agentum-entity-resolver MCP server
io.github.Algiras/agentum-entity-resolverAlgirasstreamable-httpv0.2.2Scanned
Supplier onboarding checks: company registry, EU VAT and sanctions, with MCP and REST.
7 tools: 3 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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 agentum-entity-resolver MCP server can do
The agentum-entity-resolver MCP server is published by the GitHub account Algiras. It has 7 tools. It can create or change data (3 tools: screen_sanctions, check_vendor and screen_address), but cannot delete data. 4 tools only read.
7 tools bring in text other people can write (resolve_entity, verify_eu_vat, screen_sanctions and 4 more).
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 once since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 0.2.2.
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.
7 tools
Changes things 3Claude Code: ask
check_vendorOne-call vendor KYB: registry lookup, EU VAT check and OFAC/EU/UN/UK sanctions screening with a verdict.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 One-call vendor KYB: registry lookup, EU VAT check and OFAC/EU/UN/UK sanctions screening with a verdict. Use when onboarding a supplier, approving a vendor before first payment, or re-checking a counterparty. Inputs: name; optional country (ISO-2), vatNumber, registrationNumber, domain. Returns: verdict (APPROVED/FLAGGED_FOR_REVIEW/REJECTED), riskLevel, sanctionsHit, vatValid, entity, auditTrail[]. Sources: official registries (GLEIF, Companies House); EU VIES live; OFAC/EU/UN/UK lists refreshed every 6h. Same input → same output. $0.010 per call after 5 free calls/day; pay by card credits, x402: https://agentum.asimplek.cloud/pay
Annotations the server declares
- title: Vendor KYB check: registry, VAT and sanctions in one call
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
screen_addressChecks a crypto wallet address (EVM, Bitcoin, Tron, Solana, Litecoin) against OFAC's listed digital-currency 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 Checks a crypto wallet address (EVM, Bitcoin, Tron, Solana, Litecoin) against OFAC's listed digital-currency addresses. Exact match on the official list only; not behavioural or cluster risk. Use when about to pay or send funds to an address, vetting a counterparty wallet, or checking a deposit address. Inputs: address; optional chain (evm, bitcoin, tron, solana, litecoin, other). Returns: sanctioned, riskLevel (CLEAR/EXACT_MATCH/UNKNOWN), addressType, matches[], coverage. Source: OFAC SDN, refreshed every 6h. Same input → same output. $0.002 per call after 5 free calls/day; pay by card credits, x402: https://agentum.asimplek.cloud/pay
Annotations the server declares
- title: Screen a wallet address against the OFAC sanctioned-address list
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
screen_sanctionsScreens a company or person against OFAC SDN, EU, UN and UK FCDO sanctions lists with exact and fuzzy matching.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 Screens a company or person against OFAC SDN, EU, UN and UK FCDO sanctions lists with exact and fuzzy matching. Use when screening a counterparty before paying, checking a new vendor or customer for sanctions exposure, or re-screening a payee after a detail change. Inputs: name; optional country (ISO-2), registrationNumber, threshold (default 0.75). Returns: sanctioned, riskLevel (CLEAR/POTENTIAL_MATCH/EXACT_MATCH/UNKNOWN), matchScore, matchedLists, matches[]. Sources: OFAC/EU/UN/UK lists refreshed every 6h. Same input → same output. $0.005 per call after 5 free calls/day; pay by card credits, x402: https://agentum.asimplek.cloud/pay
Annotations the server declares
- title: Screen a name against OFAC, EU, UN and UK sanctions lists
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 4Show 4 read-only tools
batch_resolveResolves 1 to 25 companies to official registry records in one call; each item works like resolve_entity.Reads text others writeNo findings
Why it is in this group
- The name "batch_resolve" says "resolve": 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 Resolves 1 to 25 companies to official registry records in one call; each item works like resolve_entity. Use when onboarding a supplier list, enriching a CSV of counterparties with registration numbers and status, or deduplicating a vendor file. Inputs: items[] of {query (name, domain or registration number), optional country (ISO-2)}. Returns: total, resolvedCount, unresolvedCount, results[] (query, resolved, entity, confidence). Sources: official registries (GLEIF, SEC EDGAR, Companies House, EU registers). Same input → same output. $0.025 per call after 5 free calls/day; pay by card credits, x402: https://agentum.asimplek.cloud/pay
Annotations the server declares
- title: Resolve up to 25 companies to registry records in one call
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
resolve_entityResolves a company to its official registry record: legal name, registration number, status, legal form, LEI, VAT.Reads text others writeNo findings
Why it is in this group
- The name "resolve_entity" says "resolve": 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 Resolves a company to its official registry record: legal name, registration number, status, legal form, LEI, VAT. Use when onboarding a vendor, verifying a counterparty on an invoice, or enriching a company name or domain with registry IDs. Inputs: query (name, domain or registration number); optional jurisdiction (ISO-2), verifyVat, checkSanctions. Returns: resolved, confidence, entity, candidates, compliance, vatVerification. Sources: official registries (GLEIF, SEC EDGAR, Companies House, EU registers). Same input → same output. $0.005 per call after 5 free calls/day; pay by card credits, x402: https://agentum.asimplek.cloud/pay
Annotations the server declares
- title: Resolve a company to its official registry record
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
