The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Odoo Surface MCP listing page.
User-equivalent Odoo access for AI agents — what the authenticated user can do in their browser, nothing more.
npx — no extra install needed)Add this to your MCP client config (e.g. Claude Desktop claude_desktop_config.json):
Restart your MCP client after saving. npx downloads and runs the package automatically — no further install steps.
.env file (keep credentials out of MCP config)Instead of putting credentials in your MCP client JSON, create a .env file in the directory where you run the MCP:
Remove the env block from the MCP client config — the .env file is loaded automatically.
Since Odoo 14+, users can generate personal API keys that act as a password replacement. Each user generates their own key from their own account — there is no admin-side menu for this.
ODOO_PASSWORD — the actual account password is never storedAPI keys can be revoked individually from the same screen without changing the account password.
Technical users commonly work with more than one Odoo instance (local dev, staging, production). Each instance gets its own named entry in the MCP config — they run as independent processes with fully isolated credentials. The AI client exposes them as separate tool namespaces.
Note: The
.envfile approach (Option A) does not work for multi-instance setups — both processes share the same working directory and would load the same file. Use theenvblock per entry instead.
Registers additional tools: ping, echo, inspect_view, inspect_action, inspect_fields, dump_cache, clear_cache, restart_mcp.
| Layer | Tools |
|---|---|
| Guidance | list_skills, get_skills, find_skill, list_workflows, get_workflows |
| Discovery | get_models, get_model_actions, get_model_interface |
| Planning | get_available_actions |
| Supporting | list_records, get_record, search_records, get_fields, get_defaults, get_filters, list_snippets, get_snippet, list_attachments, fetch_and_upload, translation_get, translation_update, translation_audit |
| Intent | create, update, execute_action, archive, post_message, schedule_activity, set_page_arch, set_page_visibility |
The agent may only do what the authenticated user can do in their browser. Scope is bounded by the user's menus, views, and ACL — nothing more. Tool verbs express functional intent (publish, confirm) rather than raw ORM operations. Discovery is lazy: the agent resolves only what the current prompt requires.
| Layer | Role | When invoked |
|---|---|---|
| 0 — Guidance | Canonical recipes (skills, workflows) the agent consults before any multi-step operation. Pure documentation, no side effects. | Before planning |
| 1 — Discovery | Establishes the bounded universe of models and reachable relations for the current user. | At intent resolution |
| 2 — Planning Bridge | Answers "what is live on this specific record right now" — record-state-aware actions. | Once a record is identified |
| 3 — Supporting | Read-only data fetchers used silently to fill gaps in the agent's plan. | Throughout planning |
| 4 — Intent | Mutating actions that fulfill the user's request — bounded by the user's UI permissions. | Final execution |
Skills and workflows are authored in skills/ and workflows/ as markdown with YAML
frontmatter; they are exposed as Layer 0 tools at runtime.