Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent safety checks: prompt-injection scan, honeypot check, x402 preflight + crypto data (USDC/x402)

REMOTE · ANGEL.OROBOROS-DESIGN.COM

Checks before an agent acts: prompt-injection scan, honeypot check, x402 preflight. 3 free calls.

+1 this week 61 Trust /100

Last scanned (23 hours ago)

Scores higher than 45% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Crypto and Web3

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability53
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2332 tokens (~333/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability check failed: schema churn in the 8 days we've observed: 18 tool removals, 0 breaking changes, 0 auth/transport breaks, 7 additions. See how to fix → Fail
Tool Coverage93
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 79% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "input_guard" implies "remove" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 0
    • Tool “preflight” rewrote its description, which is the text the model reads security
    • “preflight” added an optional parameter “agent” cosmetic
    • “preflight” added an optional parameter “budget” cosmetic
    • “preflight” added an optional parameter “currency” cosmetic
    • “preflight” added an optional parameter “need” cosmetic
    • “preflight” added an optional parameter “region” cosmetic
    • “preflight” reworded the description of “url” cosmetic
    • “preflight” made “url” optional cosmetic
    • Tool “preflight” changed its title: Pre-purchase check for any shop, checkout link, payment page, API or x402 endpoint → Pre-purchase check for any shop, checkout link, payment page, API or x402 endpoint — or for a need: find the offer and check it cosmetic
  • 19 Nov 26 −1
    • Tool “buy_signal_pack” was removed ▼ security
    • Tool “exchange_route” was removed ▼ security
    • Tool “recommend” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “buy_pack_with_card” rewrote its description, which is the text the model reads security
    • Tool “input_guard” rewrote its description, which is the text the model reads security
    • Tool “preflight” rewrote its description, which is the text the model reads security
    • Tool “shield_check” rewrote its description, which is the text the model reads security
    • Tool “stealth_read” rewrote its description, which is the text the model reads security
    • Tool “token_risk” rewrote its description, which is the text the model reads security
    • Schema quality: 280 → 308 ▼ functional
    • Destructive annotations: pass → 0 functional
    • Server version: 1.3.0 → 2.0.0 functional
    • “buy_pack_with_card” reworded the description of “email” cosmetic
    • “input_guard” reworded the description of “bundle_token” cosmetic
    • “input_guard” reworded the description of “payer_address” cosmetic
    • “preflight” reworded the description of “bundle_token” cosmetic
    • “preflight” reworded the description of “payer_address” cosmetic
    • “shield_check” reworded the description of “bundle_token” cosmetic
    • “shield_check” reworded the description of “payer_address” cosmetic
    • “stealth_read” reworded the description of “bundle_token” cosmetic
    • “stealth_read” reworded the description of “payer_address” cosmetic
    • “token_risk” reworded the description of “bundle_token” cosmetic
    • “token_risk” reworded the description of “payer_address” cosmetic
    • Tool “buy_pack_with_card” changed its title: TradeSignal: pack by card → Angel: 5,000 calls by card cosmetic
    • Tool “input_guard” changed its title: Prompt-injection scan for untrusted web, email and tool content → Remove hidden content from untrusted text and flag text aimed at the model cosmetic
    • Tool “stealth_read” changed its title: Read any URL as clean, injection-scrubbed Markdown for an LLM → Read any public page as clean Markdown, with hidden text removed cosmetic
  • 17 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 1898 → 2800 ▼ functional
    • New tool “exchange_route” functional
    • New tool “recommend” functional
    • New tool “shield_check” functional
  • 16 Nov 26 +1
    • Stability: 0.07 → fail ▼ security
    • A breaking change shipped without a version bump: still 1.3.0 ▼ security
    • Tool “buy_enterprise” was removed ▼ security
    • Tool “buy_subscription” was removed ▼ security
    • Tool “correlation_matrix” was removed ▼ security
    • Tool “funding_rates” was removed ▼ security
    • Tool “gas_window” was removed ▼ security
    • Tool “get_now” was removed ▼ security
    • Tool “get_registry” was removed ▼ security
    • Tool “get_sample_signal” was removed ▼ security
    • Tool “get_signal_card” was removed ▼ security
    • Tool “get_signals” was removed ▼ security
    • Tool “get_swap_route” was removed ▼ security
    • Tool “historical_gate” was removed ▼ security
    • Tool “liquidations” was removed ▼ security
    • Tool “orderflow_imbalance” was removed ▼ security
    • Tool “reconciliation” was removed ▼ security
    • Tool “regime” was removed ▼ security
    • Tool “registry_metrics” was removed ▼ security
    • Tool “request_enterprise_pilot” was removed ▼ security
    • Tool “send_wish” was removed ▼ security
    • Tool “sentiment_gate” was removed ▼ security
    • Tool “slippage” was removed ▼ security
    • Tool “validate_batch” was removed ▼ security
    • Tool “validate_setup” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “buy_pack_with_card” rewrote its description, which is the text the model reads security
    • Tool “buy_signal_pack” rewrote its description, which is the text the model reads security
    • Tool “input_guard” rewrote its description, which is the text the model reads security
    • Tool “preflight” rewrote its description, which is the text the model reads security
    • Tool “token_risk” rewrote its description, which is the text the model reads security
    • Schema quality: 219 → 271 ▼ functional
    • Destructive annotations: 0 → pass functional
    • New tool “stealth_read” functional
  • 15 Nov 26 +1
    • New tool “get_swap_route” functional
