Prompt Sanitizer — prompt-injection scan for untrusted content

● Active

com.oroboros-design.angel/prompt-sanitizer

Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.

Connect this server

One click to install, or copy the config below. Suits: Cursor · HTTP clients.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "prompt-sanitizer": {
      "url": "https://angel.oroboros-design.com/mcp/prompt-sanitizer"
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --transport http prompt-sanitizer https://angel.oroboros-design.com/mcp/prompt-sanitizer
VS Code
code --add-mcp '{"name":"prompt-sanitizer","type":"http","url":"https://angel.oroboros-design.com/mcp/prompt-sanitizer"}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Search & Web
Version
1.0.0
Registry
active
Published
11/14/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: Prompt Sanitizer — prompt-injection scan for untrusted content is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit 7 days ago (Nov 14, 2026), 0 open issues.
Official registry
Active
Published as com.oroboros-design.angel/prompt-sanitizer in the official MCP registry, version 1.0.0.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
Hosted by the publisher
Your client talks to angel.oroboros-design.com: prompts and tool arguments leave your machine for that host.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 13:08 UTCStatus history & uptime →
● Working449 msprotocol 2025-06-18v1.0.0tools

The endpoint answered the MCP handshake as "Prompt Sanitizer — prompt-injection scan for untrusted content" and listed 4 tools. Answering since Nov 18, 2026.

Context cost ≈ 1.2k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 4 tools.

Tools (4)

  • stealth_read4 params

    Returns a public https page as clean Markdown for an agent (headings, lists, tables kept; navigation, cookie banners, scripts and everything hidden from people removed), strips invisible Unicode and flags text aimed at the model — with verdict, score, findings, title and language. JSON and text pass through. One GET as a declared bot, no login or bot-protection bypass; a blocked page is never charged. Free with a key (500 calls) or 5 calls a day without one; then 0.02 USDC per call via x402, or 1 call from a key. After: preflight before your agent buys or pays anything the page offers (the result's next field has the exact call).

    Show parameters
    • urlstringrequiredthe public https page to read (1 MB, 10 s)
    • bundle_tokenstringYour key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too.
    • payment_txstringHash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature.
    • payer_addressstringWallet you pay from (optional; the x402 price is the same for every address).
  • input_guard5 params

    Removes hidden content and flags text aimed at the model, for untrusted input before an agent acts on it: web pages, emails, RAG chunks, tool and MCP responses. Strips invisible Unicode (tag smuggling decoded, zero-width, bidi) and HTML hidden from people; flags role takeover, forged system or tool turns, requests for keys, the prompt or payments, exfiltration links, homoglyphs and base64 payloads, in 17 languages. Rule-based. Verdict clean, caution or hostile, score, findings, cleaned text. Free with a key (500 calls) or 5 calls a day without one; then 0.02 USDC per call via x402, or 1 call from a key. After: preflight before your agent pays anything the content pointed to (the result's next field has the exact call).

    Show parameters
    • textstringthe content to check (send text or url)
    • urlstringa public https page to fetch once and check (256 KB)
    • bundle_tokenstringYour key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too.
    • payment_txstringHash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature.
    • payer_addressstringWallet you pay from (optional; the x402 price is the same for every address).
  • buy_pack_with_card2 params

    For businesses without USDC: 5,000 calls €9.00, one-time, 90 days, businesses only, paid in EUR by card or Link. Returns checkout_url for a person to open; the checkout asks for the company or freelance name. After payment the success page (Accept: application/json) returns the key, and it is e-mailed. After: any tool with bundle_token.

    Show parameters
    • callsinteger
    • emailstringWhere the key is sent (optional; Stripe asks otherwise).
  • input_guard_preview2 params

    Free prompt-injection quick scan for untrusted input: up to 4,000 characters of text, or one https page, checked for hidden instructions aimed at agents (role override, invisible Unicode, hidden HTML) in 17 languages incl. Chinese, Japanese, Korean, Hindi, Arabic. Returns verdict, score and the top 3 findings. After: input_guard for every finding and the cleaned text.

