Odoo Agency Fleet Review
Fleet-wide Odoo status across many client databases via odoo-mcp cross-instance tools
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 21, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · bdeb21a
Fetched SKILL.md via the GitHub API/raw at skills/odoo-agency-fleet-review/. Frontmatter parses cleanly with name+description; the body references no local files/scripts, only MCP tools, and I confirmed each named tool (list_instances, accounting_health_across_instances, search_across_instances, submit_async_task via src/odoo_mcp/tools_cross_instance.py; receivable_payable_aging, diagnose_odoo_call, search_records via other source modules — 5-8 grep hits each) really exists in the server source. No security smells: it is a read-only cross-instance playbook, no curl|sh, base64, or exfiltration. Trigger phrasings tested (3 activate: "which client has the most overdue receivables across all our Odoo instances", "give me a fleet-wide accounting health status across all client databases", "show a portfolio status of aging AR for every client instance"; 2 do not: "close the books for month-end on our main Odoo company", "fix the data quality issues in our Odoo database" — those route to the sibling month-end/data-quality skills). Output stage NOT run: the skill needs a connected odoo-mcp MCP server plus multiple live client Odoo databases with a multi-instance ODOO_CONFIG_FILE, none of which I can stand up, so no artifact could be produced. Docs: README skill/tool table matches the source; minor inconsistency that the manual clone/npx install lines point at erpipe-org/mcp-odoo while the tested repo is tuanle96/mcp-odoo (appears to be a mirror).
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 5/10
- Docs & honesty 4/5
What Odoo Agency Fleet Review does
A playbook for reviewing many client Odoo databases at once through the odoo-mcp server's cross-instance tools: fleet-wide accounting health, per-client AR aging, and partial-failure triage where one unreachable client is treated as a finding rather than a reason to abort. Triggers when the user asks "which client...", "across all instances/databases", or wants a fleet/portfolio status across 5-50 managed Odoo instances.
How to install Odoo Agency Fleet Review
git clone --depth 1 https://github.com/tuanle96/mcp-odoo.git /tmp/odoo-agency-fleet-review-src
mkdir -p ~/.claude/skills
cp -R /tmp/odoo-agency-fleet-review-src/skills/odoo-agency-fleet-review ~/.claude/skills/odoo-agency-fleet-review
# REQUIRES the odoo-mcp server connected AND a multi-instance config:
# uvx odoo-mcp --setup # prints the MCP client snippet
# export ODOO_CONFIG_FILE=/path/to/odoo_config.multi.json # 'instances' map, see repo odoo_config.multi.json.example
# The skill drives MCP tools list_instances, accounting_health_across_instances,
# receivable_payable_aging, search_across_instances, submit_async_task, diagnose_odoo_call.
# Without the server + live client Odoo databases the skill has nothing to call.
# Marketplace alternative (any skills-compatible agent): npx skills add erpipe-org/mcp-odoo
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Odoo Agency Fleet Review
-
/odoo-agency-fleet-reviewFleet-wide Odoo status across many client databases via odoo-mcp cross-instance tools
It also activates on plain-language prompts like these:
-
Review accounting health across all client databases -
Which client's Odoo instance needs attention -
Show fleet-wide status across our Odoo instances
Frequently asked questions
- Is the Odoo Agency Fleet Review skill free?
- Yes. The skill itself is free from tuanle96/mcp-odoo. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Odoo Agency Fleet Review work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Works with setup. Fetched SKILL.md via the GitHub API/raw at skills/odoo-agency-fleet-review/. Frontmatter parses cleanly with name+description; the body references no local files/scripts, only MCP tools, and I confirmed each named tool (list_instances, accounting_health_across_instances, search_across_instances, submit_async_task via src/odoo_mcp/tools_cross_instance.py; receivable_payable_aging, diagnose_odoo_call, search_records via other source modules — 5-8 grep hits each) really exists in the server source. No security smells: it is a read-only cross-instance playbook, no curl|sh, base64, or exfiltration. Trigger phrasings tested (3 activate: "which client has the most overdue receivables across all our Odoo instances", "give me a fleet-wide accounting health status across all client databases", "show a portfolio status of aging AR for every client instance"; 2 do not: "close the books for month-end on our main Odoo company", "fix the data quality issues in our Odoo database" — those route to the sibling month-end/data-quality skills). Output stage NOT run: the skill needs a connected odoo-mcp MCP server plus multiple live client Odoo databases with a multi-instance ODOO_CONFIG_FILE, none of which I can stand up, so no artifact could be produced. Docs: README skill/tool table matches the source; minor inconsistency that the manual clone/npx install lines point at erpipe-org/mcp-odoo while the tested repo is tuanle96/mcp-odoo (appears to be a mirror).
- What is the Odoo Agency Fleet Review SkillProof Score?
- 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
- How do I install Odoo Agency Fleet Review?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Odoo Agency Fleet Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.