Taggun MCP by usefulapi
Scan receipts with Taggun OCR from a URL or file and read receipt-validation campaigns.
我该使用它吗
质量与安全性
发现（3）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains suspicious base64-like encoded string在 taggun_list_campaigns 中
- LOWTool 'taggun_validate_receipt_campaign_url' name length outside 3-30 range在 taggun_validate_receipt_campaign_url 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"taggun": {
"url": "https://taggun.usefulapi.io/mcp"
}
}
}远程端点
https://taggun.usefulapi.io/mcpstreamable-http它能做什么
工具清单
工具（6）
🟡taggun_scan_receipt_url(url, detail, extract_time, extract_line_items, ignore_merchant_name, ...)
WRITE: this scan counts against YOUR Taggun quota and plan (free for the first 30 days or 1,000 scans, then billed per scan by Taggun), even if the receipt fails validation; it is never retried automatically. Document content is not logged by this server. Extract structured data (merchant, date, total, tax, and in verbose mode line items) from a receipt or invoice at a public https URL (JPEG, PNG, GIF, HEIF/HEIC or PDF up to 5 pages, max 20 MiB). The URL must be a public host name: no IP addresses, localhost, internal names, credentials or non-default ports. POST /api/receipt/v1/{simple|verbose}/url.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 8,
"maxLength": 2000,
"description": "Public https URL of the receipt or invoice file."
},
"detail": {
"description": "simple (default) = totals, tax, date and merchant. verbose = also line items, payment type, per-field metadata and enabled fraud/feature fields.",
"type": "string",
"enum": [
"simple",
"verbose"
]
},
"extract_time": {
"description": "true = return the time of day when found on the receipt (otherwise 12:00:00).",
"type": "boolean"
},
"extract_line_items": {
"description": "Verbose only: false = skip line-item extraction (default true).",
"type": "boolean"
},
"ignore_merchant_name": {
"description": "A name to ignore if detected as the merchant, such as a customer name.",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"language": {
"description": "Optional language hint (en, ar, kh, th, he, ...). Leave out for automatic detection.",
"type": "string",
"minLength": 2,
"maxLength": 10,
"pattern": "^[A-Za-z-]+$"
},
"near": {
"description": "A location (city, state, country) that helps identify the merchant.",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"keep_stored": {
"description": "Default false: the document and its extracted data are NOT stored by Taggun (incognito). true = Taggun stores them (up to 3 years), which enables later duplicate/similarity detection but keeps personal data from the receipt.",
"type": "boolean"
}
},
"required": [
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡taggun_scan_receipt_base64(image_base64, content_type, filename, detail, extract_time, ...)
WRITE: this scan counts against YOUR Taggun quota and plan (free for the first 30 days or 1,000 scans, then billed per scan by Taggun), even if the receipt fails validation; it is never retried automatically. Document content is not logged by this server. Extract structured data from a receipt or invoice sent as base64 (JPEG, PNG, GIF, HEIF/HEIC or PDF; the base64 text is capped at 2,000,000 characters, about 1.5 MB of file; for larger files use taggun_scan_receipt_url). POST /api/receipt/v1/{simple|verbose}/encoded.
输入模式
{
"type": "object",
"properties": {
"image_base64": {
"type": "string",
"minLength": 16,
"maxLength": 2000200,
"description": "The file content, base64-encoded (a data: URL prefix is accepted)."
},
"content_type": {
"type": "string",
"enum": [
"image/jpeg",
"image/png",
"image/gif",
"image/heic",
"image/heif",
"application/pdf"
],
"description": "The file's media type."
},
"filename": {
"description": "File name, for example receipt.jpg (default derived from content_type).",
"type": "string",
"maxLength": 120
},
"detail": {
"description": "simple (default) = totals, tax, date and merchant. verbose = also line items, payment type, per-field metadata and enabled fraud/feature fields.",
"type": "string",
"enum": [
"simple",
"verbose"
]
},
"extract_time": {
"description": "true = return the time of day when found on the receipt (otherwise 12:00:00).",
"type": "boolean"
},
"extract_line_items": {
"description": "Verbose only: false = skip line-item extraction (default true).",
"type": "boolean"
},
"ignore_merchant_name": {
"description": "A name to ignore if detected as the merchant, such as a customer name.",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"language": {
"description": "Optional language hint (en, ar, kh, th, he, ...). Leave out for automatic detection.",
"type": "string",
"minLength": 2,
"maxLength": 10,
"pattern": "^[A-Za-z-]+$"
},
"near": {
"description": "A location (city, state, country) that helps identify the merchant.",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"keep_stored": {
"description": "Default false: the document and its extracted data are NOT stored by Taggun (incognito). true = Taggun stores them (up to 3 years), which enables later duplicate/similarity detection but keeps personal data from the receipt.",
"type": "boolean"
}
},
"required": [
"image_base64",
"content_type"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡taggun_validate_receipt_campaign_url(campaign_id, url, language, near, keep_stored)
WRITE: this scan counts against YOUR Taggun quota and plan (free for the first 30 days or 1,000 scans, then billed per scan by Taggun), even if the receipt fails validation; it is never retried automatically. Document content is not logged by this server. Scan a receipt at a public https URL and check it against the rules of a campaign stored on your Taggun account (dates, merchants, products, balance owing, fraud checks). Returns pass/fail with reasons. Needs the Campaign Validation feature on your Taggun plan; use taggun_list_campaigns for the ids. Same URL rules as taggun_scan_receipt_url. POST /api/validation/v1/campaign/receipt-validation/url.
输入模式
{
"type": "object",
"properties": {
"campaign_id": {
"type": "string",
"minLength": 1,
"maxLength": 50,
"description": "A campaign id from taggun_list_campaigns."
},
"url": {
"type": "string",
"minLength": 8,
"maxLength": 2000,
"description": "Public https URL of the receipt or invoice file."
},
"language": {
"description": "Optional language hint (en, ar, kh, th, he, ...). Leave out for automatic detection.",
"type": "string",
"minLength": 2,
"maxLength": 10,
"pattern": "^[A-Za-z-]+$"
},
"near": {
"description": "A location (city, state, country) that helps identify the merchant.",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"keep_stored": {
"description": "Default false: the document and its extracted data are NOT stored by Taggun (incognito). true = Taggun stores them (up to 3 years), which enables later duplicate/similarity detection but keeps personal data from the receipt.",
"type": "boolean"
}
},
"required": [
"campaign_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢taggun_list_campaigns
List the ids of the receipt-validation campaigns stored on your Taggun account (an empty list is normal). Does not use a scan. Needs the Campaign Validation feature; without it Taggun answers that the feature must be enabled. GET /api/validation/v1/campaign/settings/list.
输入模式
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢taggun_get_campaign(campaign_id)
The stored validation rules of one campaign (dates, merchants, products, fraud checks, SmartValidate prompts). Does not use a scan. GET /api/validation/v1/campaign/settings/{campaignId}.
输入模式
{
"type": "object",
"properties": {
"campaign_id": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "A campaign id from taggun_list_campaigns."
}
},
"required": [
"campaign_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢taggun_export_reference_data(kind)
Read the reference data stored on your Taggun account as CSV: product_categories (the category taxonomy), known_merchants (merchant names and locations used for matching) or product_codes (expected product codes). Read-only; does not use a scan. The text is cut at 40,000 characters. GET /api/account/v1/{product-categories|known-merchants|known-product-codes}/export.
输入模式
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"product_categories",
"known_merchants",
"product_codes"
],
"description": "Which list to export."
}
},
"required": [
"kind"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}社区
证据