claude-md)<a href="https://agentmods.dev/instructions/simonediroma/webfetch_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/simonediroma/webfetch_mcp/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.
<a href="https://agentmods.dev/instructions/simonediroma/webfetch_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/simonediroma/webfetch_mcp/claude-md.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 | $0.02393 | $0.02393 |
| Opus 5.5 | $0.00957 | $0.00957 |
| Sonnet 5.5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade B, and why
webfetch_mcp CLAUDE.md scanned grade B with 2 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Add to `~/.claude/settings.json`: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
impersonate: str | None, # curl-cffi TLS fingerprint target, e.g. "chrome131" How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebFetch MCP Server
IMPORTANT — How to use this tool correctly
Always use mcp__webfetch__fetch to fetch URLs. Never use the built-in WebFetch tool — it ignores all custom headers and output format configuration.
Never pass output_format or extract_text unless the user explicitly asks for a specific format.
The server is configured with a default output format (currently trafilatura).
Passing output_format="raw" or extract_text=True overrides that configured default and produces lower-quality output.
Rules:
- ✅
mcp__webfetch__fetch(url="https://example.com")— correct, uses configured defaults - ❌
mcp__webfetch__fetch(url="...", output_format="raw")— wrong, overrides trafilatura default - ❌
mcp__webfetch__fetch(url="...", extract_text=True)— wrong, produces noisy CSS-contaminated text - ✅
mcp__webfetch__fetch(url="...", output_format="markdown")— ok only if the user explicitly asked for markdown
Local Python MCP server that replaces the AI assistant's built-in WebFetch tool. Main purpose: inject domain-scoped custom HTTP headers into every outbound request, used to inject provider-specific authentication headers on specific domains.
Project structure
webfetch_mcp/
├── server.py # MCP server — single entrypoint
├── requirements.txt # Python dependencies
├── .env.example # Header config template (copy to .env)
└── .claude/
└── launch.json # Dev server config for Claude Code preview_start
Setup
python -m venv .venv
# Windows
.venv\Scripts\pip install -r requirements.txt
# Mac / Linux
.venv/bin/pip install -r requirements.txt
cp .env.example .env # then edit .env with real tokens
Configuration (.env)
WEBFETCH_HEADERS — domain-scoped request headers
WEBFETCH_HEADERS is a single-line JSON object with domain-scoped headers:
WEBFETCH_HEADERS={"*": {"User-Agent": "MyBot/1.0"}, "example.com": {"X-Auth-Token": "TOKEN"}}
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.
- 3d ago Changed · +15 lines · +394 tokens per session c00ecc828fb6
- 2mo ago First seen · 223 lines · 1,999 tokens per session scan B 91ac5d8223d2
webfetch_mcp CLAUDE.md is an instructions file published in the GitHub repository simonediroma/webfetch_mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 2,393 tokens to every session, about $0.0096 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
webfetch_mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| webfetch_mcp CLAUDE.mdsimonediroma/webfetch_mcp | Instructions file | 2 | 5d ago | MIT | B | 2,393 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |
| generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginners | Instructions file | 124k | today | MIT | A | 2,981 | Codex, OpenCode |