Doxis AI.dp (Klippa DocHorizon) MCP by usefulapi
Capture invoices, receipts, IDs and bank statements with Doxis AI.dp; split, render, convert files.
사용해야 할까요
품질 및 안전성
발견 사항 (6)
- LOWTool 'dochorizon_list_prompt_configurations' name length outside 3-30 rangedochorizon_list_prompt_configurations에서
- LOWTool 'dochorizon_capture_bank_statement' name length outside 3-30 rangedochorizon_capture_bank_statement에서
- LOWTool 'dochorizon_submit_async_capture' name length outside 3-30 rangedochorizon_submit_async_capture에서
- LOWTool 'dochorizon_get_async_job_result' name length outside 3-30 rangedochorizon_get_async_job_result에서
- LOWTool 'dochorizon_search_peppol_directory' name length outside 3-30 rangedochorizon_search_peppol_directory에서
- LOWTool 'dochorizon_lookup_peppol_participant' name length outside 3-30 rangedochorizon_lookup_peppol_participant에서
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"klippa-dochorizon": {
"url": "https://klippa-dochorizon.usefulapi.io/mcp"
}
}
}원격 엔드포인트
https://klippa-dochorizon.usefulapi.io/mcpstreamable-http할 수 있는 일
도구 목록
도구 (30)
🟢dochorizon_get_key_info
Check the connected Doxis AI.dp (Klippa DocHorizon) API key: organization, project, credential id, and the services enabled for it. Does not process a document and costs nothing. GET /auth/v1/info.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_list_models
List the document capturing models enabled for this project (financial, identity, bank statement, salary slip, generic, e-invoice, ...). Does not process a document; normally not billed. GET /document_capturing/v1/enabled_models.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_list_configurations(model)
List the capturing configurations of a model (name, slug and the enabled components). Pass a slug as configuration_slug to a capture tool to choose which fields are extracted. Does not process a document; normally not billed. GET /document_capturing/v1/{model}/configurations.
입력 스키마
{
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"financial",
"identity",
"bank_statement",
"salary_slip"
],
"description": "The capturing model."
}
},
"required": [
"model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_get_model_schema(model, configuration_slug)
The JSON schema of what a capturing model returns (every field it can extract), optionally for one configuration. Does not process a document; normally not billed. GET /document_capturing/v1/{model}/schema or /{model}/configurations/{slug}/schema.
입력 스키마
{
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"financial",
"identity",
"bank_statement",
"salary_slip",
"einvoice"
],
"description": "The capturing model."
},
"configuration_slug": {
"description": "Schema for this configuration (not for einvoice).",
"type": "string",
"minLength": 1,
"maxLength": 100,
"pattern": "^[A-Za-z0-9_.-]+$"
}
},
"required": [
"model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_list_prompt_configurations
List the Prompt Builder (LLM extraction) configurations of the project: name and slug. Does not process a document; normally not billed. GET /document_capturing/v1/prompt_builder/configurations.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_get_prompt_schema(slug)
The JSON schema of the output of one Prompt Builder configuration. Does not process a document; normally not billed. GET /document_capturing/v1/prompt_builder/configurations/{slug}/schema.
입력 스키마
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"pattern": "^[A-Za-z0-9_.-]+$",
"description": "Prompt Builder configuration slug."
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_capture_financial(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: extract structured data from an invoice, receipt or other financial document with the Financial model: merchant and customer, dates, totals, VAT, line items, payment details, currency, and more (as the chosen configuration enables). Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). Synchronous; for long documents use dochorizon_submit_async_capture. POST /document_capturing/v1/financial.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Pages to process, for example '1-3, 5', '2-last', 'first-last' (default: all pages; documents over 50 pages time out).",
"type": "string",
"maxLength": 100
},
"configuration_slug": {
"description": "Slug of a capturing configuration made in the platform (see dochorizon_list_configurations). Optional: the model's defaults apply without it.",
"type": "string",
"minLength": 1,
"maxLength": 100,
"pattern": "^[A-Za-z0-9_.-]+$"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_capture_identity(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: read an identity document (passport, ID card, driver's licence, visa) with the Identity model: name, date of birth, nationality, document number, expiry, MRZ, validity and fraud checks. WARNING: the result contains personal data of the people on the document; handle it accordingly. It is returned to you only; this server never stores or logs it. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). Images up to 4096 px per side. POST /document_capturing/v1/identity.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Pages to process, for example '1-3, 5', '2-last', 'first-last' (default: all pages; documents over 50 pages time out).",
"type": "string",
"maxLength": 100
},
"configuration_slug": {
"description": "Slug of a capturing configuration made in the platform (see dochorizon_list_configurations). Optional: the model's defaults apply without it.",
"type": "string",
"minLength": 1,
"maxLength": 100,
"pattern": "^[A-Za-z0-9_.-]+$"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_capture_bank_statement(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: extract a bank statement: bank, account holder, period, opening and closing balance and every transaction. WARNING: the result contains personal data of the people on the document; handle it accordingly. It is returned to you only; this server never stores or logs it. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_capturing/v1/bank_statement.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Pages to process, for example '1-3, 5', '2-last', 'first-last' (default: all pages; documents over 50 pages time out).",
