odoo-mcp-server
Related Servers
Alternatives to odoo-mcp-server
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceEnables AI agents to connect to Odoo 16+ databases via MCP, providing read tools, diagnostics, schema discovery, and gated write workflow with multi-instance support.41MIT
- AlicenseNot gradedqualityDmaintenanceProvides read-only access to Odoo databases via OdooRPC, allowing AI assistants to query and analyze Odoo data through the MCP protocol.1MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to interact with Odoo data using natural language to search, read, create, and update records. It acts as a secure bridge between MCP clients and Odoo instances version 17.0 through 19.0.11Apache 2.0
- FlicenseNot gradedqualityBmaintenanceEnables AI assistants to securely access and interact with Odoo data through natural language, supporting CRUD operations, attachments, and role-based permissions.-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to safely query live Odoo 19 data with a defense-in-depth security layer, providing read-only tools for partners, sales, inventory, and finance.MIT
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server that enables AI assistants to query Odoo instances via XML-RPC, supporting search, read, count, and field inspection without requiring custom modules.68 PyPI1Mozilla Public 2.0
TDQS
Scored across 5 tools
Each tool has a clearly distinct role: model discovery, schema description, multi-record search, single-record read, and cheap counting. Although count_records overlaps slightly with search_records' total-match behavior, the explicit cost distinction makes the boundary clear.
All tool names follow the same snake_case verb_noun convention: list_models, describe_model, search_records, read_record, count_records. Pluralization is also used predictably for collection vs. single-record operations.
Five tools is a compact, well-scoped set for read-only Odoo data access. Each tool earns its place: discovery, schema introspection, search, single-record read, and count are all non-redundant primitives.
The read-only lifecycle is well covered: model listing, field descriptions, paginated search, single-record read, and counting. Write operations are absent, but the safety-policy wording suggests this is intentional; minor gaps include no binary/attachment read or aggregate/group-by support.