    • “preflight” added an optional parameter “partner_link” cosmetic
  • 14 Nov 26 −1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “input_guard” rewrote its description, which is the text the model reads security
    • Tool “input_guard_preview” rewrote its description, which is the text the model reads security
    • Tool “preflight” rewrote its description, which is the text the model reads security
    • Tool “registry_metrics” rewrote its description, which is the text the model reads security
    • Tool “token_risk” rewrote its description, which is the text the model reads security
    • Tool “gas_window” rewrote its description, which is the text the model reads security
    • Tool “correlation_matrix” rewrote its description, which is the text the model reads security
    • Tool “funding_rates” rewrote its description, which is the text the model reads security
    • Tool “get_signals” rewrote its description, which is the text the model reads security
    • Tool “historical_gate” rewrote its description, which is the text the model reads security
    • Tool “liquidations” rewrote its description, which is the text the model reads security
    • Tool “orderflow_imbalance” rewrote its description, which is the text the model reads security
    • Tool “reconciliation” rewrote its description, which is the text the model reads security
    • Tool “regime” rewrote its description, which is the text the model reads security
    • Tool “sentiment_gate” rewrote its description, which is the text the model reads security
    • Tool “slippage” rewrote its description, which is the text the model reads security
    • Tool “validate_batch” rewrote its description, which is the text the model reads security
    • Tool “validate_setup” rewrote its description, which is the text the model reads security
    • Schema quality: 3934 → 6078 ▼ functional
    • Schema quality: 3934 → 5831 ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Destructive annotations: pass → 0 functional
    • Server version: 1.2.0 → 1.3.0 functional
    • New tool “buy_pack_with_card” functional
    • New tool “get_now” functional
    • New tool “get_registry” functional
    • New tool “input_guard” functional
    • New tool “input_guard_preview” functional
    • New tool “preflight” functional
    • New tool “registry_metrics” functional
    • New tool “request_enterprise_pilot” functional
    • New tool “send_wish” functional
    • New tool “token_risk” functional
    • “preflight” reworded the description of “url” cosmetic
    • “correlation_matrix” reworded the description of “payer_address” cosmetic
    • “funding_rates” reworded the description of “payer_address” cosmetic
    • “gas_window” reworded the description of “payer_address” cosmetic
    • “get_signals” reworded the description of “payer_address” cosmetic
    • “historical_gate” reworded the description of “payer_address” cosmetic
    • “liquidations” reworded the description of “payer_address” cosmetic
    • “orderflow_imbalance” reworded the description of “payer_address” cosmetic
    • “reconciliation” reworded the description of “payer_address” cosmetic
    • “regime” reworded the description of “payer_address” cosmetic
    • “sentiment_gate” reworded the description of “payer_address” cosmetic
    • “slippage” reworded the description of “payer_address” cosmetic
    • “validate_batch” reworded the description of “payer_address” cosmetic
    • “validate_setup” reworded the description of “payer_address” cosmetic
    • Tool “correlation_matrix” changed its title: TradeSignal · correlation matrix → Correlation matrix for position sizing and hedging cosmetic
    • Tool “funding_rates” changed its title: TradeSignal · funding rates → Perpetual funding rates across Binance, Bybit and Hyperliquid cosmetic
    • Tool “gas_window” changed its title: TradeSignal · gas window → Gas check on Base or Ethereum: send now or wait cosmetic
    • Tool “get_signals” changed its title: TradeSignal: crypto trade setups → Crypto trade setups: entry, stop, targets now cosmetic
    • Tool “historical_gate” changed its title: TradeSignal: historical gate → Backtest the signal gate on 30 days for one pair cosmetic
    • Tool “input_guard” changed its title: TradeSignal · input guard (Klarsicht) → Prompt-injection scan for untrusted web, email and tool content cosmetic
    • Tool “input_guard_preview” changed its title: Angel: input guard preview (free) → Prompt-injection quick scan (free) cosmetic
    • Tool “liquidations” changed its title: TradeSignal · liquidations → Liquidation flow on OKX perpetuals: long vs short squeeze cosmetic
    • Tool “orderflow_imbalance” changed its title: TradeSignal · order-flow imbalance → Order-flow imbalance: buy vs sell pressure on a pair cosmetic
    • Tool “preflight” changed its title: TradeSignal · x402 preflight → Pre-purchase check for any shop, checkout link, payment page, API or x402 endpoint cosmetic
    • Tool “reconciliation” changed its title: TradeSignal · USDC reconciliation → Payment-received check: match expected USDC payments on Base cosmetic
    • Tool “regime” changed its title: TradeSignal · market regime → Market regime per pair: trending, ranging or volatile cosmetic
    • Tool “registry_metrics” changed its title: TradeSignal · registry verified metrics → Verified reliability stats for an x402 endpoint before relying on it cosmetic
    • Tool “sentiment_gate” changed its title: TradeSignal · sentiment gate → Risk-on / risk-off gate before opening a position cosmetic
    • Tool “slippage” changed its title: TradeSignal · slippage estimate → Slippage and price-impact estimate before a market order cosmetic
    • Tool “token_risk” changed its title: TradeSignal · token risk → Honeypot and rug-pull check for an ERC-20 before swap or approve cosmetic
    • Tool “validate_batch” changed its title: TradeSignal · validate batch → Batch pre-trade validation of up to 10 crypto setups cosmetic
    • Tool “validate_setup” changed its title: TradeSignal: validate a setup → Pre-trade check: validate a crypto setup before ordering cosmetic
  • 13 Nov 26 61

