OurFamilyWizard MCP
A Model Context Protocol server that connects Claude to OurFamilyWizard, giving you natural-language access to your co-parenting messages, calendar, expenses, and journal.
README
OurFamilyWizard MCP
A Model Context Protocol server that connects Claude to OurFamilyWizard, giving you natural-language access to your co-parenting messages, calendar, expenses, and journal.
[!WARNING] AI-developed project. This codebase was entirely built and is actively maintained by Claude Sonnet 4.6. No human has audited the implementation. Review all code and tool permissions before use.
What you can do
Ask Claude things like:
- "Show me my recent OFW messages"
- "What's on the kids' calendar next week?"
- "List recent expenses and tell me what I owe"
- "Add a journal entry about today's pickup"
- "Draft a reply to the last message from my co-parent"
Requirements
- Claude Desktop
- Node.js 22.5 or later (
node:sqliteis the cache backend) - An active OurFamilyWizard account
Acknowledgement of Terms
By using this MCP server, you acknowledge and agree to the following:
1. This server accesses your own OurFamilyWizard account. Auth happens via your own credentials. It does not — and cannot — access your co-parent's account, your children's accounts, or anyone else's.
2. OurFamilyWizard's Terms govern your use of this server, just as they govern your direct use of OFW. There is no explicit anti-scraping clause; the governing language is broader:
Users may not obtain or attempt to obtain any materials or information through any means not intentionally made available.
And on credentials: "You are solely responsible for (1) maintaining the strict confidentiality of assigned Authentication Methods, (2) instructing any individual to whom the assigned Authentication Method is shared ('Authorized User') to not allow another person to use the Authentication Method." OFW does contemplate "Authorized Users" and third-party-enabled integrations — but the account holder remains responsible.
You are agreeing to those terms — read by the maintainer 2026-05-23 — every time you invoke a tool in this server.
3. Personal, family use only. This project is not affiliated with, endorsed by, sponsored by, or in partnership with OurFamilyWizard, LLC or its parent. It is a personal automation tool for the named account holder. Do not use it on behalf of a co-parent without their consent, do not share credentials with anyone, and do not use it to bulk-extract another family's data.
4. OFW is a court-of-record platform. Messages, expenses, calendar entries, and journal entries on OFW may be entered into legal proceedings — including custody, divorce, and parenting-plan-modification cases. Anything this server writes to OFW (drafts you save, events you create, expenses you log) will appear with the same legal weight as if you had typed it yourself. Do not let this MCP send a message, create an event, or log an expense that you have not read and approved. Review every write operation before confirming.
5. You accept full responsibility for any consequences — both technical (account warnings, suspension) and legal (anything OFW records about your account activity). The MCP author is not your attorney; if you're using OFW in connection with an active legal matter, talk to your actual attorney before automating anything.
This section is the maintainer's good-faith summary of the terms — it is not legal advice and does not modify or supersede OurFamilyWizard's actual ToS.
Installation
1. Clone and build
git clone https://github.com/chrischall/ofw-mcp.git
cd ofw-mcp
npm install
npm run build
2. Add to Claude Desktop
Edit your Claude Desktop config file:
- Mac:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the ofw entry inside "mcpServers" (create the key if it doesn't exist):
{
"mcpServers": {
"ofw": {
"command": "node",
"args": ["/absolute/path/to/ofw-mcp/dist/index.js"],
"env": {
"OFW_USERNAME": "your-email@example.com",
"OFW_PASSWORD": "your-ofw-password"
}
}
}
}
Replace /absolute/path/to/ofw-mcp with the actual path where you cloned the repo. On Mac, run pwd inside the cloned directory to get it.
3. Restart Claude Desktop
Quit completely (Cmd+Q on Mac, not just close the window) and relaunch.
4. Verify
Ask Claude: "What does my OFW dashboard look like?" — it should show your unread message count, upcoming events, and outstanding expenses.
Authentication
ofw-mcp tries three auth paths in order; whichever succeeds first is used. Existing setups keep working unchanged.
