Skip to main content
Glama

OpenCode용 Odoo MCP 서버

이 워스페이스에는 자체 호스틸 Odoo 프로젝트의 작업, 채터(chatter), 타임시트를 에이전트가 출출할 수 있는 타입이 지정된 여級 개의 도구로 노출하는 로컬 clo CP 서버 (odoo_mcp)가 들어 있습니다. Aff아 저장소에 есть 원본 odoo_tasks.py CLI이 그대로 유지되어 있으며, 동작은 바지 않았고 MCP 서버와 서비스 층을 박합니다.

사전 준비 사항

  • Python 3.10+ (워크스페이스는 3.12를 기주으로 개발됨)

  • uv on PATH (없Il시 pip install uv)

단, install following:

uv sync

Related MCP server: MCP Server for Odoo

자력 증명(환경 변수)

변수

용도

기본 값

ODOO_URL

내 Odoo 인스턴스의 기본 URL

https://odoo.geosigmgroup

ODOO_DB

데이터베스 이름

odoo

ODOO_USERNAME

로그인 이메일

필수

ODOO_PASWORD

비밀 번호 또 느 외부 API 키

필수

ODOO_URL는 자격 증명 정보가 평문 HTTP를 통해 전송되지 않도록 절대 HTTPS URL이어야 합니다.

API 키 테스트 (Odoo: Preferences → Account Security → New API Key): it is 등록에, 해지 가능 하고 웹 로그인에는 사렇지 못합니다. .env.example를 .env로 복사한 후 작성고 여기에 env 파일들을 자동 로드합니다. OpenCode나 는 이미 설한 환경 변수가 우 순입니다. .env은 절대 커밋하지 마세요.

보간 주의 사항: opencode.json은 {env:VAR} 자리표시자를 사용합니다. 어떤 변수가 없어 OpenCode가 시작할 경우에 빌(обстр), 모든 도구 호出是성인 in zero. (Missing required environment variables: ODOO_USERNAME, ...). Values는 never echo에 logs or results.

OpenCode에 등록

이 워스페이스의 opencode.json에는 이미 다음 내용이 포함되어 있습니다:

{
  "mcp": {
    "odoo": {
      "type": "local",
      "command": ["uv", "run", "python", "-m", "odoo_mcp"],
      "environment": { "...": "{env:ODOO_*} placeholders" },
      "enabled": true
    }
  }
}

OpenCode는 시작 시 구성을 로드합니다. 자격 증명 또는 이 파일을 변환한 후에는 변경 사항이 적용되도록 OpenCode를 종류 고 다시 시작해 주세요. 서버는 세성당 stdio로 한 번만 생성되며, network 포트를 리슨하지 않습니다.

도구

변형 도구는 기본적으로 즉시 실행됩니다**. 각 도구에는 아무 것도 기록하지 않고 미리 보기를 받는 dry_run=true 플래가 있습니다.

도구

하는 일

list_my_tasks

내게 allocated된 작업; 프로젝트/스테이즈/상태/마감일로 필터링

get_task

작업 단 하나의 완 Brooks detail입니다 (예정/전환 시간 포함)

update_task

이름/설명/우선/마감/시간/상태/단계 설정; append_description는 기존 설명에 텍스트를 병합

post_task_message

작업 채터에 게시 (팔로워에게 알림)

get_task_states

서버에서 유효한 워크스테이 상태와 indecator

list_stages

필터링 위한 작업 단계 ID/이름

list_timesheets

my time entry; task or recent days filter

create_timesheet

task의 시간을 기록 (date default today)

update_timesheet

entry의 시간/날짜/설명/task change

State code varies by Odoo build — don't guess it: get_task_states first; inuvalid one is rejected with the valid list.

설치 확인

uv sync                                              # deps resolve
uv run pytest tests -q                               # protocol + service suites
uv run python -m unittest discover -s tests -v       # CLI characterization suite
uv run python odoo_tasks.py --help                   # legacy CLI still intact

stdio handshake itself is covered by tests/test_stdio_smoke.py.

