Klardaten DATEV-Connector

Get DATEV Accounting data for the resource selected via resourceUri. REQUIRED WORKFLOW for most accounting resources: (1) List datev://accounting/clients to get the clientId GUID. (2) List datev://accounting/fiscal_years with that clientId to discover available fiscalYearId values (YYYYMMDD). (3) Use both IDs to query the target resource. Do not guess or fabricate clientId or fiscalYearId values. REPORTING WORKFLOW: For monthly Umsatz/revenue/sales or account-balance questions, use datev://accounting/accounting_sums_and_balances after resolving clientId + fiscalYearId. Select id, account_number, caption, accounting_sums_and_balances_month_values. When listing large Accounting datasets, keep select minimal and use top and skip whenever the resource exposes paging. For filter fields, required ids, and per-resource notes call datev_describe with the resourceUri as topic; module guide: topic='accounting'. Supported optional arguments across this module: accountingSequenceProcessedId, accountingSumsAndBalancesId, accountingTransactionKeysId, accountPostingsId, accountsPayableId, accountsReceivableId, clientId, costCenterId, costCenterPropertyId, costSequenceId, costSystemId, creditorId, debitorId, fiscalYearId, generalLedgerAccountId, recordId, termOfPaymentId, variousAddressId, expand, filter, select, skip, startAt, top. Returns a minimized DATEV response envelope with status and body; error bodies carry code, message, hint, and retryable.

List DATEV Accounting data for the resource selected via resourceUri. REQUIRED WORKFLOW for most accounting resources: (1) List datev://accounting/clients to get the clientId GUID. (2) List datev://accounting/fiscal_years with that clientId to discover available fiscalYearId values (YYYYMMDD). (3) Use both IDs to query the target resource. Do not guess or fabricate clientId or fiscalYearId values. REPORTING WORKFLOW: For monthly Umsatz/revenue/sales or account-balance questions, use datev://accounting/accounting_sums_and_balances after resolving clientId + fiscalYearId. Select id, account_number, caption, accounting_sums_and_balances_month_values. When listing large Accounting datasets, keep select minimal and use top and skip whenever the resource exposes paging. For filter fields, required ids, and per-resource notes call datev_describe with the resourceUri as topic; module guide: topic='accounting'. Supported optional arguments across this module: accountingSequenceProcessedId, assetId, clientId, costSequenceId, costSystemId, fiscalYearId, expand, filter, select, skip, top. Returns a minimized DATEV response envelope with status and body; error bodies carry code, message, hint, and retryable.

Discover the correct DATEV resource contract and arguments before calling a data tool, or describe this server's modules, workflows, filter dialects, and id formats. MCP version 1.0.309; callers that cache this value may pass it as the optional version argument. Makes no DATEV API call. topic accepts: 'overview' (server guide, module index, guide list, error codes) | a module name ('accounting', 'master-data', 'dms', 'order-management', 'payroll') for that module's workflow guide and resource catalog | a resource URI like 'datev://accounting/fiscal_years' for its required path arguments, filter fields, and notes | a guide name like 'datev-dms-filter-builder' for a task guide. This metadata provides valid filter fields and id formats before a data call and explains remediation hints returned by other tools.

Get DATEV DMS data for the resource selected via resourceUri. ID TYPES: document id is a GUID ('number' is a separate human-friendly integer); structure_item id and document_file_id are Integers; domain/folder/register/state ids are Integers; user ids and correspondence_partner_guid are GUIDs; the date_time fields are ISO datetimes. FILTER RULES: use only documented filter fields; never infer/translate/invent names. gt/lt only on number, Integer ids (domain.id/folder.id/register.id/state.id), and date_time fields; not GUID fields. eq on all. Each field once, except gt+lt range. NO EXPAND, NO SELECT. Page with top/skip — the server caps responses at 1,000 entries. SEARCH WORKFLOW: (1) resolve names to ids via datev://dms/domains and datev://dms/document_states, (2) list datev://dms/documents with a filter from those ids (domain.id eq 1 and state.id eq 5) plus top/skip. DOWNLOAD WORKFLOW: (1) list datev://dms/structure_items with id = document GUID to get document_file_id values, (2) get datev://dms/document_files with documentFileId — returns a temporary single-use download link, never inline bytes. For filter fields, required ids, and per-resource notes call datev_describe with the resourceUri as topic; module guide: topic='dms'. Supported optional arguments across this module: documentFileId, id, stateId, structureItemId. Returns a minimized DATEV response envelope with status and body; error bodies carry code, message, hint, and retryable.

