odoo-mcp-19: Instructions file for Claude Code

CLAUDE.md

odoo-mcp-19 CLAUDE.md is an instructions file for Claude Code from AlanOgic/odoo-mcp-19. It costs 10,821 tokens per session, scanned C, original, MIT.

A project guide for an MCP server that connects AI assistants to Odoo 19, business software, through Odoo's JSON-2 web API. It explains supported tools and resources, authentication, deployment options, dependency limits, and development commands.

In plain words
What is it for?
Use it when developing, testing, deploying, or updating the Odoo connection, its MCP tools, resources, prompts, authentication, or dependency versions.
Why use it?
It clarifies how the server exposes Odoo data and actions and prevents incompatible dependency or protocol changes. It also explains how single-user and multi-user setups differ.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is AlanOgic/odoo-mcp-19's own configuration. It tells Claude Code how to work on odoo-mcp-19 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything odoo-mcp-19 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AlanOgic/odoo-mcp-19. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AlanOgic/odoo-mcp-19/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AlanOgic/odoo-mcp-19

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for odoo-mcp-19 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alanogic/odoo-mcp-19/claude-md/github.svg)](https://agentmods.dev/instructions/alanogic/odoo-mcp-19/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alanogic/odoo-mcp-19/claude-md"><img src="https://agentmods.dev/badge/instructions/alanogic/odoo-mcp-19/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for odoo-mcp-19 CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alanogic/odoo-mcp-19/claude-md"><img src="https://agentmods.dev/badge/instructions/alanogic/odoo-mcp-19/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,821 This file is loaded in full into every session.
When invoked 10,821 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.10821 $0.10821
Opus 5 $0.05411 $0.05411
Sonnet 5 $0.02164 $0.02164
Haiku 4.5 $0.01082 $0.01082

Measured yesterday against content hash 630a687998ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

odoo-mcp-19 CLAUDE.md scanned grade C with 1 finding 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 yesterday.

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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

- **Every positional parameter a method accepts must appear in its `V2_ARG_MAPPING` entry.** `convert_args_to_v2` iterates the supplied args, not the table, and raises `ValueError` on a positional it has no name for — JS
CLAUDE.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

odoo-mcp-19 — Standalone MCP server for Odoo 19+ using the v2 JSON-2 API (POST /json/2/{model}/{method}, Bearer token auth, named args only). No v1 fallback.

  • Version: 1.18.0 · Python: 3.10+ · MCP: 2025-11-25 (FastMCP >=3.4.6,<4; cryptography>=42 is a direct dependency of token_crypto, not just a transitive Authlib one; anyio>=4 is a direct dependency of the event-loop offload in server.py / resources.py)
  • The <4 ceiling is deliberate. FastMCP 4.x targets MCP spec 2026-07-28 and is not a drop-in — see docs/mcp-2026-07-28-migration.md and tests/test_dependency_pins.py, which fails the build if the bound is widened or the environment drifts. uv.lock is gitignored (.gitignore: "project uses pip + pyproject.toml") — it pins only your local .venv, never the documented pip install git+… path, so pyproject.toml is the only thing between a fresh install and FastMCP 4.x. Do not relax the ceiling on the strength of the lockfile.
  • Surface: 5 tools, 38 odoo:// resources, 19 prompts (12 generic + 7 cyanview-* workflow skill prompts)
  • Discovery is via resources, action is via tools — there is no list_models tool, agents read odoo://models instead.
  • Two deployment shapes: single-user (STDIO or HTTP with one static MCP_API_KEY) and multi-user HTTP (per-user cv_odoo_… keys from the CLORAG-managed registry, personal Odoo clients, per-user skill visibility — see "Multi-user mode" below).

Development commands

# Install (local workflow — uv-managed .venv; uv.lock is deliberately gitignored, the project ships via pip + pyproject.toml)
uv sync --extra dev
# then prefix commands with `uv run`, e.g.:
uv run pytest tests/test_safety.py
# pip equivalent: pip install -e ".[dev]"

# Install as a package (installs the `odoo-mcp-19` console entry point) — deliberately NOT on PyPI
pip install git+https://github.com/AlanOgic/odoo-mcp-19.git

# Run server — STDIO (default); loads .env from cwd
python -m odoo_mcp

# Run server — HTTP (requires MCP_API_KEY *or* USERS_DB_PATH, else sys.exit(1))
MCP_TRANSPORT=streamable-http MCP_API_KEY=<token> python -m odoo_mcp

# Interactive setup wizard — generates .env, Docker cmd, Claude Desktop config
python -m odoo_mcp --setup

# Tests — unit (no Odoo needed)
uv run pytest tests/ --ignore=tests/live
uv run pytest tests/test_safety.py::TestClassifyOperation::test_safe_methods_are_safe   # single test
# Note: bare `pytest tests/` collects NO live tests (they are __main__-guarded scripts with no test_* functions),
# but it does *import* them, and their module-level load_dotenv() pushes real .env credentials into os.environ
# for the whole session. Always --ignore=tests/live.

# Tests — live (requires .env with real Odoo creds; script-style runners)
python tests/live/test_safety_live.py
python tests/live/test_v1110_live.py
python tests/live/test_locked_mode_live.py

# Format + lint + typecheck
black . && isort .   # both clean; isort has skip_gitignore=true so it skips venvs like black does
ruff check .         # known baseline: 26 errors (20 E501, 6 E402) — see below
mypy src/odoo_mcp    # known baseline: 51 errors, mostly [index]/[assignment] in resources.py + server.py

# If `uv run pytest` reports ModuleNotFoundError: No module named 'odoo_mcp' (17 collection
# errors), the dev extras are not installed — run `uv sync --extra dev` first. uv also ignores a
# VIRTUAL_ENV pointing anywhere other than ./.venv (it warns and uses .venv regardless), so an
# activated sibling venv silently gives you a system pytest/ruff/mypy or none at all.

# Docker
docker build -t odoo-mcp-19 .
docker compose up -d           # uses .env, requires MCP_API_KEY
# Multi-user overlay (on the clorag host — registry mounted read-only)
docker compose -f docker-compose.yml -f docker-compose.multiuser.yml up -d

Read the full file on GitHub · 350 lines

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. yesterday Changed · +29 lines · +1,637 tokens per session 630a687998ef
  2. 4d ago Changed · +22 lines · +912 tokens per session scan A → C ed40090034f7
  3. 5d ago Changed · +30 lines · +1,283 tokens per session 1fd2dce65cdb
  4. 9d ago First seen · 269 lines · 6,989 tokens per session scan A 626904144f72

Subscribe to this mod's changes

odoo-mcp-19 CLAUDE.md is an instructions file published in the GitHub repository AlanOgic/odoo-mcp-19 (10 stars, last pushed yesterday), licensed MIT. It adds 10,821 tokens to every session, about $0.0541 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens