MCP servercom.oroboros-design.angel/prompt-sanitizer
Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.
Overview
Score?
UNRATED 0.038
of what a free look can see, on 2 looks
Looks
2
last 1 day ago
Tools
4
changed 1 day ago
More info
URL
angel.oroboros-design.com/mcp/prompt-sanitizer
streamable-http
Says it is
angel-prompt-sanitizer 1.0.0
protocol 2025-06-18
In the record since
3 days ago
Among servers32,724 with a card
0median 0.546 · this server 0.038 · highest on record 0.8351
Toolsfrom sha256:43d88f893c…592d9c · +1 −0 1 day ago
| Tool | Schema |
|---|---|
| buy_pack_with_card For agents and people without USDC: prepaid packs paid in EUR by card or Link (100 calls €1.50 · 500 calls €5.00 · 5,000 calls €39.00) — including Link's wallet for agents (one-tim |
input · no output |
| input_guard Prompt-injection and hidden-instruction scan for untrusted input before an agent acts on it: web pages, emails, RAG chunks, tool and MCP responses. Flags text aimed at the model (r |
input · no output |
| input_guard_preview 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 U |
input · no output |
| stealth_read added Read a public https page for an agent: the main content as clean Markdown (headings, lists, tables kept; navigation, cookie banners, scripts and everything hidden from humans remov |
input · no output |
Verify it yourself
npx teppi-check https://angel.oroboros-design.com/mcp/prompt-sanitizercurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M7EW0Z5FYQ937H6D4HFR597Q