ID & Format Oracle MCP server
tech.noahsarch/id-format-oraclenoahsarch.techstreamable-httpv0.1.1Scanned
Validate IBAN, BIC, VAT, national IDs, phones, postal codes offline; 240+ identifiers.
7 tools: 3 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 2 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 ID & Format Oracle MCP server can do
The ID & Format Oracle MCP server is published by noahsarch.tech, a domain the MCP Registry verified. It has 7 tools. It can create or change data (3 tools: validate_identifier, detect_identifier and validate_postal_code), 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.
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 0.1.1.
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
detect_identifierTry every validator for the given country plus the international ones and return the types that accept the value, best first (checksum-bearing types rank above pattern-only ones).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 Try every validator for the given country plus the international ones and return the types that accept the value, best first (checksum-bearing types rank above pattern-only ones). Use when a document or form field holds a number of unknown type. A match is structural, not proof of type. Example: number '12345678901', country 'KW'. Response: result plus data_confidence (high = check-digit algorithm from a public specification; medium = community-documented checksum or pattern-only; low = structure only), estimated_items[], sources[], data_version and a disclaimer (structural validation only — never proof that an identifier is issued or belongs to someone).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
validate_identifierValidate and normalise one identifier whose type you know (format, length, dates and check digits).1 finding
Why it is in this group
- The name "validate_identifier" says "validate": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "validate_identifier" 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":true,"openWorldHint":false}; The name "validate_identifier" says "validate": a word for reading.
Description, as the server wrote it Validate and normalise one identifier whose type you know (format, length, dates and check digits). Returns valid, compact and formatted forms, the checks performed, a reason when invalid, and extracted details where the number encodes them (birth date, sex, holder type). Example: number '784-1990-1234567-1', code 'ae_emirates_id'. Response: result plus data_confidence (high = check-digit algorithm from a public specification; medium = community-documented checksum or pattern-only; low = structure only), estimated_items[], sources[], data_version and a disclaimer (structural validation only — never proof that an identifier is issued or belongs to someone).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
validate_postal_codeCheck a postal/ZIP code against the national format for 158 countries, and say so when the country has no postal codes (UAE, Qatar…).1 finding
Why it is in this group
- The name "validate_postal_code" says "validate": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "validate_postal_code" 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":true,"openWorldHint":false}; The name "validate_postal_code" says "validate": a word for reading.
Description, as the server wrote it Check a postal/ZIP code against the national format for 158 countries, and say so when the country has no postal codes (UAE, Qatar…). Pattern check only. Example: code '11564', country 'SA'. Response: result plus data_confidence (high = check-digit algorithm from a public specification; medium = community-documented checksum or pattern-only; low = structure only), estimated_items[], sources[], data_version and a disclaimer (structural validation only — never proof that an identifier is issued or belongs to someone).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
Only reads 4Show 4 read-only tools
list_identifiersCatalogue of the identifier codes this service validates (250+ across 90 countries plus international standards), filterable by country and category.No findings
Why it is in this group
- The name "list_identifiers" says "list": a word for reading.
Description, as the server wrote it Catalogue of the identifier codes this service validates (250+ across 90 countries plus international standards), filterable by country and category. Free. Call it once to find the right code for validate_identifier. Response: result plus data_confidence (high = check-digit algorithm from a public specification; medium = community-documented checksum or pattern-only; low = structure only), estimated_items[], sources[], data_version and a disclaimer (structural validation only — never proof that an identifier is issued or belongs to someone).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
validate_bicValidate a BIC (ISO 9362): structure, country code, test-BIC flag, bank and branch parts, and the bank name(s) where known.No findings
Why it is in this group
- The name "validate_bic" says "validate": a word for reading.
Description, as the server wrote it Validate a BIC (ISO 9362): structure, country code, test-BIC flag, bank and branch parts, and the bank name(s) where known. Example: 'EBILAEAD'. Response: result plus data_confidence (high = check-digit algorithm from a public specification; medium = community-documented checksum or pattern-only; low = structure only), estimated_items[], sources[], data_version and a disclaimer (structural validation only — never proof that an identifier is issued or belongs to someone).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
validate_ibanValidate an IBAN (ISO 13616 length, mod-97 and national BBAN rules) and return the country, bank code, branch, bank name and BIC where the bundled registry knows it, SEPA membershi…No findings
Why it is in this group
- The name "validate_iban" says "validate": a word for reading.
Description, as the server wrote it Validate an IBAN (ISO 13616 length, mod-97 and national BBAN rules) and return the country, bank code, branch, bank name and BIC where the bundled registry knows it, SEPA membership, compact and printed forms. Example: 'AE070331234567890123456'. Response: result plus data_confidence (high = check-digit algorithm from a public specification; medium = community-documented checksum or pattern-only; low = structure only), estimated_items[], sources[], data_version and a disclaimer (structural validation only — never proof that an identifier is issued or belongs to someone).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
validate_phoneParse a phone number for any country, say whether it is valid (matches a national numbering-plan pattern) or merely possible, and return E.164, international and national formats, …No findings
Why it is in this group
- The name "validate_phone" says "validate": a word for reading.
Description, as the server wrote it Parse a phone number for any country, say whether it is valid (matches a national numbering-plan pattern) or merely possible, and return E.164, international and national formats, number type (mobile/fixed_line/toll_free…), region, location, original carrier hint and time zones. Example: number '050 123 4567', default_region 'AE'. Response: result plus data_confidence (high = check-digit algorithm from a public specification; medium = community-documented checksum or pattern-only; low = structure only), estimated_items[], sources[], data_version and a disclaimer (structural validation only — never proof that an identifier is issued or belongs to someone).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: 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 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 15, 2026, 13:23 UTC, unchanged since Oct 31, 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
- 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 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://idcheck.noahsarch.tech/mcp: tools/list returned 7 tools to an anonymous client, including validate_identifier (write), detect_identifier (write), validate_postal_code (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "validate_identifier" 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":true,"openWorldHint":false}; The name "validate_identifier" says "validate": a word for reading.
The server marks "validate_postal_code" 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":true,"openWorldHint":false}; The name "validate_postal_code" says "validate": a word for reading.
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 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http id-format-oracle https://idcheck.noahsarch.tech/mcpclaude mcp add --transport http id-format-oracle https://idcheck.noahsarch.tech/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__id-format-oracle__list_identifiers",
"mcp__id-format-oracle__validate_iban",
"mcp__id-format-oracle__validate_bic",
"mcp__id-format-oracle__validate_phone"
],
"ask": [
"mcp__id-format-oracle__validate_identifier",
"mcp__id-format-oracle__detect_identifier",
"mcp__id-format-oracle__validate_postal_code"
],
"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 id-format-oracle. 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/tech.noahsarch/id-format-oracle/verify?hash=4e0391cbaf581a1d7d8b3521e321b4d4574d9e1d1ebfcff267c697c5bda532cd" | jq -e '.changed == false'Pinned hash 4e0391cbaf58, from Nov 13, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/tech.noahsarch/id-format-oracle/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/tech.noahsarch/id-format-oracle)Source: MCP Registry. Synced Oct 31, 2026, 23:17 UTC.
ID & Format Oracle MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ID & Format Oracle MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 3 of which can change, send or delete something, and 2 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 ID & Format Oracle MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ID & Format Oracle 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 ID & Format Oracle MCP server have?
- 7 tools: 3 write, 4 read. validate_identifier, detect_identifier, validate_postal_code, list_identifiers, validate_iban, validate_bic and validate_phone.
Does the ID & Format Oracle MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ID & Format Oracle MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the ID & Format Oracle MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.