io.github.normancomics/phantomoperator
io.github.normancomics/phantomoperatornormancomicsstreamable-httpv1.1.0Scanned
Authorized privacy and exposure checks for people and agents; USDC on Base via x402.
11 tools: 9 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
Anlyon alternative
9 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →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.
11 tools
Changes things 9Claude Code: ask
breach-checkKeyless email breach intelligence check (XposedOrNot + HIBP) and optional k-anonymity SHA-1 password check.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.
Description, as the server wrote it Keyless email breach intelligence check (XposedOrNot + HIBP) and optional k-anonymity SHA-1 password check. Costs $0.10 USDC on Base via x402.
cypherpunk-redteam-dossierComprehensive 6-operator Cypherpunk Red-Team Dossier (Web Metadata + OSINT Threat Scan + Breach Check + OPSEC Score + EVM Wallet Hygiene + $XMR Monero Audit + MMR Attestation).Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Comprehensive 6-operator Cypherpunk Red-Team Dossier (Web Metadata + OSINT Threat Scan + Breach Check + OPSEC Score + EVM Wallet Hygiene + $XMR Monero Audit + MMR Attestation). Costs $5.00 USDC on Base via x402.
data-removalMatches an authorized data-broker listing with supported removal paths and drafts a reviewable CCPA/GDPR-style request.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.
Description, as the server wrote it Matches an authorized data-broker listing with supported removal paths and drafts a reviewable CCPA/GDPR-style request. Does not submit a removal without explicit authorization. Costs $0.50 USDC on Base via x402.
full-privacy-sweepCombines authorized public-exposure, privacy scoring, and removal guidance into one structured report.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.
Description, as the server wrote it Combines authorized public-exposure, privacy scoring, and removal guidance into one structured report. Costs $1.00 USDC on Base via x402.
monero-opsec-auditCryptonote Base58 + Keccak-256 Monero ($XMR) address/subaddress decoder (Spend Key, View Key, checksum), live Monero RingCT telemetry, EVM <-> $XMR swap correlation check, and MMR …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Cryptonote Base58 + Keccak-256 Monero ($XMR) address/subaddress decoder (Spend Key, View Key, checksum), live Monero RingCT telemetry, EVM <-> $XMR swap correlation check, and MMR proof. Costs $0.25 USDC on Base via x402.
opsec-scoreMulti-vector OPSEC exposure score (0–100, grade A–F) across public web search, data brokers, paste sites, and social profiles.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.
Description, as the server wrote it Multi-vector OPSEC exposure score (0–100, grade A–F) across public web search, data brokers, paste sites, and social profiles. Costs $0.25 USDC on Base via x402.
sovereign-opsec-retainerEnterprise & DAO Zero-Trace OPSEC Retainer Package with $XMR Atomic-Swap Treasury Isolation Blueprint and Statutory Takedown Binder.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Enterprise & DAO Zero-Trace OPSEC Retainer Package with $XMR Atomic-Swap Treasury Isolation Blueprint and Statutory Takedown Binder. Costs $25.00 USDC on Base via x402.
spam-caller-removalPrepare official caller-ID unlisting and spam-label dispute steps for an authorized phone number.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a destination (input.phoneNumber): what the tool writes goes there.
Description, as the server wrote it Prepare official caller-ID unlisting and spam-label dispute steps for an authorized phone number. Does not submit requests. Costs $0.10 USDC on Base via x402.
wallet-opsec-auditOn-chain Base/EVM wallet deanonymization & hygiene audit + deterministic $XMR settlement subaddress.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.
Description, as the server wrote it On-chain Base/EVM wallet deanonymization & hygiene audit + deterministic $XMR settlement subaddress. Costs $0.50 USDC on Base via x402.
Only reads 2Show 2 read-only tools
metadata-auditFetch any HTTP/HTTPS URL and extract metadata leaks (HTTP headers, meta tags, HTML comments, third-party trackers).Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch any HTTP/HTTPS URL and extract metadata leaks (HTTP headers, meta tags, HTML comments, third-party trackers). Costs $0.05 USDC on Base via x402.
threat-scanSearch the public web for mentions of a person's name containing exposed PII (phone numbers, emails, SSNs, home addresses).Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "email": it reads mail.
- untrusted-inputThe description's first sentence says "search" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it Search the public web for mentions of a person's name containing exposed PII (phone numbers, emails, SSNs, home addresses). Costs $0.10 USDC on Base via x402.
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.
8 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__phantomoperator__threat-scan"
]
}
}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 Oct 29, 2026, 21:20 UTC, unchanged since Oct 29, 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://freysaai.freysa.dev/mcp: tools/list returned 11 tools to an anonymous client, including breach-check (write), opsec-score (write), monero-opsec-audit (write), data-removal (write), wallet-opsec-audit (write) and 4 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http phantomoperator https://freysaai.freysa.dev/mcpclaude mcp add --transport http phantomoperator https://freysaai.freysa.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__phantomoperator__threat-scan"
],
"ask": [
"mcp__phantomoperator__metadata-audit",
"mcp__phantomoperator__breach-check",
"mcp__phantomoperator__opsec-score",
"mcp__phantomoperator__monero-opsec-audit",
"mcp__phantomoperator__data-removal",
"mcp__phantomoperator__wallet-opsec-audit",
"mcp__phantomoperator__full-privacy-sweep",
"mcp__phantomoperator__cypherpunk-redteam-dossier",
"mcp__phantomoperator__sovereign-opsec-retainer",
"mcp__phantomoperator__spam-caller-removal"
],
"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 phantomoperator. Review it before you use it.
Capability tags behind 5 rules
- mcp__phantomoperator__metadata-audit untrusted-input, outbound
- mcp__phantomoperator__threat-scan private-data, untrusted-input
- mcp__phantomoperator__cypherpunk-redteam-dossier outbound
- mcp__phantomoperator__sovereign-opsec-retainer outbound
- mcp__phantomoperator__spam-caller-removal outbound
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://anlyon.dev/api/v1/servers/io.github.normancomics/phantomoperator/verify?hash=6eabc4d8aeb2a31bba50fbc076338d4048a1468fbfda8429f5996a692f79dd1f" | jq -e '.changed == false'Pinned hash 6eabc4d8aeb2, from Oct 29, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://anlyon.dev/servers/io.github.normancomics/phantomoperator/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://anlyon.dev/servers/io.github.normancomics/phantomoperator)Source: MCP Registry · repository. Synced Oct 29, 2026, 20:17 UTC.