EdgeScreen x402 Security Screening MCP server
dev.workers.asostudio.aso-x402-screen/edgescreenaso-x402-screen.asostudio.workers.devstreamable-httpv2.2.0Scanned
Free MCP hooks + x402 security scans; MCP manifest and SKILL.md audits cost $0.003 Base USDC.
17 tools: 9 change things and 8 only read.
- Reads private data · 2
- Reads text others write · 10
- Can send data out · 2
- 7 findings
Tools listed without sign-in. Remote posture
With Anlyon
9 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the EdgeScreen x402 Security Screening MCP server can do
The EdgeScreen x402 Security Screening MCP server is published by aso-x402-screen.asostudio.workers.dev, a domain the MCP Registry verified. It has 17 tools. It can create or change data (9 tools: verify_audit_receipt, screen_mcp_manifest, screen_batch, screen_address and 5 more), but cannot delete data. 8 tools only read.
2 tools read private data (preview_secret_lint and screen_diff); 10 tools bring in text other people can write (screen_x402_challenge, screen_mcp_manifest, screen_batch and 7 more); 2 tools can send data out of your system (screen_batch and screen_url). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 7 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 5 times since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 2.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
17 tools
Changes things 9Claude Code: ask
screen_addressOFAC SDN crypto wallet sanctions screening for EVM, Bitcoin, and TRON addresses.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it OFAC SDN crypto wallet sanctions screening for EVM, Bitcoin, and TRON addresses. Requires $0.002 (2000 atomic) Base USDC on eip155:8453 via @x402/mcp _meta["x402/payment"] or PAYMENT-SIGNATURE header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
screen_batchRun a multi-item single-payment pipeline for up to 25 total items: crypto addresses, domains/handles, prompts, URLs, text snippets and git diffs.Reads text others writeCan send data out3 findings
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "...rivate/metadata IPs, dangerous schemes, credentials, IDN homoglyphs, and open redirects."
- Info
The input schema at properties.urls.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.urls.description: "...mal IP encodings), non-HTTP(S) schemes, credentials, punycode homoglyphs, and open redirect..."
- Warn
The server marks "screen_batch" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Run a multi-item single-payment pipeline for up to 25 total items: crypto addresses, domains/handles, prompts, URLs, text snippets and git diffs. Returns combined deterministic findings after one $0.005 (5000 atomic) Base USDC x402 payment.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
screen_domainScreen one hostname for DNS/IDN/punycode/TLS infrastructure naming risks: Unicode UTS #39 confusables and brand typosquatting.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Screen one hostname for DNS/IDN/punycode/TLS infrastructure naming risks: Unicode UTS #39 confusables and brand typosquatting. Static hostname analysis only; no DNS resolution or TLS certificate probe. Returns lookalike findings. Requires $0.002 Base USDC via x402. Use screen_impersonation for the 61-brand DeFi/AI handle corpus.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
screen_impersonationScreen a handle or lookalike against the 61-brand DeFi/AI corpus: Unicode homographs, Levenshtein-1 typosquats, rn/m swaps and fake support/airdrop lures.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Screen a handle or lookalike against the 61-brand DeFi/AI corpus: Unicode homographs, Levenshtein-1 typosquats, rn/m swaps and fake support/airdrop lures. Returns risk_score, verdict, signals and canonical_comparison. Requires $0.002 Base USDC via x402. Use screen_domain for single-hostname infrastructure naming checks.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
screen_mcp_manifestScan MCP manifests and SKILL.md for poisoning, hidden Unicode, cross-tool overrides, mutable executables and credential exfiltration.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...tool overrides, mutable executables and credential exfiltration. Returns findings, remedia..."
Description, as the server wrote it Scan MCP manifests and SKILL.md for poisoning, hidden Unicode, cross-tool overrides, mutable executables and credential exfiltration. Returns findings, remediated output, SHA-256 pin and Ed25519 audit receipt. Requires $0.003 (3000 atomic) Base USDC via x402.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
screen_promptDeterministic prompt-injection, MCP tool-poisoning, Unicode tag smuggling, and secret exfiltration firewall.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Deterministic prompt-injection, MCP tool-poisoning, Unicode tag smuggling, and secret exfiltration firewall. Requires $0.002 (2000 atomic) Base USDC on eip155:8453 via @x402/mcp _meta["x402/payment"] or PAYMENT-SIGNATURE header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
screen_secretDeterministic pre-publish secret leak detector & redactor for PRs, logs, and webhooks (OpenAI, Anthropic, AWS, GitHub, Stripe, Slack, Google keys, PEM & 64-hex private keys, JWTs, …Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Deterministic pre-publish secret leak detector & redactor for PRs, logs, and webhooks (OpenAI, Anthropic, AWS, GitHub, Stripe, Slack, Google keys, PEM & 64-hex private keys, JWTs, Bearer tokens -> safe, riskScore, masked findings, redactedText). Requires $0.002 (2000 atomic) Base USDC on eip155:8453 via @x402/mcp _meta["x402/payment"] or PAYMENT-SIGNATURE header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
screen_urlDeterministic pre-fetch URL & SSRF firewall detecting loopback, RFC1918, CGNAT, IPv6 mapped/unique-local/link-local, AWS/GCP/Azure/Alibaba metadata endpoints, hex/octal/decimal IP …Reads text others writeCan send data out3 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...encodings, dangerous schemes, embedded credentials, punycode homoglyphs, and open redirect..."