- Env-var credentials (legacy, recommended for Claude Desktop). Set
OFW_USERNAME+OFW_PASSWORDand the server logs in via OFW's form endpoint. This is the path shown in the Claude Desktop config above. - fetchproxy fallback (no env vars needed). When the credentials are absent, the server reads
localStorage["auth"]once at startup from your already-signed-inourfamilywizard.comtab via the fetchproxy browser extension. After that one read, all OFW API calls go directly from Node — the extension is not in the request hot path. Install the fetchproxy extension (Chrome Web Store / Safari.dmg), sign into OurFamilyWizard once, and the MCP just works. If you have multiple OFW accounts and want them to use separate caches, setOFW_CACHE_IDENTITYto a label per profile. - Error. If neither path is available, the server tells you exactly which fix to apply. Set
OFW_DISABLE_FETCHPROXY=1to skip the fetchproxy fallback entirely (turns missing credentials into a hard error — useful in headless CI).
Credential options (env-var path)
Option A — env block in Claude Desktop config (shown above, recommended):
"env": {
"OFW_USERNAME": "your-email@example.com",
"OFW_PASSWORD": "your-ofw-password"
}
Option B — .env file in the project directory:
cp .env.example .env
# edit .env and fill in your credentials
Environment variables always take priority over the .env file. You can also pass them directly on the command line:
OFW_USERNAME=you@example.com OFW_PASSWORD=yourpass node dist/index.js
Hosted connector (Cloudflare Worker)
Instead of running ofw-mcp locally, you can add it to claude.ai as a remote MCP connector — a hosted Cloudflare Worker you reach from Settings → Connectors on Claude web, desktop, or mobile (connectors sync across all three). The same tool registrars back both targets, so the tools and behaviour are identical to the local stdio install; the Worker just wraps them with @chrischall/mcp-connector (the shared OAuth + streamable-HTTP harness) and a per-user Durable Object cache in place of the local SQLite file.
- How you connect. Each person you share the connector URL with logs in through the connector's own OAuth page with their own OurFamilyWizard email and password. Those credentials are stored (encrypted at rest) per user because OFW bearer tokens expire after ~6h with no refresh token, so the connector must be able to re-login on its own. One user can never see another's account or cache.
- Attachments are inline-only. The Worker has no local filesystem, so
ofw_download_attachmentalways returns content as MCP content blocks (OFW_INLINE_ATTACHMENTS=true) rather than writing to disk. Spreadsheets, PDFs and Office documents come back as extracted text/CSV, so they are readable even though the host cannot render the file itself. - Write mode defaults to
all. The hosted connector registers every tool by default, configurable per deployment viaOFW_WRITE_MODE/OFW_CALENDAR_WRITESinwrangler.jsonc— see Write protection. - Message sync is bounded and resumable. To stay under Cloudflare's per-request subrequest cap,
ofw_sync_messageson the hosted connector caps how many OFW requests one call makes (OFW_SYNC_MAX_REQUESTSinwrangler.jsonc, default40) and resumes across calls, so a large mailbox backfills over multipleofw_sync_messagescalls rather than one; the local stdio server is unbounded. Seedocs/DEPLOY-CONNECTOR.md.
Standing this up requires a Cloudflare account and is a one-time setup for whoever hosts it; after that the deploy-connector job in release-please.yml deploys each release automatically (and Actions → deploy-connector → Run workflow deploys any ref on demand) — see docs/DEPLOY-CONNECTOR.md for the full runbook. wrangler.jsonc serves the Worker at a custom domain (https://connector.ofw.nullnet.app/mcp) plus the account's *.workers.dev URL; whoever hosts it uses their own domain. The local stdio / .mcpb install above remains the desktop-only alternative if you'd rather run it against just your own account.
Available tools
Read-only tools run automatically. Write tools ask for your confirmation first. The Write mode column shows the minimum OFW_WRITE_MODE a tool needs to be available at all — see Write protection below.
| Tool | What it does | Permission | Write mode |
|---|---|---|---|
ofw_get_profile |
Your profile and co-parent info | Auto | any |
ofw_get_notifications |
Dashboard counts (unread messages, upcoming events, outstanding expenses) | Auto | any |
ofw_list_message_folders |
Folders with unread counts — get folder IDs here before listing messages | Auto | any |
ofw_list_messages |
Messages in a folder | Auto | any |
ofw_get_message |
Full content of a single message | Auto | any |
ofw_sync_messages |
Sync messages into the local cache (unread bodies left unfetched to avoid read receipts) | Auto | any |
ofw_get_unread_sent |
Sent messages a recipient hasn't read yet (from local cache) | Auto | any |
ofw_check_freshness |
Cheap live check that the cache still matches OFW — per id, whether it is still a draft or was sent/deleted, without a full sync |
Auto | any |
ofw_status |
One live call for "where does everything stand?" — the full verified draft inventory, and the current state of any ids or draft keys | Auto | any |
ofw_download_attachment |
Download a message attachment to disk, or inline as extracted content / bytes | Auto | any |
ofw_send_message |
Send a message | Confirm | all |
ofw_list_drafts |
Draft messages | Auto | any |
ofw_save_draft |
Create or update a draft | Confirm | drafts |
ofw_delete_draft |
Delete a draft | Confirm | drafts |
ofw_upload_attachment |
Upload a local file to My Files; returns a fileId to attach via ofw_send_message/ofw_save_draft |
Auto | drafts |
ofw_list_events |
Calendar events in a date range | Auto | any |
ofw_create_event |
Create a calendar event | Confirm | all (or drafts + OFW_CALENDAR_WRITES) |
ofw_update_event |
Update a calendar event | Confirm | all (or drafts + OFW_CALENDAR_WRITES) |
ofw_delete_event |
Delete a calendar event | Confirm | all (or drafts + OFW_CALENDAR_WRITES) |
ofw_get_expense_totals |
Expense summary totals | Auto | any |
ofw_list_expenses |
Expense history | Auto | any |
ofw_create_expense |
Log a new expense | Confirm | all |
ofw_list_journal_entries |
Journal entries | Auto | any |
ofw_create_journal_entry |
Create a journal entry | Confirm | all |
Data freshness (OFW_FRESHNESS_TTL_SECONDS)
Message and draft reads are served from the local cache, which means a result can look authoritative while being minutes or months out of date. The cache also cannot detect some changes on its own: editing a draft in the OFW web app bumps no timestamp at all, so "nothing changed" and "we didn't look" are indistinguishable unless the server says which happened.
So every read tool (ofw_list_messages, ofw_list_drafts, ofw_get_message, ofw_list_message_folders, ofw_sync_messages) returns a freshness block alongside its data:
"freshness": {
"source": "cache",
"asOf": "2026-07-20T12:40:00.000Z",
"ageSeconds": 5231,
"staleness": "unverified",
"lastServerSyncAt": "2026-07-20T13:59:00.000Z",
"syncComplete": false,
"historyComplete": true,
"warning": "Served from cache last verified 87 min ago; the last sync did not finish checking drafts. Re-read before asserting current state — call ofw_check_freshness for a cheap live confirmation, or ofw_sync_messages to refresh."
}
staleness is fresh only when the data was fetched live in that call, or verified against OFW within the threshold by a sync that actually reached that folder. It degrades to unverified when it ages out or a sync skipped the folder, and stale when the folder has never been checked at all. Anything other than fresh always carries a human-readable warning stating the age and the reason. The bias is deliberate and one-directional: a false unverified costs one extra call, whereas a false fresh lets remembered state be narrated as present fact.
Drafts additionally carry per-item cacheStatus, asOf, and serverConfirmed — true only when a completed drafts walk verified them inside the threshold. serverConfirmed: false means a draft's existence and unsent status are remembered, not known, and should not be stated as current fact without calling ofw_check_freshness first.
ofw_check_freshness is the cheap way to re-verify: one request for a folder count comparison plus one per message id, no bodies, no full sync. Draft ids are compared by content revision, not timestamp, for the reason above. It probes ids that are cached as drafts, as sent messages, or as already-read inbox messages freely, because none of those can change anything; any other id would mark an unread inbox message as read on OurFamilyWizard — an irreversible change to a court-visible record — so those are skipped unless you pass allowMarkRead: true.