"type": "string",
"maxLength": 100
},
"configuration_slug": {
"description": "Slug of a capturing configuration made in the platform (see dochorizon_list_configurations). Optional: the model's defaults apply without it.",
"type": "string",
"minLength": 1,
"maxLength": 100,
"pattern": "^[A-Za-z0-9_.-]+$"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_capture_salary_slip(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: extract a salary slip (payslip): employer, employee, period, gross and net pay, deductions. WARNING: the result contains personal data of the people on the document; handle it accordingly. It is returned to you only; this server never stores or logs it. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_capturing/v1/salary_slip.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Pages to process, for example '1-3, 5', '2-last', 'first-last' (default: all pages; documents over 50 pages time out).",
"type": "string",
"maxLength": 100
},
"configuration_slug": {
"description": "Slug of a capturing configuration made in the platform (see dochorizon_list_configurations). Optional: the model's defaults apply without it.",
"type": "string",
"minLength": 1,
"maxLength": 100,
"pattern": "^[A-Za-z0-9_.-]+$"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_capture_generic(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: turn any document into generic structured data: key-value pairs and tables, as JSON. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_capturing/v1/generic.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Pages to process, for example '1-3, 5', '2-last', 'first-last' (default: all pages; documents over 50 pages time out).",
"type": "string",
"maxLength": 100
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_capture_einvoice(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: read an invoice with the financial model and return it in the Universal Invoice structure used for e-invoicing (parties, lines, tax subtotals, totals, payment means). Does not send anything to a network. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_capturing/v1/einvoice.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Pages to process, for example '1-3, 5', '2-last', 'first-last' (default: all pages; documents over 50 pages time out).",
"type": "string",
"maxLength": 100
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_capture_with_prompt(slug, url, data_base64, file_id, filename, ...)
SPENDS CREDITS: extract data from a document with a Prompt Builder configuration (an LLM extraction prompt you defined in the platform). Output follows that configuration's schema (see dochorizon_get_prompt_schema). The result may contain whatever personal data the document holds. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_capturing/v1/prompt_builder/configurations/{slug}.
입력 스키마
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"pattern": "^[A-Za-z0-9_.-]+$",
"description": "Prompt Builder configuration slug (see dochorizon_list_prompt_configurations)."
},
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Pages to process, for example '1-3, 5', '2-last', 'first-last' (default: all pages; documents over 50 pages time out).",
"type": "string",
"maxLength": 100
}
},
"required": [
"slug"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_submit_async_capture(model, url, data_base64, file_id, filename, ...)
SPENDS CREDITS: queue one document for capturing and return a job_id right away; poll dochorizon_get_async_job, then read dochorizon_get_async_job_result. Use it for long documents and bursts (async jobs are not subject to the concurrent-request limit). No webhook or human review is configured. For identity, salary_slip and bank_statement the result holds personal data. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_capturing/v1/{model}/async.
입력 스키마
{
"type": "object",
"properties": {
"model": {
"type": "string",
"enum": [
"financial",
"identity",
"bank_statement",
"salary_slip",
"generic",
"einvoice"
],
"description": "The capturing model."
},
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Pages to process, for example '1-3, 5', '2-last', 'first-last' (default: all pages; documents over 50 pages time out).",
"type": "string",
"maxLength": 100
},
"configuration_slug": {
"description": "Slug of a capturing configuration made in the platform (see dochorizon_list_configurations). Optional: the model's defaults apply without it.",
"type": "string",
"minLength": 1,
"maxLength": 100,
"pattern": "^[A-Za-z0-9_.-]+$"
}
},
"required": [
"model"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_list_async_jobs(status, limit, offset)
List the project's async capture jobs (newest first as returned): job_id, status, created time, with paging. Does not process a document; normally not billed. GET /document_capturing/v1/async.
입력 스키마
{
"type": "object",
"properties": {
"status": {
"description": "Only jobs in these states.",
"maxItems": 7,
"type": "array",
"items": {
"type": "string",
"enum": [
"in_queue",
"processing",
"hitl",
"done",
"error",
"closed",
"rejected"
]
}
},
"limit": {
"description": "Jobs per page (default 25).",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"offset": {
"description": "Skip this many jobs (use the previous reply's paging_data).",
"type": "integer",
"minimum": 0,
"maximum": 1000000
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_get_async_job(job_id)
The status of one async capture job (in_queue, processing, hitl, done, error, closed, rejected). Does not process a document; normally not billed. GET /document_capturing/v1/async/{job_id}.
