1c-odata-mcp
Related Servers
Alternatives to 1c-odata-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients such as Cursor and Claude to query and inspect 1C:Enterprise infobase data via COM without configuration extensions or changes, using 1C query language and metadata tools.2MIT
- AlicenseAqualityDmaintenanceBridges AI agents to 1C:Enterprise via OData, enabling natural language queries of business entities like counterparties and invoices with read-only access.846 npmMIT
- AlicenseNot gradedqualityBmaintenanceConnects to 1C:Enterprise through OData to read business records, preview field-by-field changes, and create or update permitted catalog items and draft documents only after a human explicitly approves each write.MIT
- AlicenseNot gradedqualityBmaintenanceEnables ChatGPT's desktop Codex app to query a live 1C (1С) database through OData in read-only mode, so users can ask plain-language questions about sales, stock, items, and counterparties, and get answers, charts, and dashboards without exports or programming.4MIT
- AlicenseNot gradedqualityBmaintenanceEnables users to ask natural-language questions about live 1C:Enterprise data and receive answers from read-only OData sources, covering sales, inventory, items, and counterparties; supports direct connections or an SSH tunnel for IP-allowlisted installations.9MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to work with remote 1C:Enterprise through a local MCP bridge and an EPF agent over outbound HTTPS, supporting metadata inspection, queries, BSL execution, document access, file transfer, and configuration changes without COM or database publication.MIT
TDQS
Scored across 75 tools
Most tools target distinct resources and actions, but several direct overlaps exist: read.accounting.get_settlement_settings and read.accounting.get_contract_settlement_settings have near-identical descriptions (same for the write pair), write.entity.create_folder vs write.counterparty.create_group, write.entity.move_to_folder vs write.counterparty.set_group, and generic write.entity.update_entity vs specific update_counterparty/update_nomenclature. An agent can usually pick correctly from descriptions, but these duplicate pairs create real misselection risk.
Names follow a clear namespaced pattern (read.<domain>.<verb_noun>, write.<domain>.<verb_noun>), e.g. read.analytics.get_sales, write.warehouse.create_writeoff. Minor deviations exist: write.operation.status lacks a verb, and legacy alias pairs carry different names for the same tool, but the overall convention is predictable.
75 tools is far beyond a comfortable surface for an accounting-domain MCP; there are also literal duplicate aliases and many near-duplicate document creators (create_act, create_services_act, create_shipment, create_invoice, create_supplier_invoice). The surface is heavy enough to overwhelm tool selection and should be consolidated.
Coverage is deep: schema introspection, document search/get, extensive read analytics (sales, debtors, cashflow, settlement settings), plus writes for most document types, catalogs, and entity updates. Gaps are minor: no hard delete/rollback of documents (only mark_for_deletion), and some entities (e.g. price lists, users) are only reachable via generic update_entity rather than dedicated tools.