
Mealie MCP Server
io.github.ni-c由 GitHub 帳號 ni-c 發布v0.6.0更新於 Oct 27, 2026
MCP server for Mealie, the self-hosted recipe manager and meal planner
概覽
針對自架 Mealie 的 MCP 伺服器,讓助理搜尋、匯入與編輯食譜、安排餐點計畫並產生購物清單。
- 可以做什麼
- 搜尋、讀取、建立、更新、複製與刪除食譜,包含封面圖片與最近烹調日期
- 預覽並從網址、HTML/JSON 或圖片匯入食譜
- 管理標籤、分類與工具,以及食材和單位,包含合併操作
- 檢視與編輯餐點計畫、今日餐點與隨機餐點
- 建立購物清單、加入或移除食譜項目並編輯清單內容
- 管理食譜集、評分、留言、時間軸事件與分享權杖,並讀取實例資訊
- 適用情境
- 適合自架 Mealie 並希望助理直接處理自己食譜庫的情況:尋找食譜、從網站匯入、整理標籤與分類、安排一週餐點,並把計畫轉成購物清單。
- 執行需求
- 透過 npx 以 stdio 在本機執行(需 Node.js 24 或更新版本),也可使用已發布的容器映像。需要可連線的 Mealie 實例網址(MEALIE_URL),以及 Mealie 設定 → API Tokens 建立的權杖(MEALIE_API_TOKEN)。選用變數可控制語言、唯讀模式、工具篩選與 TLS 處理。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Mealie MCP Server,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
mealie-mcp
[CI]
[OpenSSF Scorecard]
[Socket Badge]
[Glama score]
[npm version]
[container image]
[HTTP via mcp-hub]
[docs]
[sponsor]
A Model Context Protocol (MCP) server for Mealie, the self-hosted recipe manager and meal planner.
Lets MCP clients like Claude Code, Claude Desktop or Codex work with your recipe collection: search and read recipes with their ingredients and steps, import new ones from a website, keep tags and categories tidy, plan meals, build shopping lists from those plans, and record what was actually cooked.
Fifty-three tools is the ceiling, not the floor: MEALIE_ALLOW_TOOLS=essential
registers a curated eight instead, and a model picks the right tool far more
reliably from eight than from fifty-four — see
choosing which tools load.
Mealie's REST API has 259 operations across 175 paths. This server exposes 54
tools, chosen so that the common tasks are one call and the dangerous surface is
not reachable at all. Verified against Mealie v3.28.0; the source of truth for
every request shape is the GET /openapi.json of a running instance, not the
published documentation, which is out of date in several places.
What makes it different
Fifty-three curated tools out of 259 API operations. Mealie's REST API is far larger than a model should reach into; what is here covers the common tasks in one call — search, read and import recipes, keep tags and categories tidy, plan meals, build shopping lists, manage cookbooks and ratings.
update_recipe uses PATCH, not PUT. Mealie's replace route silently drops
recipe fields that were not sent; only the fields you name change here.
The dangerous surface is unreachable. No admin routes, no token minting, no webhooks and no outbound-HTTP triggers, whatever the token would allow.
Requirements
- Node.js 24 or newer
- A Mealie instance and an API token from Settings → API Tokens
Configuration
The two booleans are compared against the literal string true, so a typo leaves
them off — check the startup line on stderr, which reports the mode in effect.
The token is removed from the process environment once it has been read, so child
processes cannot pick it up out of /proc/<pid>/environ.
Choosing which tools load
MEALIE_ALLOW_TOOLS and MEALIE_DENY_TOOLS take comma-separated tool names;
a trailing * matches a whole family. essential is a curated preset of
eight: search_recipes, get_recipe, import_recipe_from_url, create_recipe, get_todays_meals, create_mealplan_entry, list_shopping_lists, add_recipe_to_shopping_list.
An entry that matches no tool aborts startup and names it, so a typo cannot
silently hide a tool — an absent tool is not something anyone traces back to an
environment variable. A filtered tool is never registered, so it is absent from
tools/list and unknown to tools/call alike, exactly like a write tool under
MEALIE_READ_ONLY.
If you run several of these servers at once, mcp-hub
is the other answer — its /hub endpoint replaces every server's tools with six
meta-tools.
Installation
Claude Code
Claude Desktop
The same entry works in any MCP client that takes a JSON config:
Codex
~/.codex/config.toml:
MCP Inspector
To poke at the tools interactively:
Docker
Through mcp-hub
A client that cannot spawn a local process — ChatGPT connectors, Claude on the web,
Cursor, LibreChat — reaches mealie-mcp through mcp-hub: one
container serves many stdio MCP servers over Streamable HTTP, with an OAuth 2.1 login
behind a single password and long-lived tokens for the clients that cannot do OAuth. Its
/hub endpoint puts every server behind six meta-tools, so one connector reaches all of
them without N×tool schemas in the model's context, and it speaks both protocol revisions
— a question this server asks travels through it to the person at the far end.
Its /config/mcp.json uses Claude Code's format, so the entry is the one you already
have:
allowTools and denyTools there are the hub's own per-server filter, which is not
the same thing as *_ALLOW_TOOLS in env — the difference, and the mistake it invites,
are in the client guide.
Tools
Every tool declares an outputSchema and answers with structuredContent
alongside the text block, so a client can use the result without parsing prose.
Nine tools that answered with a sentence — "Deleted the recipe with id …" —
now answer with the fields as well.
