screening MCP server
com.compliapi/screeningcompliapi.comstreamable-httpv1.0.0Scanned
OFAC and global sanctions screening: crypto addresses, emails, websites, IDs, countries, VPN, geo
11 tools: 11 change things.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
11 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 screening MCP server can do
The screening MCP server is published by compliapi.com, a domain the MCP Registry verified. It has 11 tools. It can create or change data (11 tools: screen_crypto_address, screen_email, screen_website, screen_government_id and 7 more), but cannot delete data. None of its tools only reads.
3 tools bring in text other people can write (screen_pep, detect_vpn and geolocate_ip).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 1.0.0.
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.
11 tools
Changes things 11Claude Code: ask
detect_vpnDetect whether an IP address is using a VPN.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 Detect whether an IP address is using a VPN.
Annotations the server declares
- title: Detect VPN usage
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
geolocate_ipGeolocate an IP address and flag whether it is in a sanctioned country.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 Geolocate an IP address and flag whether it is in a sanctioned country.
Annotations the server declares
- title: Geolocate an IP address
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
screen_aircraftScreen an aircraft by registration (tail number, e.g.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 Screen an aircraft by registration (tail number, e.g. EP-GOL), manufacturer's serial number or Mode S transponder code (OFAC SDN publishes these). Exact match, ignoring punctuation and case; serial numbers under six characters are not indexed. Each match carries the aircraft model. `lists`: optional comma-separated list slugs.
Annotations the server declares
- title: Screen an aircraft
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
screen_countryCheck whether a country or region carries sanctions designations (OFAC-curated today).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 Check whether a country or region carries sanctions designations (OFAC-curated today). `lists`: optional comma-separated list slugs.
Annotations the server declares
- title: Check country sanctions
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
screen_crypto_addressScreen a crypto address on any chain (or an ENS name, e.g.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 Screen a crypto address on any chain (or an ENS name, e.g. vitalik.eth) across the enabled sanctions and crime lists. `lists`: optional comma-separated list slugs.
Annotations the server declares
- title: Screen a crypto address
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
screen_emailScreen an email address across the enabled sanctions and crime lists.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 Screen an email address across the enabled sanctions and crime lists. `lists`: optional comma-separated list slugs.
Annotations the server declares
- title: Screen an email address
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
screen_government_idScreen a government-issued ID (passport, tax ID, …) across the enabled lists (fuzzy matching).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 Screen a government-issued ID (passport, tax ID, …) across the enabled lists (fuzzy matching). `lists`: optional comma-separated list slugs.
Annotations the server declares
- title: Screen a government ID
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
screen_nameScreen a person, company, vessel or aircraft name against the primary names and aliases on the sanctions lists with name coverage (OFAC SDN and Consolidated, UN Security Council, E…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 Screen a person, company, vessel or aircraft name against the primary names and aliases on the sanctions lists with name coverage (OFAC SDN and Consolidated, UN Security Council, EU, UK, Swiss SECO, Canada, Australia DFAT, French Trésor, Japan MOF). Fuzzy, order- and accent-insensitive; each match has a 0-100 `score` and `reasons`. `type` restricts to one party type. `birth_date` (YYYY, YYYY-MM or YYYY-MM-DD) excludes listed individuals whose birth dates all disagree; `country` (ISO code or name) ranks matches by listed nationality/address/flag; `id_number` (passport, national ID or registration number) ranks a party listing that document first. `threshold`: minimum score (50-100, default 85). `lists`: optional comma-separated list slugs.
Annotations the server declares
- title: Screen a name
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
screen_pepScreen a person's name against the OpenSanctions PEP (politically exposed persons) dataset.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 person's name against the OpenSanctions PEP (politically exposed persons) dataset. Returns scored candidates; `pep` is true when any candidate clears the 0.7 match threshold. `birth_date` (YYYY-MM-DD, or partial) and `country` (name or ISO code) sharpen matching.
Annotations the server declares
- title: Screen for politically exposed persons
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
screen_vesselScreen a ship by IMO number (7 digits, with or without the "IMO" prefix) or MMSI (9 digits) across the lists that publish ship identifiers (OFAC SDN, UK, Swiss SECO, Canada, Austra…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 Screen a ship by IMO number (7 digits, with or without the "IMO" prefix) or MMSI (9 digits) across the lists that publish ship identifiers (OFAC SDN, UK, Swiss SECO, Canada, Australia, French Trésor). Exact match, ignoring each list's formatting; each match names the listed vessel. `lists`: optional comma-separated list slugs.
Annotations the server declares
- title: Screen a vessel
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
screen_websiteScreen a website or domain across the enabled sanctions and crime lists.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 Screen a website or domain across the enabled sanctions and crime lists. `lists`: optional comma-separated list slugs.
Annotations the server declares
- title: Screen a website or domain
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or 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 20, 2026, 18:36 UTC, unchanged since Nov 13, 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
- 11
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.compliapi.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://api.compliapi.com/
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 11 tools that change things (11 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.compliapi.com/mcp: tools/list returned 11 tools to an anonymous client, including screen_crypto_address (write), screen_email (write), screen_website (write), screen_government_id (write), screen_vessel (write) and 6 more
Posture changes
- Nov 13, 2026
- Tools that change things, listed without credentials: 8 to 11
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.
PostureRemote posture changed. Tools that change things, listed without credentials: 8 -> 11.View diff
- Tools that change things, listed without credentials: 8 to 11
Tools3 added.+3 addedView diff
- Added:screen_aircraftChanges things
- Added:screen_nameChanges things
- Added:screen_vesselChanges things
Tools8 changed.~8 changedView diff
- Changed:detect_vpnChanges thingsannotations
- Changed:geolocate_ipChanges thingsannotations
- Changed:screen_countryChanges thingsannotations
- Changed:screen_crypto_addressChanges thingsannotations
- Changed:screen_emailChanges thingsannotations
- Changed:screen_government_idChanges thingsannotations
- Changed:screen_pepChanges thingsannotations
- Changed:screen_websiteChanges thingsannotations
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http screening https://api.compliapi.com/mcpclaude mcp add --transport http screening https://api.compliapi.com/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": [],
"ask": [
"mcp__screening__screen_crypto_address",
"mcp__screening__screen_email",
"mcp__screening__screen_website",
"mcp__screening__screen_government_id",
"mcp__screening__screen_vessel",
"mcp__screening__screen_aircraft",
"mcp__screening__screen_name",
"mcp__screening__screen_country",
"mcp__screening__screen_pep",
"mcp__screening__detect_vpn",
"mcp__screening__geolocate_ip"
],
"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 screening. Review it before you use it.
Capability tags behind 3 rules
- mcp__screening__screen_pep untrusted-input
- mcp__screening__detect_vpn untrusted-input
- mcp__screening__geolocate_ip 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/com.compliapi/screening/verify?hash=690de194706234573cdfea99a169712e5b0c7a257a45b2ed92a4f6ab598a42ab" | jq -e '.changed == false'Pinned hash 690de1947062, from Nov 12, 2026, 22:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.compliapi/screening/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.compliapi/screening)Source: MCP Registry. Synced Oct 21, 2026, 17:53 UTC.
screening MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the screening MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 11 of which can change, send or delete something, and 0 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 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 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 screening MCP server have?
- 11 tools: 11 write. screen_crypto_address, screen_email, screen_website, screen_government_id, screen_vessel, screen_aircraft, screen_name, screen_country and 3 more.
Does the screening MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the screening MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the screening MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.