Set OFW_FRESHNESS_TTL_SECONDS to tune the threshold (default 300, i.e. 5 minutes). Unusable values fall back to the default rather than widening the window.
Is it still what I think it is? (ofw_status)
Freshness answers how old is this data. It does not answer is this entity still what I think it is — and that is a different failure. A draft that has been sent still exists on the server, so "does this id exist?" comes back true for the one case where the answer matters most.
ofw_status is the call that should back any status summary:
{
"checkedAt": "2026-07-28T09:12:00.000Z",
"requested": [
{ "id": 538279699, "state": "sent", "sentAt": "2026-07-27T23:31:09", "inSync": false },
{ "id": 538086428, "state": "draft", "inSync": true }
],
"complete": true
}
stateisdraft,sent,received,deletedorunknown, read live from OFW.unknownmeans the question was not answered — it is not a synonym for "fine".- With no arguments it returns the full draft inventory, verified against OFW first.
complete: truemeans every part of the snapshot was confirmed live. If it is false,incompleteReasonssays what wasn't, and the payload is not a basis for stating a count.
Draft keys. Editing a draft mints a new OFW id every time (ofw_save_draft replaces by create-then-delete, because OFW's update-in-place endpoint silently no-ops). ofw_save_draft therefore also returns a draftKey that stays constant across every edit and follows the message into Sent. ofw_status(draftKeys: ["dk_…"]) resolves it to the current id and state — including state: "sent" with sentMessageId — so "what happened to the draft I was working on?" is one call, not a guess about which id is current.
Absence is never reported from a stale cache
A cached read that comes back empty is shaped identically to a verified "nothing there". ofw_list_messages, ofw_list_drafts and ofw_get_unread_sent therefore refuse rather than answer when the result is empty and the backing cache is not fresh:
{
"result": "UNVERIFIED_EMPTY",
"reason": "No drafts were found, but the backing cache is \"unverified\" — it was last verified 207 min ago. Refusing to report absence from unverified data…",
"remedy": "Call ofw_sync_messages(folders:[\"drafts\"]) and retry, re-call with autoRefresh:true, or use ofw_status(includeDraftInventory:true) for a single live answer.",
"complete": false
}
A false negative ("no, that was never sent") is more dangerous than a refusal, because it reads as a definitive answer. Non-empty results are never withheld — a stale cache that did find something is still evidence of presence, labelled with its age as before. Pass autoRefresh: true (or set OFW_AUTO_REFRESH=true) to have the tool sync and answer instead of refusing; a refresh that still cannot make the read verifiable refuses anyway.
Every list read also carries an explicit complete boolean describing the result set — "this is every matching item on OurFamilyWizard as of asOf" — with a completeNote naming what is missing when it is false. Check it before stating a count.
Write protection (OFW_WRITE_MODE)
The "Confirm" permission above is a hint to the MCP host — a host configured to auto-approve tools (or a user who clicked "always allow" once) would leave nothing between model output and a sent message. Because OurFamilyWizard is a court-of-record platform, the server also supports a structural gate: set OFW_WRITE_MODE in the server's env block and tools above your chosen level are never registered, so no host setting or prompt-injected instruction can invoke them.
OFW_WRITE_MODE |
What's available |
|---|---|
none |
Read/sync/search only. No write tools exist. |
drafts |
Adds draft-level writes: ofw_save_draft, ofw_delete_draft, ofw_upload_attachment. Nothing that lands on the court-visible record — the AI prepares, only a human signed into the OFW web UI can send. |
all |
Everything (the default — fully backward compatible). |
Unrecognized values fail closed to none, with a warning on stderr — a typo never silently grants write access.