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://angel.oroboros-design.com/agenten/signal/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.oroboros-design.com CN=YR2,O=Let's Encrypt,C=US 28 Oct 2026 26 Jan 2027 RSA 2048 SHA256-RSA 5c407b368cf93bd9f2f03db9f58a77f6c9f
SANs: *.oroboros-design.com, oroboros-design.com
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of angel.oroboros-design.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
oroboros-design.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://angel.oroboros-design.com/agenten/signal/mcp Verified 200
http (plaintext) http://angel.oroboros-design.com/agenten/signal/mcp HTTPS enforced 308 https://angel.oroboros-design.com/agenten/signal/mcp
MCP tools · 7 exposed · ~2,072 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
buy_pack_with_card ~118

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.

NameTypeReqDescription
callsinteger––
emailstring–Where the key is sent (optional; Stripe asks otherwise).

No output schema declared.

No examples provided.

input_guard ~318

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).

NameTypeReqDescription
bundle_tokenstring–Your key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too.
payer_addressstring–Wallet you pay from (optional; the x402 price is the same for every address).
payment_txstring–Hash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature.
textstring–the content to check (send text or url)
urlstring–a public https page to fetch once and check (256 KB)

No output schema declared.

No examples provided.

input_guard_preview ~105

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.

NameTypeReqDescription
textstring––
urlstring––

No output schema declared.

No examples provided.

preflight ~555

Before an agent buys, pays or hires: send url (shop, checkout, payment link, API or x402 endpoint), need (what to buy in plain words; Angel takes the pick from the open sea at mareliberum.dev and checks it) or agent (mare:… resident: its trust score). One unpaid request each: TLS, domain age, look-alikes, redirects, payment provider, card fields, text aimed at agents and, for x402, USDC contract, payTo and price traps. Verdict pay, caution or do_not_pay, risk_score, reasons. 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: input-guard on the page text you will act on (the result's next field has the exact call).

NameTypeReqDescription
agentstring–instead of a url: a resident of the open sea (mareliberum.dev) you want to pay or hire; Angel returns its trust score 0-100 from its work, notes, seals and own endpoint
budgetnumber–with need: highest price
bundle_tokenstring–Your key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too.
currencystring–with need: currency of the budget
max_price_usdnumber––
methodstring––
needstring–instead of a url: what your user wants to buy, in plain words (sizes, budget, place included), e.g. "trail running shoes size 44 under 150 EUR, ships to Germany". Angel takes the pick from the open s…
partner_linkboolean–default true: on verdict pay for a shop with an affiliate program, the answer adds partner_link (same merchant, disclosed: Angel may earn a commission, merchant sets the price); false omits it
payer_addressstring–Wallet you pay from (optional; the x402 price is the same for every address).
payment_txstring–Hash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature.
regionstring–with need: country code or name
urlstring–the shop, checkout or payment link, API or x402 endpoint to check (public https domain, port 443). Send url or need.

