Odoo Claude MCP
Related Servers
Alternatives to Odoo Claude MCP
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceMCP server to connect Claude with Odoo 18, enabling CRUD operations on Odoo models via natural language.2-
- AlicenseNot gradedqualityAmaintenanceAn MCP server that enables AI assistants like Claude to interact with Odoo ERP systems through natural language, allowing users to search, create, update, and manage business data in their Odoo instance.1,571 PyPI384Mozilla Public 2.0
- AlicenseBqualityCmaintenanceConnects MCP clients like Claude to your Odoo ERP, enabling natural language queries, reports, and optional data modifications.923 npmMIT
- AlicenseBqualityAmaintenanceAn MCP server implementation that integrates with Odoo ERP systems, enabling AI assistants to interact with Odoo data and functionality through the Model Context Protocol.41656 PyPI408MIT
- AlicenseAqualityBmaintenanceA version-agnostic MCP server for Odoo that enables AI agents to interact with any Odoo app's data, schema, and source code, supporting tasks like data CRUD, schema mapping, code analysis, and feature implementation.14MIT
- AlicenseDqualityCmaintenanceMCP server for Odoo 18 that provides 85 tools for CRUD operations, business actions, and migration workflows, enabling natural language interaction with Odoo ERP.856MIT
TDQS
Scored across 138 tools
Many tools have clear distinct purposes, but there are several overlapping pairs like odoo_search vs odoo_search_read vs odoo_search_count, odoo_report vs odoo_web_report vs public_access_report_pdf, and odoo_execute vs odoo_web_call. The separation between web-session and XML-RPC tools is subtle and could cause misselection. Some AI and stock tools are also highly specialized, but their descriptions help.
Most tools follow a consistent snake_case prefix_domain_action pattern (e.g., odoo_read, telegram_send_message, google_calendar_list). Some outliers like identify, who_am_i, and open_connection_manager break the pattern but are still readable. Overall the naming is predictable and grouped by domain.
138 tools is far beyond any reasonable scope for a single MCP server. Even for a multi-domain personal assistant, this is excessive and will overwhelm an agent's tool selection. The server would benefit from splitting into separate MCP servers per domain (Odoo, Telegram, Google, AI, etc.).
The tool surface covers a wide range of operations across Odoo (CRUD, web, reports, translations, website snippets, fiscal positions, stock), Telegram, Google (Gmail, Calendar), AI pipelines, and memory. Some minor gaps exist (e.g., no Gmail draft/delete, no Odoo user management), but core workflows are well covered. The sheer number suggests high coverage, though it could be more focused.