No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by rosenvladimirov · MCP Server · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is odoo-claude-mcp safe to install? View the security audit →
Odoo Claude MCP Production-grade Model Context Protocol (MCP) server suite for Odoo ERP Odoo MCP server for Claude Code and Claude.ai — turn any self-hosted Odoo instance (15 → 19) into an AI assistant via the Model Context Protocol. 197+ tools, multi-tenant, Bulgaria localization (НАП, ДДС, ЕИК) included. Connect Claude, Claude Code, and any MCP-compatible client to Odoo, GitHub, filesystem, Portainer, Teams, and more — through a unified, authenticated gateway. Quick Start · Why this vs alternatives? · Use Cases · Architecture · MCP Servers · Companion Modules · Deployment 🇧🇬 Български README See Claude editing a live Odoo sale order — real CRUD, real auto-recalculation  server that enables AI assistants like Claude to securely exe
Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j +
Explore other popular mcp server tools:
odoo-claude-mcp is Self-hosted MCP server connecting Claude to Odoo 15→19 — 197+ tools, multi-tenant, Bulgaria l10n. It is categorized as a MCP Server with 50 GitHub stars.
odoo-claude-mcp is primarily written in Python. It covers topics such as ai-agents, anthropic, bulgaria.
You can find installation instructions and usage details in the odoo-claude-mcp GitHub repository at github.com/rosenvladimirov/odoo-claude-mcp. The project has 50 stars and 15 forks, indicating an active community.
odoo-claude-mcp is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to odoo-claude-mcp on Agent Skills Hub include claude-historian-mcp, odoo-mcp-pro, OmoiOS. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: