{ "openapi": "3.1.1", "info": { "title": "Unicode Inspector API", "version": "1.0.0", "summary": "Every code point with name, script and bytes, plus hidden characters and look-alikes.", "description": "Every endpoint performs the same calculation as the human page and returns inputs, result, units, assumptions, sources, warnings and computedAt. MCP endpoint: /mcp." }, "servers": [ { "url": "https://unicodeinspector.usefulweb.site" } ], "paths": { "/api/v1/calculate": { "post": { "operationId": "calculate", "summary": "Every code point with name, script and bytes, plus hidden characters and look-alikes.", "description": "Breaks text into code points with U+ value, name, general category, script and UTF-8/UTF-16 encoding; counts graphemes; compares NFC/NFD/NFKC/NFKD forms; and flags zero-width and invisible characters, bidirectional controls (Trojan Source) and mixed-script look-alike words used in phishing.\n\nMethodology:\n- The text is split into Unicode code points. General category and script come from the JavaScript regular-expression Unicode property tables of the server (\\p{gc=…}, \\p{Script=…}), which follow the Unicode version of its ICU build.\n- Names: the complete Unicode name list is about 2 MB, so a compact built-in table covers ASCII, Latin-1, basic Greek and Cyrillic, all invisible/format/space characters, common punctuation and variation selectors; CJK ideographs, Hangul syllables, fullwidth forms and tag characters are named algorithmically. Other characters show no name.\n- Grapheme clusters (user-perceived characters) are counted with Intl.Segmenter. Normalization forms come from String.prototype.normalize.\n- Invisible: zero-width characters, format characters (Cf), fillers, variation selectors and tag characters. Bidi controls (U+202A–202E, U+2066–2069) can make source code display differently from how it compiles (CVE-2021-42574, \"Trojan Source\").\n- Look-alikes: words mixing scripts (e.g. Latin + Cyrillic) and characters from a curated subset of Unicode confusables.txt are flagged; the skeleton maps them to Latin for comparison. This is a subset, not the full UTS #39 algorithm.", "tags": [ "developer" ], "x-mcp-tool": "unicode_inspector", "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/UnicodeInspectorInput" }, "examples": { "example1": { "summary": "Look-alike domain (Cyrillic \"а\" in paypal) with a zero-width space", "value": { "text": "pаypal​.com" } }, "example2": { "summary": "Trojan Source: right-to-left override in code", "value": { "text": "access_level != \"user‮ ⁦// Check if admin⁩ ⁦\"" } }, "example3": { "summary": "Emoji family, combining accents and fullwidth letters", "value": { "text": "Café 👨‍👩‍👧 ＡＢＣ" } } } } } }, "responses": { "200": { "description": "Calculation result envelope.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/UnicodeInspectorResult" } } } }, "400": { "description": "Malformed JSON body.", "content": { "application/problem+json": { "schema": { "$ref": "#/components/schemas/Problem" } } } }, "422": { "description": "Invalid input (see errors[]).", "content": { "application/problem+json": { "schema": { "$ref": "#/components/schemas/Problem" } } } }, "429": { "description": "Rate limit exceeded (see Retry-After).", "content": { "application/problem+json": { "schema": { "$ref": "#/components/schemas/Problem" } } } } } } }, "/api/v1/tool": { "get": { "operationId": "getToolDefinition", "summary": "Inputs, output schema and examples for this tool", "responses": { "200": { "description": "Tool definition.", "content": { "application/json": { "schema": { "type": "object" } } } } } } } }, "components": { "schemas": { "Problem": { "type": "object", "description": "RFC 9457 problem details. 