입력 스키마
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "The job_id returned when the document was submitted."
}
},
"required": [
"job_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_get_async_job_result(job_id)
The captured data of a finished async job (status done). The result may contain personal data (identity, salary slip, bank statement). Does not process a document; normally not billed. GET /document_capturing/v1/async/{job_id}/result.
입력 스키마
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "The job_id returned when the document was submitted."
}
},
"required": [
"job_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_get_async_job_logs(job_id, limit, offset)
Status changes and error messages of an async job, to debug a failed one. Does not process a document; normally not billed. GET /document_capturing/v1/async/{job_id}/logs.
입력 스키마
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "The job_id returned when the document was submitted."
},
"limit": {
"description": "Entries per page (default 25).",
"type": "integer",
"minimum": 1,
"maximum": 100
},
"offset": {
"description": "Skip this many entries.",
"type": "integer",
"minimum": 0,
"maximum": 1000000
}
},
"required": [
"job_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🔴dochorizon_delete_async_job(job_id)
WRITE: permanently delete an async job, its result and the stored documents from Doxis AI.dp's servers; a job still waiting in the queue is cancelled. Use it to remove personal data you no longer need. Cannot be undone. DELETE /document_capturing/v1/async/{job_id}.
입력 스키마
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "The job_id returned when the document was submitted."
}
},
"required": [
"job_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_document_info(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: page count, page sizes, content type, metadata and permissions of a PDF or TIFF. Useful to check the page count before capturing. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_toolkit/v1/info.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_document_split(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: split a PDF into several PDFs by page ranges (one output file per range, for example ['1-3','4-6']). Output files are stored in Doxis AI.dp storage and returned as file ids you can pass to any other tool as file_id. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_toolkit/v1/split.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"pattern": "^[A-Za-z0-9,\\- ]+$"
},
"description": "One entry per output file, e.g. ['1-3', '4-6', '7']."
}
},
"required": [
"page_ranges"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_document_render(url, data_base64, file_id, filename, content_type, ...)
SPENDS CREDITS: render pages of a PDF as images, optionally limited in width/height. Each render config gives page_ranges and optional width and height in pixels. Images are stored in Doxis AI.dp storage and returned as file ids (use dochorizon_download_file for small ones). Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file). POST /document_toolkit/v1/render.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"renders": {
"minItems": 1,
"maxItems": 10,
"type": "array",
"items": {
"type": "object",
"properties": {
"page_ranges": {
"minItems": 1,
"maxItems": 20,
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"pattern": "^[A-Za-z0-9,\\- ]+$"
},
"description": "Pages to render, e.g. ['1', '3-4']."
},
"width": {
"description": "Maximum width in pixels.",
"type": "integer",
"minimum": 1,
"maximum": 10000
},
"height": {
"description": "Maximum height in pixels.",
"type": "integer",
"minimum": 1,
"maximum": 10000
}
},
"required": [
"page_ranges"
]
},
"description": "The render configurations."
}
},
"required": [
"renders"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_document_merge(documents)
SPENDS CREDITS: merge two or more PDFs into one, in the order given, optionally taking only some pages of each. The merged file is stored in Doxis AI.dp storage and returned as a file id. Uses your own Doxis AI.dp (Klippa) credits: billed per request or per page depending on the service (extra components in a configuration can add cost), at your project's price (Billing → Pricing in the platform); a new account starts with EUR 25 of free credit. Each document is one of url (public https), data_base64 or file_id. POST /document_toolkit/v1/merge.
입력 스키마
{
"type": "object",
"properties": {
"documents": {
"minItems": 2,
"maxItems": 10,
"type": "array",
"items": {
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"file_id": {
"description": "A Doxis AI.dp storage file id (from dochorizon_upload_file or a toolkit result).",
"type": "string",
"minLength": 1,
"maxLength": 200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"password": {
"description": "Password of a protected PDF. Only used for this request.",
"type": "string",
"maxLength": 200
},
"page_ranges": {
"description": "Only these pages of this document, e.g. ['1-2']. Default: all.",
"maxItems": 20,
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"pattern": "^[A-Za-z0-9,\\- ]+$"
}
}
}
},
"description": "The PDFs to merge, in order (2 to 10)."
}
},
"required": [
"documents"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_upload_file(url, data_base64, filename, content_type)
WRITE: store a file in your Doxis AI.dp storage and get a file_id to reuse in other tools (capture the same file several times without sending it again). Give a public https url or small base64 data. The file stays in your project's storage until it expires per your data-retention setting. May use credits per your pricing. POST /storage/v1/files.
입력 스키마
{
"type": "object",
"properties": {
"url": {
"description": "Public https URL of the document. Klippa downloads it (must complete within 30 seconds).",
"type": "string",
"maxLength": 2048
},
"data_base64": {
"description": "The document as base64 (at most about 1.5 MB of file). Prefer url or file_id for anything bigger.",
"type": "string",
"maxLength": 2000200
},
"filename": {
"description": "A name for the file (helps content-type detection).",
"type": "string",
"maxLength": 255
},
"content_type": {
"description": "MIME type, if it cannot be detected.",
"type": "string",
"maxLength": 100,
"pattern": "^[\\w.+-]+\\/[\\w.+-]+$"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_download_file(file_id)
Fetch a stored file by file_id and return it as base64. Only files up to 30 KB are returned inline; for larger files use the file_id in other tools instead. Does not process a document; normally not billed. GET /storage/v1/files/{file_id}.
입력 스키마
{
"type": "object",
"properties": {
"file_id": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "A storage file id."
}
},
"required": [
"file_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_validate_einvoice(xml, data_base64, einvoice_type)
Validate an e-invoice (XML or hybrid PDF) against its standard (EN 16931, XRechnung, Peppol BIS, ...): returns the detected type, valid yes/no, a summary and each broken rule with its XPath location. Nothing is sent to anyone. May use credits per your pricing. POST /einvoicing/v1/tools/validate.
입력 스키마
{
"type": "object",
"properties": {
"xml": {
"description": "The e-invoice as XML text (UBL, CII, ...).",
"type": "string",
"maxLength": 1000000
},
"data_base64": {
"description": "The e-invoice file as base64 (XML, or a hybrid PDF such as ZUGFeRD / Factur-X).",
"type": "string",
"maxLength": 2000200
},
"einvoice_type": {
"description": "The e-invoice type, if it should not be auto-detected (see dochorizon_list_einvoice_types).",
"type": "string",
"maxLength": 60,
"pattern": "^[A-Za-z0-9_.:-]+$"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡dochorizon_convert_einvoice(xml, data_base64, einvoice_type, include_unmapped_fields, validate)
Convert an e-invoice (XML or hybrid PDF) to the Universal Invoice JSON structure (parties, lines, taxes, totals). Nothing is sent to anyone. May use credits per your pricing. POST /einvoicing/v1/tools/convert/einvoice.
입력 스키마
{
"type": "object",
"properties": {
"xml": {
"description": "The e-invoice as XML text (UBL, CII, ...).",
"type": "string",
"maxLength": 1000000
},
"data_base64": {
"description": "The e-invoice file as base64 (XML, or a hybrid PDF such as ZUGFeRD / Factur-X).",
"type": "string",
"maxLength": 2000200
},
"einvoice_type": {
"description": "The e-invoice type, if it should not be auto-detected (see dochorizon_list_einvoice_types).",
"type": "string",
"maxLength": 60,
"pattern": "^[A-Za-z0-9_.:-]+$"
},
"include_unmapped_fields": {
"description": "Also return fields of the original that have no place in the universal format.",
"type": "boolean"
},
"validate": {
"description": "Validate the e-invoice during conversion.",
"type": "boolean"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_list_einvoice_types
The e-invoice types Doxis AI.dp understands (ids to pass as einvoice_type). Does not process a document; normally not billed. GET /einvoicing/v1/tools/einvoice-types.
입력 스키마
{
"type": "object",
"properties": {},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_search_peppol_directory(environment, query)
Search the public Peppol business directory by company name, identifier or other text: participant identifiers, countries, contacts, websites and the document types each can receive. Public business data; costs nothing. GET /einvoicing/v1/peppol/environments/{environment}/directory.
입력 스키마
{
"type": "object",
"properties": {
"environment": {
"type": "string",
"enum": [
"production",
"acceptance"
],
"description": "Peppol environment: production (live network) or acceptance (test)."
},
"query": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "Name, identifier or other identifying text."
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢dochorizon_lookup_peppol_participant(environment, participant_identifier)
Look up one Peppol participant by identifier (for example iso6523-actorid-upis::0106:64111512) in the Peppol network (SML): the document types it can receive. Does not process a document; normally not billed. GET /einvoicing/v1/peppol/environments/{environment}/participants/{participant_identifier}.
입력 스키마
{
"type": "object",
"properties": {
"environment": {
"type": "string",
"enum": [
"production",
"acceptance"
],
"description": "Peppol environment: production (live network) or acceptance (test)."
},
"participant_identifier": {
"type": "string",
"minLength": 3,
"maxLength": 200,
"pattern": "^[A-Za-z0-9_.:-]+$",
"description": "The Peppol participant identifier."
}
},
"required": [
"participant_identifier"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}커뮤니티
증거