List DATEV DMS data for the resource selected via resourceUri. ID TYPES: document id is a GUID ('number' is a separate human-friendly integer); structure_item id and document_file_id are Integers; domain/folder/register/state ids are Integers; user ids and correspondence_partner_guid are GUIDs; the date_time fields are ISO datetimes. FILTER RULES: use only documented filter fields; never infer/translate/invent names. gt/lt only on number, Integer ids (domain.id/folder.id/register.id/state.id), and date_time fields; not GUID fields. eq on all. Each field once, except gt+lt range. NO EXPAND, NO SELECT. Page with top/skip — the server caps responses at 1,000 entries. SEARCH WORKFLOW: (1) resolve names to ids via datev://dms/domains and datev://dms/document_states, (2) list datev://dms/documents with a filter from those ids (domain.id eq 1 and state.id eq 5) plus top/skip. DOWNLOAD WORKFLOW: (1) list datev://dms/structure_items with id = document GUID to get document_file_id values, (2) get datev://dms/document_files with documentFileId — returns a temporary single-use download link, never inline bytes. For filter fields, required ids, and per-resource notes call datev_describe with the resourceUri as topic; module guide: topic='dms'. Supported optional arguments across this module: id, filter, skip, top. Returns a minimized DATEV response envelope with status and body; error bodies carry code, message, hint, and retryable.

Stages an attachmentHandle returned by datev_dms_get and exposes the file through the stable DATEV attachment resource. The prepared resource is read immediately because only one attachment can be pending per authorized connection. An attachment_slot_busy response means the stable resource still exposes the previously prepared file, not the requested file; reading it would return that previous file. A later preparation is possible after the previous file is consumed or expires.

Optional Klardaten add-on for searching indexed DATEV DMS document content with a German or English natural-language query. Returns relevance-ranked documents and evidence; it retrieves documents and does not generate an answer. The highest-scoring chunk plus up to three adjacent chunks on each side is included by default. A concise retrieval phrase works best. The first search for a distinctive named entity uses the user's original spelling. Corrected spellings and synonyms are used only in separate follow-up searches and are not combined with generic document terms. One transient failure supports one retry with topK 2. A focused follow-up can search a returned dmsDocumentId with topK 1 when context lacks a requested fact. When the add-on is disabled, exact metadata remains available through datev_dms_list, but metadata search is not equivalent to content search.

Get DATEV Master Data data for the resource selected via resourceUri. Always use select and filter to narrow results. For high-volume resources (clients, addressees, deleted_clients, deleted_addressees), always provide top to limit the page size; use skip to iterate. The clientId parameter requires a GUID (not a number). Retrieve valid client GUIDs via datev://master-data/clients first. Filter syntax: contains(field, 'text') for partial matches, startswith(field, 'text') for prefixes, field eq value for exact matches; combine with 'and'. Prefer contains() over eq for text/name searches. Examples: contains(name, 'Muster') | number eq 10010004 | contains(current_company_name, 'Acme'). For filter fields, required ids, and per-resource notes call datev_describe with the resourceUri as topic; module guide: topic='master-data'. Supported optional arguments across this module: addresseeId, clientCategoryTypeId, clientGroupTypeId, clientId, employeeId, establishmentId, organizationId, expand, range, select, start. Returns a minimized DATEV response envelope with status and body; error bodies carry code, message, hint, and retryable.

List DATEV Master Data data for the resource selected via resourceUri. Always use select and filter to narrow results. For high-volume resources (clients, addressees, deleted_clients, deleted_addressees), always provide top to limit the page size; use skip to iterate. The clientId parameter requires a GUID (not a number). Retrieve valid client GUIDs via datev://master-data/clients first. Filter syntax: contains(field, 'text') for partial matches, startswith(field, 'text') for prefixes, field eq value for exact matches; combine with 'and'. Prefer contains() over eq for text/name searches. Examples: contains(name, 'Muster') | number eq 10010004 | contains(current_company_name, 'Acme'). For filter fields, required ids, and per-resource notes call datev_describe with the resourceUri as topic; module guide: topic='master-data'. Supported optional arguments across this module: clientId, filter, nationalRight, select, skip, top. Returns a minimized DATEV response envelope with status and body; error bodies carry code, message, hint, and retryable.

Get DATEV Order Management data for the resource selected via resourceUri. DISCOVERY WORKFLOW: (1) list datev://order-management/self_clients to resolve client names to client_id GUIDs, (2) list datev://order-management/order_types to decode numeric ordertype codes, (3) list datev://order-management/orders with top and skip; narrow with filter=client_id eq <GUID>. FILTERS: operators eq, ne, gt, ge, lt, le combined with 'and'/'or'. Quote strings; use unquoted YYYY-MM-DD dates; integers and booleans unquoted. Each field at most once per filter — no same-field ranges. ORDER DETAIL: use datev_order_management_get on datev://order-management/orders with orderId and expand=suborders; never combine expand with select. Always add top and skip to list calls to avoid oversized result sets. For filter fields, required ids, and per-resource notes call datev_describe with the resourceUri as topic; module guide: topic='order-management'. Supported optional arguments across this module: invoiceId, orderId, costRate, expand, select. Returns a minimized DATEV response envelope with status and body; error bodies carry code, message, hint, and retryable.