422 responses include per-field `errors`.", "required": [ "type", "title", "status", "detail" ], "properties": { "type": { "type": "string" }, "title": { "type": "string" }, "status": { "type": "integer" }, "detail": { "type": "string" }, "code": { "type": "string" }, "errors": { "type": "array", "items": { "type": "object", "required": [ "field", "message" ], "properties": { "field": { "type": "string" }, "message": { "type": "string" } } } } } }, "UnicodeInspectorInput": { "type": "object", "additionalProperties": false, "properties": { "text": { "title": "Text", "description": "Up to 20,000 characters; the table lists the first 500 code points.", "type": "string", "maxLength": 20000 } }, "required": [ "text" ] }, "UnicodeInspectorResult": { "type": "object", "additionalProperties": false, "required": [ "schemaVersion", "tool", "computedAt", "inputs", "summary", "result", "units", "assumptions", "sources", "warnings", "presentation", "links" ], "properties": { "schemaVersion": { "type": "string", "const": "1.0" }, "tool": { "type": "object", "additionalProperties": false, "required": [ "id", "name", "version" ], "properties": { "id": { "type": "string" }, "name": { "type": "string" }, "version": { "type": "string" } } }, "computedAt": { "type": "string", "format": "date-time" }, "inputs": { "type": "object", "description": "Normalised inputs actually used, including applied defaults." }, "summary": { "type": "string" }, "result": { "type": "object", "additionalProperties": false, "required": [ "codePoints", "utf16Units", "utf8Bytes", "graphemes", "truncated", "chars", "scripts", "normalization", "findings", "skeleton", "escaped" ], "properties": { "codePoints": { "type": "integer" }, "utf16Units": { "type": "integer", "description": "JavaScript string length." }, "utf8Bytes": { "type": "integer" }, "graphemes": { "type": "integer", "description": "User-perceived characters (extended grapheme clusters)." }, "truncated": { "type": "boolean", "description": "true when more than 500 code points; chars then lists the first 500." }, "chars": { "type": "array", "items": { "type": "object", "additionalProperties": false, "required": [ "index", "codePoint", "char", "name", "category", "categoryName", "script", "utf8", "utf16", "flags" ], "properties": { "index": { "type": "integer" }, "codePoint": { "type": "string" }, "char": { "type": "string" }, "name": { "type": [ "string", "null" ] }, "category": { "type": "string" }, "categoryName": { "type": "string" }, "script": { "type": "string" }, "utf8": { "type": "string" }, "utf16": { "type": "string" }, "flags": { "type": "array", "items": { "type": "string" } } } } }, "scripts": { "type": "object", "additionalProperties": { "type": "integer" } }, "normalization": { "type": "array", "items": { "type": "object", "additionalProperties": false, "required": [ "form", "equal", "codePoints", "utf8Bytes", "text" ], "properties": { "form": { "type": "string" }, "equal": { "type": "boolean" }, "codePoints": { "type": "integer" }, "utf8Bytes": { "type": "integer" }, "text": { "type": "string" } } } }, "findings": { "type": "object", "additionalProperties": true }, "skeleton": { "type": "string", "description": "NFKC + Latin look-alike mapping, for comparing against an expected string." }, "escaped": { "type": "string", "description": "The input with invisible/bidi/control characters as \\u{…} escapes." } } }, "units": { "type": "object", "additionalProperties": { "type": "string" } }, "assumptions": { "type": "array", "items": { "type": "string" } }, "sources": { "type": "array", "items": { "type": "object", "additionalProperties": false, "required": [ "title" ], "properties": { "title": { "type": "string" }, "url": { "type": "string" }, "publisher": { "type": "string" }, "retrievedAt": { "type": "string" }, "note": { "type": "string" } } } }, "warnings": { "type": "array", "items": { "type": "string" } }, "presentation": { "type": "array", "items": { "type": "object" }, "description": "Display blocks used by the human page (same data)." }, "links": { "type": "object", "additionalProperties": false, "required": [ "human", "api", "openapi", "methodology" ], "properties": { "human": { "type": "string", "format": "uri" }, "api": { "type": "string", "format": "uri" }, "openapi": { "type": "string", "format": "uri" }, "methodology": { "type": "string", "format": "uri" } } } } } } } }