verify_bank_payeeValidates an IBAN (ISO 13616 format, length, MOD-97 checksum) and checks the account country matches the expected payee country.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "validate": 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 Validates an IBAN (ISO 13616 format, length, MOD-97 checksum) and checks the account country matches the expected payee country. Use when validating bank details on an invoice, confirming a payee's account change before paying, or checking for invoice redirection. Inputs: iban; optional expectedCountry (ISO-2), payeeName, payeeTaxId (for ownership lookup in public registers). Returns: valid, countryCode, checksumValid, countryMatch, ownershipVerified, issues[]. Sources: ISO 13616 rules; public registers. Same input → same output. $0.003 per call after 5 free calls/day; pay by card credits, x402: https://agentum.asimplek.cloud/pay
Annotations the server declares
- title: Validate an IBAN and its match to the payee's country
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
verify_eu_vatValidates an EU VAT number against the European Commission VIES service and returns the registered name and address.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "validate": 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 Validates an EU VAT number against the European Commission VIES service and returns the registered name and address. Use when validating the VAT ID on a supplier invoice, applying reverse charge on a cross-border B2B sale, or confirming a vendor's VAT registration at onboarding. Inputs: vatNumber with 2-letter country prefix (e.g. DE129274202). Returns: valid, countryCode, vatNumber, registeredName, registeredAddress, checkedAt, source (EU_VIES, CACHE, SYNTAX_ONLY), linkedEntity. Source: EU VIES live. Same input → same output. $0.005 per call after 5 free calls/day; pay by card credits, x402: https://agentum.asimplek.cloud/pay
Annotations the server declares
- title: Validate an EU VAT number against VIES
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- 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.
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 write7
- 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 19, 2026, 17:23 UTC, unchanged since Nov 12, 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
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://agentum.asimplek.cloud/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://agentum.asimplek.cloud
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agentum.asimplek.cloud/mcp: tools/list returned 7 tools to an anonymous client, including screen_sanctions (write), check_vendor (write), screen_address (write)
Posture changes
- Nov 12, 2026
- Tools that change things, listed without credentials: 2 to 3
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: 2 -> 3.View diff
- Tools that change things, listed without credentials: 2 to 3
Tools1 added, 6 changed.+1 added~6 changedView diff
- Added:screen_addressChanges things
- Changed:batch_resolveOnly readstitledescriptionannotations
- Changed:check_vendorChanges thingstitledescriptionannotations
- Changed:resolve_entityOnly readstitledescriptioninputSchemaannotations
- Changed:screen_sanctionsChanges thingstitledescriptionannotations
- Changed:verify_bank_payeeOnly readstitledescriptionannotations
- Changed:verify_eu_vatOnly readstitledescriptionannotations
Install
Pinned to version 0.2.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentum-entity-resolver https://agentum.asimplek.cloud/mcpclaude mcp add --transport http agentum-entity-resolver https://agentum.asimplek.cloud/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__agentum-entity-resolver__resolve_entity",
"mcp__agentum-entity-resolver__verify_eu_vat",
"mcp__agentum-entity-resolver__verify_bank_payee",
"mcp__agentum-entity-resolver__batch_resolve"
],
"ask": [
"mcp__agentum-entity-resolver__screen_sanctions",
"mcp__agentum-entity-resolver__check_vendor",
"mcp__agentum-entity-resolver__screen_address"
],
"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 agentum-entity-resolver. Review it before you use it.
Capability tags behind 7 rules
- mcp__agentum-entity-resolver__resolve_entity untrusted-input
- mcp__agentum-entity-resolver__verify_eu_vat untrusted-input
- mcp__agentum-entity-resolver__screen_sanctions untrusted-input
- mcp__agentum-entity-resolver__check_vendor untrusted-input
- mcp__agentum-entity-resolver__verify_bank_payee untrusted-input
- mcp__agentum-entity-resolver__screen_address untrusted-input
- mcp__agentum-entity-resolver__batch_resolve 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/io.github.Algiras/agentum-entity-resolver/verify?hash=1bd27dfee34e521c81ce595099cb687202123d509a2ebddb461e73c6a83057d2" | jq -e '.changed == false'Pinned hash 1bd27dfee34e, from Nov 18, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Algiras/agentum-entity-resolver/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Algiras/agentum-entity-resolver)Source: MCP Registry · repository. Synced Nov 18, 2026, 13:17 UTC.
agentum-entity-resolver MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the agentum-entity-resolver MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 3 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 agentum-entity-resolver MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the agentum-entity-resolver 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 agentum-entity-resolver MCP server have?
- 7 tools: 3 write, 4 read. screen_sanctions, check_vendor, screen_address, resolve_entity, verify_eu_vat, verify_bank_payee and batch_resolve.
Does the agentum-entity-resolver MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the agentum-entity-resolver MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the agentum-entity-resolver MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 7, 2026. Every change is on this page and in its Atom feed.