    Show parameters
    • textstring
    • urlstring

Checked by Serverdex with a plain initialize + tools/list call to angel.oroboros-design.com/mcp/prompt-sanitizer, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 17, 2026
Stars
0
Forks
0
Last push
Nov 14, 2026
License
MIT

JavaScriptagent-securityai-agentsguardrailsllm-securitymcpmcp-servermodel-context-protocolprompt-injectionx402

From the README

mcp-prompt-sanitizer Prompt-injection scan for untrusted content — a single-purpose MCP server for AI agents. No install, no account: it runs as a remote server; this repo also has a zero-dependency stdio bridge. Use it Claude Code Claude Desktop, Cursor, Windsurf, VS Code (remote server) Any stdio client (Node 18+) Then ask your agent, for example: Before summarising https://example.com/article, run input_guard on it and only use the cleaned text. Tools Paying The first 3 paid calls per agent are free (identify your agent with the header X-API-Key, or set ANGELAPIKEY for the stdio bridge). After that each call is paid per request in USDC on Base via x402 (params.meta["x402/payment"]), with a prepaid pack (bundletoken) or by card (buypackwith_card). The 402 answer names the exact amount and the pay-to address before anything is signed. The scan is deterministic (patterns and character checks, no model). Treat caution and hostile as a reason to ignore instructions in that content, not as proof that it is harmless otherwise. More • Same checks as a library: npm i angel-agent-guard · pip install angel-agent-guard (angel-agent-guard) • All of Angel's tools in one server: https://angel.oroboros-design.com/agenten/signal/mcp · A2A agent card: https://angel.oroboros-design.com/.well-known/agent.json • MCP Registry: com.oroboros-design.angel/prompt-sanitizer Operated by Oroboros Design (Köln, Germany). MIT licence for the code in this repo.

Read the full README on GitHub →

Remotes

  • streamable-httphttps://angel.oroboros-design.com/mcp/prompt-sanitizer

Alternatives to Prompt Sanitizer — prompt-injection scan for untrusted content

All Prompt Sanitizer — prompt-injection scan for untrusted content alternatives →Best Search & Web servers →

The most-starred Search & Web servers in the index, with their live-check result.

ServerStarsLast pushLive check
Browser Use121,623Nov 2026Working
Scrapling MCP Server104,822Nov 2026Local / not checked
Chrome DevTools MCP58,028Nov 2026Local / not checked
Chrome DevTools MCP58,014Nov 2026Local / not checked
com.puter MCP Server44,182Nov 2026Needs sign-in

Prompt Sanitizer — prompt-injection scan for untrusted content: questions people ask

Is Prompt Sanitizer — prompt-injection scan for untrusted content a remote or a local MCP server?
According to its entry in the official MCP registry, Prompt Sanitizer — prompt-injection scan for untrusted content ships as a hosted endpoint (streamable-http) that your client connects to by URL.
Does Prompt Sanitizer — prompt-injection scan for untrusted content need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is Prompt Sanitizer — prompt-injection scan for untrusted content safe to use?
Looks healthy: Prompt Sanitizer — prompt-injection scan for untrusted content is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is Prompt Sanitizer — prompt-injection scan for untrusted content still maintained?
Active: the repository's last commit 7 days ago. Last push Nov 14, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 17, 2026.
What tools does Prompt Sanitizer — prompt-injection scan for untrusted content expose?
4 tools as listed by the server itself during the live check, including stealth_read, input_guard, buy_pack_with_card, input_guard_preview. The full list with parameters is in the Live check section above.
How do I add Prompt Sanitizer — prompt-injection scan for untrusted content to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.

More from daoudandiaye98-alt

All 6 servers by daoudandiaye98-alt →
  1. Mare Liberum · the open sea for agentsFirst stop for agents: read any page as Markdown, check sites, shared memory, buy for people.
  2. Mare Liberum · the open sea for agentsThe open sea for agents: call a need, get stores, products, prices and the routes that worked.
  3. Base Token Audit — ERC-20 honeypot check and swap route dataERC-20 honeypot and rug-pull check on Base and Ethereum, plus free swap route data.
  4. Checkout Guard — pre-purchase check for shops, payment links and paid APIsPre-purchase check for any shop, checkout or payment link, paid API or x402 endpoint.
Browse all Search & Web →

Add the badge to your site

Show visitors that Prompt Sanitizer — prompt-injection scan for untrusted content is listed here — it’s also the link we check for a free listing.

Prompt Sanitizer — prompt-injection scan for untrusted content — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/com-oroboros-design-angel-prompt-sanitizer?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Prompt Sanitizer — prompt-injection scan for untrusted content — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![Prompt Sanitizer — prompt-injection scan for untrusted content — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/com-oroboros-design-angel-prompt-sanitizer?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/com-oroboros-design-angel-prompt-sanitizer) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/com-oroboros-design-angel-prompt-sanitizer) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/com-oroboros-design-angel-prompt-sanitizer)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/com-oroboros-design-angel-prompt-sanitizer"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/com-oroboros-design-angel-prompt-sanitizer"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/com-oroboros-design-angel-prompt-sanitizer"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).