Available Tools

9 tools
create_timesheetA

Log hours worked on a task (defaults to today); returns {"entry_id": id}.

hours must be > 0; date must be YYYY-MM-DD. With dry_run=true returns {"dry_run": true, "vals": {...}} without writing.

Inputs: hours (required), task_id (required), date, dry_run, +1 more.

get_taskA

Fetch one task by id with full detail fields (hours, progress, stage...).

Inputs: task_id (required).

get_task_statesA

List this server's valid task workflow states as {code, label, terminal}.

Inputs: no named parameters. Returns: result

list_my_tasksA

List the caller's Odoo tasks (tasks they are assigned to).

By default terminal states (done/cancelled/closed) are excluded; pass include_done=true to see everything. Optional filters: project_id, stage_id, exact state code, deadline window due_after/due_before (YYYY-MM-DD). limit=0 means no limit.

Inputs: limit, state, stage_id, due_after, +3 more. Returns: result

list_stagesA

List the task stages (project.task.type) available on the server.

Inputs: no named parameters. Returns: result

list_timesheetsA

List the caller's timesheet entries, newest first.

Optional filters: task_id restricts to one task; days restricts to the last N days; limit caps the row count (default 50).

Inputs: days, limit, task_id. Returns: result

post_task_messageA

Post a message to a task's chatter (followers get notified).

Returns {"message_id": id}, or {"dry_run": true, ...} with dry_run=true.

Inputs: message (required), task_id (required), dry_run.

update_taskA

Update mutable fields of a task; executes immediately unless dry_run.

Field args: name, description (replaces), append_description (appends to the existing description after a blank line), allocated_hours (planned effort), progress (0-100; computed field - prefer allocated_hours), priority (0 low .. 3 urgent), deadline (YYYY-MM-DD), state (workflow code from get_task_states), stage (exact stage display name). With dry_run=true returns {"dry_run": true, "vals": {...}} without writing.

Inputs: task_id (required), name, stage, state, +7 more.

update_timesheetA

Modify an existing timesheet entry; returns {"ok": true} on success.

Pass at least one of hours (> 0), date (YYYY-MM-DD), description or task_id (moves the entry, keeping its project consistent). With dry_run=true returns {"dry_run": true, "vals": {...}} without writing.

Inputs: entry_id (required), date, hours, dry_run, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: tasks (get, list, update, message, states) and timesheets (list, create, update), plus stage listing. There is no overlap or ambiguity between tool purposes.

    Naming Consistency5/5

    Tool names follow a consistent verb_noun pattern throughout: get_task, list_my_tasks, update_task, post_task_message, list_stages, create_timesheet, etc. Minor variation between 'get_task_states' and 'list_stages' is natural and still fits the pattern.

    Tool Count5/5

    With 9 tools, the set is well-scoped. Each tool serves a clear purpose within the task and timesheet domain, and the count is in the ideal range for usability.

    Completeness3/5

    Task and timesheet operations cover the main read/update workflows, including states, stages, and messaging. However, there are notable gaps: no create_task, no delete_task, and no delete_timesheet, which prevents full lifecycle management.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables AI assistants to interact with Odoo ERP systems through natural language to search records, create entries, update data, and manage business operations. Supports secure authentication and configurable access controls for production environments.
      Mozilla Public 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to interact with Odoo ERP systems through natural language, allowing users to search, create, update, and manage business records like customers, products, and invoices across any Odoo instance.
      1
      Mozilla Public 2.0
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to interact with Odoo ERP as the authenticated user, with tools for discovery, planning, and mutations bounded by user permissions.
      36
      56 npm
      2
      Apache 2.0
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables authenticated team members to manage Odoo projects, tasks, timesheets, and milestones through Claude, with per-user token-based authentication.
      -