Most tools carry untrusted: true and source: "mealie" as fields: recipes are
routinely scraped from arbitrary websites and comments come from other users of
the instance. The eleven without it answer with an id this server was given — or,
for get_about, a version string and the permission flags of the account it
authenticates as, which are facts the model should act on.
Mealie's records are described as open objects with the top-level keys this server builds. A self-hosted Mealie is any release, and the SDK validates each result against its schema before it goes out — a strict shape would turn a field a release adds into a tool that fails outright.
Recipes — search_recipes, get_recipe, suggest_recipes, create_recipe,
update_recipe, parse_recipe_ingredients, duplicate_recipe, set_recipe_image, set_recipe_last_made,
delete_recipe 🔒
Import — preview_recipe_url (dry run, saves nothing), import_recipe_from_url,
import_recipe_from_html_or_json, import_recipe_from_image
Organizing — list_organizers, create_organizer, update_organizer,
delete_organizer 🔒 — each takes kind: tag | category | tool
Ingredients — list_foods, create_food, merge_foods 🔒, list_units,
create_unit, merge_units 🔒, parse_ingredients
Meal plans — list_mealplans, get_todays_meals, create_mealplan_entry,
create_random_meal, update_mealplan_entry, delete_mealplan_entry 🔒
Shopping — list_shopping_lists, get_shopping_list, create_shopping_list,
delete_shopping_list 🔒, add_shopping_list_items, update_shopping_list_items,
delete_shopping_list_items 🔒, add_recipe_to_shopping_list,
remove_recipe_from_shopping_list
Cookbooks — list_cookbooks, get_cookbook, create_cookbook,
delete_cookbook 🔒
Notes and sharing — set_recipe_rating, add_recipe_comment,
delete_recipe_comment 🔒, list_recipe_comments, list_recipe_timeline,
create_timeline_event, list_share_tokens, create_share_token 🔒,
delete_share_token 🔒
Instance — get_about
🔒 asks a person through MCP elicitation — a dialog the model cannot answer on its
behalf. Where the client cannot show one it falls back to a two-call
confirm_token. See
Asking a person.
Recipes can be addressed by slug or by UUID everywhere — Mealie splits its identifier space between the two, and the tools resolve whichever they are given.
Not exposed, on purpose
Everything under /api/admin (backups, restore, maintenance, user, group and
household management, email, AI provider settings), /api/users/api-tokens (a tool
that mints API credentials is privilege-escalation surface), the authentication
routes, user CRUD and passwords, webhooks, event notifications and recipe actions
(all three trigger outbound HTTP from the instance), meal plan rules, migrations,
seeders, invitations, bulk export and ZIP download, and asset uploads. The one
upload route that is exposed is a recipe's cover image, through
set_recipe_image.
PUT /api/recipes/{slug} is not exposed either: it replaces the entire 33-field
recipe object, so a partial update through it silently drops ingredients, steps and
tags. update_recipe uses PATCH.
Safety
- Instance content is untrusted input. Recipes are routinely scraped from
arbitrary websites and comments come from other users, so every tool result that
can contain instance content is prefixed with an explicit marker telling the model
to treat it as data. This matters after the import too: the text stays in the
database and comes back through
get_recipe. - The import tools make Mealie fetch, not this server. URLs are restricted to
http/https, and loopback and link-local hosts are refused — including the cloud metadata endpoints and the hostnames that resolve to them. Addresses are compared numerically, so an IPv4-mapped literal such as[::ffff:169.254.169.254]is caught too, and a hostname is resolved as well — best effort, since a name that does not resolve here is passed on. Private LAN addresses are passed on as of 0.1.2, but Mealie refuses them itself, so such an import fails there rather than here. See SECURITY.md for what the check does not cover, includingimport_recipe_from_html_or_json. - Confirmation prompts quote no upstream text — ids, counts and flags only.
- Responses are bounded: oversized results drop whole items rather than cutting the JSON mid-string, and a response body is never read past 8 MB.
- Redirects are refused so the token cannot be resent to another host.
See SECURITY.md for the trust model and how to report a vulnerability.
Documentation
The full guide, tool reference and security notes live at
mealie-mcp.ni-c.de (source in docs/).
Development
npm run test:integration exercises every tool in the catalogue against a
throwaway Mealie instance in Docker; the recipe for bringing one up is in
CONTRIBUTING.md.
The architecture diagram and the social card are rendered from
docs/assets/architecture.source.svg and docs/assets/og.json by
npm run assets; CI fails if a rendered copy was edited by hand.
Releasing
Everything is driven by a tag; there is no manual publish step.
-
Move the
[Unreleased]section of CHANGELOG.md to the new version and date it. The release workflow extracts that section withawk, so the## [x.y.z]heading shape matters. -
Bump
versioninpackage.json. -
npm run lint && npm run build && npm run test:coverage. -
Commit, then a signed annotated tag:
release.yml then verifies the tag matches package.json, publishes to npm over
Trusted Publishing (OIDC — no npm token exists to leak) with provenance, syncs the
version into both server.json package entries, publishes to the MCP registry, and
cuts the GitHub release from the changelog section. ci.yml pushes the multi-arch
container image to GHCR in parallel.
Contributing
Issues, discussions and pull requests are welcome — see CONTRIBUTING.md. For vulnerabilities please use private reporting rather than a public issue; the policy is in SECURITY.md.
License
MIT © Willi Thiel
來源:README.md,提交 425cf49
工具
0版本歷史
4- v0.6.0最新Oct 7, 2026
- v0.5.1Sep 29, 2026
- v0.5.0Sep 22, 2026
- v0.4.0Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分