No output schema declared.

No examples provided.

shield_check ~406

Spend firewall for AI agents with a wallet or card, called before every payment: checks your rules (per-payment cap, daily budget reserved atomically, allow/block lists, chains, tokens, approval threshold, new merchants, kill switch), the merchant or checkout URL (preflight), the text that triggered the payment (input-guard: hidden instructions) and non-USDC tokens (token-risk). Returns allow, hold or block with reasons; with a stored policy the amount is reserved until confirm or release. 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: pay, then POST /shield/confirm with the reservation_id (or /shield/release if you did not pay) (the result's next field has the exact call).

NameTypeReqDescription
bundle_tokenstring–Your key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too.
hold_secondsinteger–how long an allowed amount stays reserved (default 900)
idempotency_keystring–same key = same reservation, never reserved twice
payer_addressstring–Wallet you pay from (optional; the x402 price is the same for every address).
paymentobjectyes–
payment_txstring–Hash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature.
policyobject–inline rules (stateless); for a daily budget and remembered merchants store them with POST /shield/policy and send policy_id
policy_idstring–a stored policy (needs your key as X-Bundle-Token or bundle_token)
triggerobject–the instruction, message or page that made the agent want to pay

No output schema declared.

No examples provided.

stealth_read ~275

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).

NameTypeReqDescription
bundle_tokenstring–Your key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too.
payer_addressstring–Wallet you pay from (optional; the x402 price is the same for every address).
payment_txstring–Hash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature.
urlstringyesthe public https page to read (1 MB, 10 s)

No output schema declared.

No examples provided.

token_risk ~295

Honeypot and rug-pull check for an ERC-20 on Base or Ethereum before a swap, approval or signature, read straight from the contract: upgradeable proxy (EIP-1967, beacon, clone), owner powers in the bytecode (mint, pause, blacklist, fee or max-tx setters, trading switch, burn from any address), owner renounced or active and the owner's share of supply; known issuers labeled. Risk low, medium or high with reasons. Signals, not investment advice. 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 or signs on the site that offers this token (the result's next field has the exact call).

NameTypeReqDescription
bundle_tokenstring–Your key instead of paying per call: free (500 calls, POST /key) or bought by card. The connection header X-Bundle-Token works too.
chainstring––
payer_addressstring–Wallet you pay from (optional; the x402 price is the same for every address).
payment_txstring–Hash of a USDC transfer on Base to payTo (≥ the price, ≤ 72 h old) instead of an x402 signature.
tokenstringyes–

No output schema declared.

No examples provided.

Install

How do I install the Agent safety checks: prompt-injection scan, honeypot… MCP server?

Agent safety checks: prompt-injection scan, honeypot… is a hosted endpoint at https://angel.oroboros-design.com/agenten/signal/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · angel.oroboros-design.com

# add to Claude Code
claude mcp add --transport http com-oroboros-design-angel-tradesignal 'https://angel.oroboros-design.com/agenten/signal/mcp'
Common questions

What is the Agent safety checks: prompt-injection scan, honeypot… MCP server?

Agent safety checks: prompt-injection scan, honeypot… is an MCP server listed in the public MCP registry as com.oroboros-design.angel/tradesignal. Checks before an agent acts: prompt-injection scan, honeypot check, x402 preflight. 3 free calls. This page covers its hosted endpoint (https://angel.oroboros-design.com/agenten/signal/mcp).

Is the Agent safety checks: prompt-injection scan, honeypot… MCP server safe to use?

Agent safety checks: prompt-injection scan, honeypot… scores 61 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agent safety checks: prompt-injection scan, honeypot… MCP server expose?

Agent safety checks: prompt-injection scan, honeypot… exposes 7 tools: stealth_read, input_guard, input_guard_preview, preflight, token_risk, and 2 more. Their descriptions and schemas cost roughly 2,072 tokens of context every time the server is loaded.

Does the Agent safety checks: prompt-injection scan, honeypot… MCP server require authentication?

No. We connected to Agent safety checks: prompt-injection scan, honeypot… without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent safety checks: prompt-injection scan, honeypot… MCP server still maintained?

Agent safety checks: prompt-injection scan, honeypot… is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Agent safety checks: prompt-injection scan, honeypot… MCP server?

VerifyMCP ran 12 checks on Agent safety checks: prompt-injection scan, honeypot…, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Agent safety checks: prompt-injection scan, honeypot…: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.