odoo

A set of rules for working with Odoo through an Odoo MCP server. Odoo is business software with records and models for areas such as accounting, sales, and inventory.

In plain words
What is it for?
Use it when querying Odoo models, checking model history or relationships, searching or aggregating records, diagnosing permission errors, or approving changes through the required write process.
Why use it?
It reduces mistakes when discovering Odoo data, handling different server instances, reading records, and making changes safely.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/erpipe-org/mcp-odoo/odoo
Clone the repo
git clone --depth 1 https://github.com/erpipe-org/mcp-odoo
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 236 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00236
Opus 5 $0.00007 $0.00118
Sonnet 5 $0.00003 $0.00047
Haiku 4.5 $0.00001 $0.00024

Measured 3d ago against content hash 6128567e2e25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

odoo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • odoo — 100% identical, 0 lines differ
examples/cursor/rules/odoo.mdc · 20 lines

What it actually says

  • Before guessing any Odoo schema, call get_model_fields (use relevance="top" on wide models) or inspect_model_relationships.
  • If a model name might be outdated (e.g. account.invoice), check it with lookup_model_history first.
  • Never call unlink/write/create directly through execute_method — use the gated workflow: preview_writevalidate_writeexecute_approved_write.
  • When several Odoo instances are configured, pass the instance argument on every tool call; run list_instances to discover them.
  • Prefer search_records with explicit field lists over full-record fetches; use aggregate_records for counts and sums instead of reading rows and adding them up yourself.
  • When a call fails with a permission error, pass the error text to diagnose_access as observed_error instead of retrying blindly.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 20 lines · 14 tokens per session scan A 6128567e2e25

Subscribe to this mod's changes

odoo is a cursor rule published in the GitHub repository erpipe-org/mcp-odoo (400 stars, last pushed 9d ago), licensed MIT. It adds 14 tokens to every session and 236 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.