- Info
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "...rivate/metadata IPs, dangerous schemes, credentials, IDN homoglyphs, and open redirects."
- Info
The input schema at properties.urls.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.urls.description: "...mal IP encodings), non-HTTP(S) schemes, credentials, punycode homoglyphs, and open redirect..."
Description, as the server wrote it Deterministic pre-fetch URL & SSRF firewall detecting loopback, RFC1918, CGNAT, IPv6 mapped/unique-local/link-local, AWS/GCP/Azure/Alibaba metadata endpoints, hex/octal/decimal IP encodings, dangerous schemes, embedded credentials, punycode homoglyphs, and open redirects. Requires $0.002 (2000 atomic) Base USDC on eip155:8453 via @x402/mcp _meta["x402/payment"] or PAYMENT-SIGNATURE header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
verify_audit_receiptVerify an EdgeScreen Ed25519 signed audit receipt or PAYMENT-REFERRAL-RECEIPT for $0.00, without a wallet.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Verify an EdgeScreen Ed25519 signed audit receipt or PAYMENT-REFERRAL-RECEIPT for $0.00, without a wallet. Returns valid, receiptType, signerPublicKey, payloadSummary and verifiedAt using trusted server public keys. Unknown keys or tampering return valid=false; no payment or payout confirmation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 8Show 8 read-only tools
get_service_healthInspect EdgeScreen health, version, active OFAC snapshot size, and x402 pricing (free, no payment required).No findings
Why it is in this group
- The name "get_service_health" says "get": a word for reading.
Description, as the server wrote it Inspect EdgeScreen health, version, active OFAC snapshot size, and x402 pricing (free, no payment required).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_x402_quickstartFREE ($0.00, zero wallet required): Return turnkey copy-paste @x402/mcp and @x402/fetch setup snippets (Cursor, Claude Code, TypeScript viem, Python) plus the live Base USDC pricin…No findings
Why it is in this group
- The name "get_x402_quickstart" says "get": a word for reading.
Description, as the server wrote it FREE ($0.00, zero wallet required): Return turnkey copy-paste @x402/mcp and @x402/fetch setup snippets (Cursor, Claude Code, TypeScript viem, Python) plus the live Base USDC pricing ladder so an agent can wire x402 payments in 30 seconds.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
preview_mcp_manifestFree, zero-wallet deterministic MCP manifest or SKILL.md quickcheck: risk, severity, findingCount and manifestPinSha256.No findings
Why it is in this group
- The name "preview_mcp_manifest" says "preview": a word for reading.
Description, as the server wrote it Free, zero-wallet deterministic MCP manifest or SKILL.md quickcheck: risk, severity, findingCount and manifestPinSha256. No external lookups or payload storage. Full findings, remediation and signed receipt: screen_mcp_manifest ($0.003 Base USDC).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
preview_punycode_decodeFREE ($0.00, zero wallet required): Decode IDN xn-- punycode and inspect mixed Unicode scripts on 1 domain or @handle (0 brand-corpus lookup).No findings
Why it is in this group
- The name "preview_punycode_decode" says "preview": a word for reading.
Description, as the server wrote it FREE ($0.00, zero wallet required): Decode IDN xn-- punycode and inspect mixed Unicode scripts on 1 domain or @handle (0 brand-corpus lookup). Returns upgrade_hint to paid screen_impersonation ($0.002 Base USDC) for 61-brand Levenshtein/typosquat/subdomain spoofing detection.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
preview_secret_lintFREE ($0.00, zero wallet required): Lint up to 500 chars for obvious high-risk secret prefixes (AKIA, sk_live_, sk-proj-/sk-ant-, -----BEGIN, ghp_/github_pat_, xoxb-) without full …Reads private dataNo findings
Why it is in this group
- The name "preview_secret_lint" says "preview": a word for reading.
What it can reach
- private-dataThe name "preview_secret_lint" says "preview" and "secret": it reads secrets.
- private-dataThe description's first sentence says "secret": it reads secrets.
Description, as the server wrote it FREE ($0.00, zero wallet required): Lint up to 500 chars for obvious high-risk secret prefixes (AKIA, sk_live_, sk-proj-/sk-ant-, -----BEGIN, ghp_/github_pat_, xoxb-) without full entropy, offsets, or surgical redaction. Returns upgrade_hint to paid screen_secret / screen_diff ($0.002-$0.005 Base USDC).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
preview_x402_challengeFree zero-wallet x402 challenge quickcheck: verdict, top_finding and upgrade_hint.No findings
Why it is in this group
- The name "preview_x402_challenge" says "preview": a word for reading.
Description, as the server wrote it Free zero-wallet x402 challenge quickcheck: verdict, top_finding and upgrade_hint. Inspects supplied JSON or headers only; no DNS, chain lookups or payload logging.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
screen_diffDeterministic pre-merge git diff & PR patch auditor detecting leaked secrets in added lines, destructive shell/SQL commands, GitHub Actions/CI workflow injection, malicious package…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "screen_diff" says "diff": a word for reading.
What it can reach
- private-dataThe description's first sentence says "secret": it reads secrets.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Deterministic pre-merge git diff & PR patch auditor detecting leaked secrets in added lines, destructive shell/SQL commands, GitHub Actions/CI workflow injection, malicious package lifecycle hooks, SSRF & cloud metadata endpoints, auth/TLS verification bypasses, Trojan Source BiDi Unicode smuggling, and corrupt hunk counts. Requires $0.002 (2000 atomic) Base USDC on eip155:8453 via @x402/mcp _meta["x402/payment"] or PAYMENT-SIGNATURE header.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
screen_x402_challengeInspect x402 v1/v2 challenges for spoofed stablecoins, decimal inflation, price mismatch, unsafe recipients and SSRF URLs.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "inspect": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Inspect x402 v1/v2 challenges for spoofed stablecoins, decimal inflation, price mismatch, unsafe recipients and SSRF URLs. Pinned mainnet tokens on Base, Ethereum, Arbitrum, Optimism, Polygon and Solana. Returns all findings, nominal USD estimate and Ed25519 receipt. $0.002 (2000 atomic) Base USDC.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
40 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write10
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__edgescreen__screen_batch",
"mcp__edgescreen__screen_url"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:21 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 9
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 9 tools that change things (9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://aso-x402-screen.asostudio.workers.dev/mcp: tools/list returned 17 tools to an anonymous client, including verify_audit_receipt (write), screen_mcp_manifest (write), screen_batch (write), screen_address (write), screen_domain (write) and 4 more
Posture changes
- Nov 21, 2026
- Tools that change things, listed without credentials: 6 to 9
Findings
Matches of fixed checks, with the text they matched.
- Warnscreen_batch
The server marks "screen_batch" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "run": a word for a change.
The description mentions "credential".
What this check looks forMatched text
description: "...tool overrides, mutable executables and credential exfiltration. Returns findings, remedia..."
- Infoscreen_batch
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "...rivate/metadata IPs, dangerous schemes, credentials, IDN homoglyphs, and open redirects."
- Infoscreen_batch
The input schema at properties.urls.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.urls.description: "...mal IP encodings), non-HTTP(S) schemes, credentials, punycode homoglyphs, and open redirect..."
- Infoscreen_url
The description mentions "credentials".
What this check looks forMatched text
description: "...encodings, dangerous schemes, embedded credentials, punycode homoglyphs, and open redirect..."
- Infoscreen_url
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "...rivate/metadata IPs, dangerous schemes, credentials, IDN homoglyphs, and open redirects."
Show 1 more findingShow fewer
- Infoscreen_url
The input schema at properties.urls.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.urls.description: "...mal IP encodings), non-HTTP(S) schemes, credentials, punycode homoglyphs, and open redirect..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 6 -> 9.View diff
- Tools that change things, listed without credentials: 6 to 9
Tools8 added, 7 removed, 8 changed.+8 added−7 removed~8 changedView diff
- Added:get_service_healthOnly reads
- Added:get_x402_quickstartOnly reads
- Added:preview_mcp_manifestOnly reads
- Added:preview_punycode_decodeOnly reads
- Added:preview_secret_lintOnly reads
- Added:preview_x402_challengeOnly reads
- Added:screen_x402_challengeOnly reads
- Added:verify_audit_receiptChanges things
- Removed:edgescreen_x402_quickstart
- Removed:free_mcp_manifest_quickcheck
- Removed:free_punycode_decode
- Removed:free_secret_prefix_lint
- Removed:free_x402_challenge_quickcheck
- Removed:health_check
- Removed:screen_x402_payment_challenge
- Changed:screen_addressChanges thingsannotations
- Changed:screen_batchChanges thingsdescriptionannotations
- Changed:screen_diffOnly readsannotations
- Changed:screen_domainChanges thingsdescriptionannotations
- Changed:screen_impersonationChanges thingsdescriptionannotations
- Changed:screen_promptChanges thingsannotations
- Changed:screen_secretChanges thingsannotations
- Changed:screen_urlChanges thingsannotations
Tools2 added.+2 addedView diff
- Added:free_x402_challenge_quickcheckChanges things
- Added:screen_x402_payment_challengeCan't be undone
Tools2 added.+2 addedView diff
- Added:free_mcp_manifest_quickcheckChanges things
- Added:screen_mcp_manifestChanges things
Tools3 added, 8 changed.+3 added~8 changedView diff
- Added:edgescreen_x402_quickstartChanges things
- Added:free_punycode_decodeChanges things
- Added:free_secret_prefix_lintChanges things
- Changed:screen_addressChanges thingsdescription
- Changed:screen_batchChanges thingsdescription
- Changed:screen_diffOnly readsdescription
- Changed:screen_domainChanges thingsdescription
- Changed:screen_impersonationChanges thingsdescription
- Changed:screen_promptChanges thingsdescription
- Changed:screen_secretChanges thingsdescription
- Changed:screen_urlChanges thingsdescription
Tools2 added, 3 changed.+2 added~3 changedView diff
- Added:screen_diffOnly reads
- Added:screen_impersonationChanges things
- Changed:screen_addressChanges thingsinputSchema
- Changed:screen_batchChanges thingsdescriptioninputSchema
- Changed:screen_promptChanges thingsinputSchema
Install
Pinned to version 2.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http edgescreen https://aso-x402-screen.asostudio.workers.dev/mcpclaude mcp add --transport http edgescreen https://aso-x402-screen.asostudio.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__edgescreen__preview_x402_challenge",
"mcp__edgescreen__screen_x402_challenge",
"mcp__edgescreen__preview_mcp_manifest",
"mcp__edgescreen__preview_punycode_decode",
"mcp__edgescreen__preview_secret_lint",
"mcp__edgescreen__get_x402_quickstart",
"mcp__edgescreen__screen_diff",
"mcp__edgescreen__get_service_health"
],
"ask": [
"mcp__edgescreen__verify_audit_receipt",
"mcp__edgescreen__screen_mcp_manifest",
"mcp__edgescreen__screen_batch",
"mcp__edgescreen__screen_address",
"mcp__edgescreen__screen_domain",
"mcp__edgescreen__screen_impersonation",
"mcp__edgescreen__screen_prompt",
"mcp__edgescreen__screen_url",
"mcp__edgescreen__screen_secret"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as edgescreen. Review it before you use it.
Capability tags behind 11 rules
- mcp__edgescreen__screen_x402_challenge untrusted-input
- mcp__edgescreen__screen_mcp_manifest untrusted-input
- mcp__edgescreen__preview_secret_lint private-data
- mcp__edgescreen__screen_batch untrusted-input, outbound
- mcp__edgescreen__screen_address untrusted-input
- mcp__edgescreen__screen_domain untrusted-input
- mcp__edgescreen__screen_impersonation untrusted-input
- mcp__edgescreen__screen_prompt untrusted-input
- mcp__edgescreen__screen_url untrusted-input, outbound
- mcp__edgescreen__screen_secret untrusted-input
- mcp__edgescreen__screen_diff private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.workers.asostudio.aso-x402-screen/edgescreen/verify?hash=67c8797f45dcc831a390e863898feb560061ba980a7216577e5164ce714357b5" | jq -e '.changed == false'Pinned hash 67c8797f45dc, from Nov 15, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.workers.asostudio.aso-x402-screen/edgescreen/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.workers.asostudio.aso-x402-screen/edgescreen)Source: MCP Registry. Synced Nov 15, 2026, 23:17 UTC.
EdgeScreen x402 Security Screening MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the EdgeScreen x402 Security Screening MCP server safe?
- No scan can promise that. What its definitions show: 17 tools, 9 of which can change, send or delete something, and 7 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the EdgeScreen x402 Security Screening MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the EdgeScreen x402 Security Screening MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the EdgeScreen x402 Security Screening MCP server have?
- 17 tools: 9 write, 8 read. verify_audit_receipt, screen_mcp_manifest, screen_batch, screen_address, screen_domain, screen_impersonation, screen_prompt, screen_url and 9 more.
Does the EdgeScreen x402 Security Screening MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the EdgeScreen x402 Security Screening MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): screen_batch and screen_url.
Has the EdgeScreen x402 Security Screening MCP server changed its tools?
- Yes, 5 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.