GlyphGuard
Find hidden Unicode (zero-width, bidi, tag payloads), homoglyphs and lookalike names in text.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"glyphguard": {
"url": "https://glyphguard.mike-tusa.workers.dev/mcp"
}
}
}Remote endpoints
https://glyphguard.mike-tusa.workers.dev/mcpstreamable-httpWhat it can do
Tool inventory
Tools (3)
π’scan_text(text)
Find invisible characters, bidi controls (Trojan Source), hidden Unicode tag payloads (decoded), variation-selector runs, control characters, unusual spaces, mixed-script words and lookalike letters. ZWJ/ZWNJ/VS16 in legitimate context (emoji sequences, Persian/Arabic joining, Indic virama) are reported as info joiner_in_context and do not raise risk; elsewhere they stay medium. Lone surrogates are flagged. Returns a risk level (none/low/medium/high), counts, and findings with UTF-16 offsets and code points. Read-only. Same engine as GET /api/scan.
Input Schema
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Text to inspect (up to 2000 UTF-16 code units)."
}
},
"required": [
"text"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"risk": {
"type": "string",
"enum": [
"none",
"low",
"medium",
"high"
]
},
"length": {
"type": "integer"
},
"codePoints": {
"type": "integer"
},
"total": {
"type": "integer"
},
"counts": {
"type": "object"
},
"tagPayload": {
"type": "string"
},
"findings": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string"
},
"severity": {
"type": "string"
},
"offset": {
"type": "integer"
},
"codePoint": {
"type": "string"
},
"name": {
"type": "string"
},
"char": {
"type": "string"
},
"looksLike": {
"type": "string"
},
"script": {
"type": "string"
},
"word": {
"type": "string"
},
"scripts": {
"type": "array",
"items": {
"type": "string"
}
}
}
}
},
"truncated": {
"type": "boolean"
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"normalizedNfkcDiffers": {
"type": "boolean"
},
"version": {
"type": "string"
}
},
"required": [
"risk",
"total",
"counts",
"findings",
"version"
]
}π’clean_text(text, lookalikes, nfkc, spaces, keep_joiners, ...)
Return the text with invisible characters, bidi controls, tag characters and control characters removed and unusual spaces turned into normal spaces. By default ZWJ/ZWNJ/VS16 are kept inside emoji sequences, between letters of joining scripts (Arabic, Persian) and after an Indic virama (keep_joiners=true); strict=true removes them everywhere. Optional: map lookalike letters to Latin (lookalikes) and apply NFKC normalisation (nfkc). Read-only. Same engine as GET /api/clean.
Input Schema
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Text to inspect (up to 2000 UTF-16 code units)."
},
"lookalikes": {
"type": "boolean",
"default": false,
"description": "Map lookalike letters (e.g. Cyrillic Π°) to Latin. Changes legitimate non-Latin text too."
},
"nfkc": {
"type": "boolean",
"default": false,
"description": "Apply Unicode NFKC first (fullwidth and math letters β plain)."
},
"spaces": {
"type": "boolean",
"default": true,
"description": "Turn unusual spaces into a normal space."
},
"keep_joiners": {
"type": "boolean",
"default": true,
"description": "Keep ZWJ/ZWNJ/VS16 where they are legitimate: emoji ZWJ sequences and VS16 emoji presentation, between letters of joining scripts (Arabic, Persian), and after an Indic virama. Joiners elsewhere are always removed."
},
"strict": {
"type": "boolean",
"default": false,
"description": "Strict mode: remove every joiner and variation selector, even in emoji and Persian/Indic text (overrides keep_joiners)."
}
},
"required": [
"text"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"changed": {
"type": "boolean"
},
"removed": {
"type": "object"
},
"joinersKept": {
"type": "integer"
},
"lookalikesMapped": {
"type": "integer"
},
"options": {
"type": "object"
},
"length": {
"type": "integer"
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"version": {
"type": "string"
}
},
"required": [
"text",
"changed",
"removed",
"version"
]
}π’compare_names(name, targets)
Check whether a name, username, domain label or brand looks the same as any of up to 50 protected names (for example "pΠ°ypal" with a Cyrillic Π° vs "paypal"), using a UTS #39-style confusable skeleton (curated subset, case and accents ignored). Read-only. Same engine as GET /api/compare.
Input Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Name, username, domain label or brand to test."
},
"targets": {
"type": "array",
"minItems": 1,
"maxItems": 50,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"description": "1 to 50 protected names."
}
},
"required": [
"name",
"targets"
],
"additionalProperties": false
}Output Schema
{
"type": "object",
"properties": {
"name": {
"type": "string"
},
"skeleton": {
"type": "string"
},
"confusableWith": {
"type": "array",
"items": {
"type": "string"
}
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"target": {
"type": "string"
},
"skeleton": {
"type": "string"
},
"identical": {
"type": "boolean"
},
"confusable": {
"type": "boolean"
},
"caseOnly": {
"type": "boolean"
}
}
}
},
"nameRisk": {
"type": "string"
},
"nameScripts": {
"type": "array",
"items": {
"type": "string"
}
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"version": {
"type": "string"
}
},
"required": [
"skeleton",
"confusableWith",
"results",
"version"
]
}Community
Evidence