VerifyDesk MCP server
com.agenttoolworks/verifydeskagenttoolworks.comstreamable-httpv1.2.0Scanned
Verify French and UK companies, EU VAT and IBANs; screen OFAC, UN, EU and UK sanctions lists.
6 tools: 2 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 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 VerifyDesk MCP server can do
The VerifyDesk MCP server is published by agenttoolworks.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (2 tools: verify_company and screen_sanctions), but cannot delete data. 4 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
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.
Last scanned Nov 17, 2026, version 1.2.0.
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.
6 tools
Changes things 2Claude Code: ask
screen_sanctionsScreens a person or company name against official sanctions lists: OFAC SDN and OFAC Consolidated (US Treasury), the UN Security Council Consolidated List, the EU consolidated fina…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 Screens a person or company name against official sanctions lists: OFAC SDN and OFAC Consolidated (US Treasury), the UN Security Council Consolidated List, the EU consolidated financial sanctions list and the UK Sanctions List, primary names and aliases. Matching ignores case, accents, punctuation, word order and legal forms (LLC, PJSC, GmbH), and tolerates one typo in a word of 4+ letters and common transliterations (Sergei, Sergey, Sergej). Each match has a score from 0 to 1 and a match_type (exact, alias, fuzzy); only scores at or above min_score (default 0.85) are returned, at most 10 designated parties. Always reports which lists were screened, which were unavailable and when each was last refreshed: keep 'data_as_of' with the result as evidence of the check. Latin-script names only; dates of birth, nationalities and addresses are not compared. A match is a signal for enhanced due diligence, never a legal determination. Costs 1 credit.
verify_companyVerifies a company against its official state registry and returns its legal status.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 Verifies a company against its official state registry and returns its legal status. France (SIREN/SIRET) and the United Kingdom (Companies House company number) are supported. Input: country and a query that is either a registration number or a company name. Returns up to 5 normalized records: registration number, legal name, active/closed status, legal form, activity code, registered address, creation date. Costs 1 credit.
Only reads 4Show 4 read-only tools
enrich_companyReturns extended registry data for one company identified by its registration number: officers/directors currently in office (name and role), legal form, activity, address, headcou…No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns extended registry data for one company identified by its registration number: officers/directors currently in office (name and role), legal form, activity, address, headcount range when available. Input: country (FR or GB) and the exact registration number (SIREN for FR, company number for GB). Costs 1 credit.
get_usageReturns your current plan, remaining credit balance and call volume over the last 30 days.No findings
Why it is in this group
- The name "get_usage" says "get": a word for reading.
Description, as the server wrote it Returns your current plan, remaining credit balance and call volume over the last 30 days. Free to call.
validate_ibanValidates an IBAN offline against the SWIFT IBAN Registry (Release 103, Sep 2026, all 89 countries): registered country, length, the national account format (BBAN), check digits 02…No findings
Why it is in this group
- The name "validate_iban" says "validate": a word for reading.
Description, as the server wrote it Validates an IBAN offline against the SWIFT IBAN Registry (Release 103, Sep 2026, all 89 countries): registered country, length, the national account format (BBAN), check digits 02-98 and the ISO 7064 mod-97 checksum. Returns valid, and when invalid a stable reason_code (malformed, unknown_country, wrong_length, bad_bban_format, bad_check_digits, checksum_failed) with a human reason; on a valid IBAN, the bank_code and branch_code the registry defines for that country. Optional bic: checks the ISO 9362 format and its country code, returned as bic.valid; a BIC country that differs from the IBAN country is a warnings entry, not an invalid result. 'valid' is about the IBAN only. This checks structure, not that the account or BIC exists. Light read: costs 0.2 credit.
verify_vatValidates an EU VAT number live against VIES (European Commission) and returns whether it is currently valid, with the registered name and address when the member state provides th…No findings
Why it is in this group
- The description's first verb is "validate": a word for reading.
Description, as the server wrote it Validates an EU VAT number live against VIES (European Commission) and returns whether it is currently valid, with the registered name and address when the member state provides them. Input: the full VAT number with its country prefix, e.g. 'FR40303265045'. Optional: requester_vat_number, your own EU VAT number; VIES then issues a consultationNumber, its official proof that you made this check at checkedAt. If VIES or the member state is down, returns the last answer VIES gave us for that number within the past 7 days, marked stale: true with its original checkedAt and never a consultation number; with no such answer, a retryable error. Fresh answers carry stale: false. Light read: costs 0.2 credit.
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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, 19:22 UTC, unchanged since Oct 22, 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://verifydesk.agenttoolworks.com/mcp: tools/list returned 6 tools to an anonymous client, including verify_company (write), screen_sanctions (write)
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 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http verifydesk https://verifydesk.agenttoolworks.com/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http verifydesk https://verifydesk.agenttoolworks.com/mcp --header 'Authorization: <your-authorization>'Run 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__verifydesk__verify_vat",
"mcp__verifydesk__validate_iban",
"mcp__verifydesk__enrich_company",
"mcp__verifydesk__get_usage"
],
"ask": [
"mcp__verifydesk__verify_company",
"mcp__verifydesk__screen_sanctions"
],
"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 verifydesk. Review it before you use it.
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.agenttoolworks/verifydesk/verify?hash=680a4a2606afc0e87178eaafe8e9f7d9c7fd74d03207a83553887924f7803622" | jq -e '.changed == false'Pinned hash 680a4a2606af, from Nov 17, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.agenttoolworks/verifydesk/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.agenttoolworks/verifydesk)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:48 UTC.
VerifyDesk MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the VerifyDesk MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 2 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 VerifyDesk MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the VerifyDesk 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 VerifyDesk MCP server have?
- 6 tools: 2 write, 4 read. verify_company, screen_sanctions, verify_vat, validate_iban, enrich_company and get_usage.
Does the VerifyDesk MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the VerifyDesk MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the VerifyDesk MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.