Reading is a write, too (OFW_ALLOW_MARK_READ)
Fetching a message body for the first time marks it read on OurFamilyWizard and stamps a "First Viewed" timestamp your co-parent can see. That is part of the record and cannot be undone — and it happens as a side effect of an ordinary read, so OFW_WRITE_MODE does not govern it.
By default nothing changes: reads behave exactly as they always have. Two controls exist if you want them:
| Setting | Effect |
|---|---|
ofw_get_message(allowMarkRead: false) |
Refuses a fetch that would stamp an unread inbox message, returning a structured MARK_READ_BLOCKED payload instead. Cached bodies, sent messages and already-read messages still return normally — none of them can stamp anything. |
OFW_ALLOW_MARK_READ=false |
Deployment-wide ceiling. No tool may stamp: ofw_get_message refuses, ofw_check_freshness / ofw_status ignore allowMarkRead:true, ofw_sync_messages ignores fetchUnreadBodies:true. A per-call argument cannot raise it. |
OFW_FETCH_UNREAD_BODIES=true flips ofw_sync_messages to fetch unread bodies by default (off unless set) — useful where read receipts are routine. It is capped by OFW_ALLOW_MARK_READ.
Calendar opt-in (OFW_CALENDAR_WRITES)
Calendar events sit between the two message tiers: they have no draft stage (a created event is immediately visible on the shared record), but unlike a sent message they are reversible — an event can be edited or deleted afterward. If you run in drafts mode but are comfortable with direct calendar writes, set OFW_CALENDAR_WRITES=true to additionally register ofw_create_event, ofw_update_event, and ofw_delete_event. The flag is redundant in all mode and never overrides none.
Troubleshooting
"0 messages" — Claude may have read the notification counts rather than the actual messages. Ask explicitly: "List the messages in my OFW inbox" or "Use ofw_list_message_folders then ofw_list_messages".
"OFW auth: set OFW_USERNAME + OFW_PASSWORD, or install the fetchproxy extension…" — neither auth path is configured. Either fill in the env block in your Claude Desktop config, or install the fetchproxy extension and sign into ourfamilywizard.com in your browser.
"fetchproxy fallback failed" — the env-var path wasn't configured and the extension couldn't be reached. Confirm the fetchproxy extension is installed, signed into OFW, and that it's running (open the extension popup). If you want to disable the fallback entirely, set OFW_DISABLE_FETCHPROXY=1.
403 Forbidden — wrong credentials. Verify your username/password at ofw.ourfamilywizard.com.
Tools not appearing in Claude — go to Claude Desktop → Settings → Developer to see connected servers and any error output. Make sure you fully quit and relaunched after editing the config.
Can't find the config file on Mac — in Finder press Cmd+Shift+G and paste ~/Library/Application Support/Claude/.
Security
- Credentials live only in your local config file or
.env - They are passed to the server as environment variables and never logged
- The server authenticates with OFW using the same login flow as the web app
- Use a strong, unique OFW password
Development
npm test # run the vitest suite
npm run build # tsc → dist/, then esbuild bundle → dist/bundle.js
npm run dev # node --env-file=.env dist/index.js (requires built dist)
Main is protected. All changes land via PR — open with gh pr create --label <release-notes-label> and add ready-to-merge once you're satisfied with the auto-review feedback. See CLAUDE.md for the full PR + release flow.
Project structure
src/
index.ts MCP server entry (McpServer + StdioServerTransport)
client.ts OFW HTTP client with Bearer token + 401/429 retry
auth.ts resolveAuth(): env-var creds → fetchproxy → error
auth-password.ts Spring Security form login (legacy env-var path)
cache.ts SQLite cache (messages, drafts, attachments, sync state)
sync.ts Folder ID resolution + per-folder sync logic
config.ts Cache dir, attachment dir, env parsing
tools/
_shared.ts Recipient mapping, response helpers, path expansion
user.ts ofw_get_profile, ofw_get_notifications
messages.ts Folders, list, get, send, drafts, sync, attachments
calendar.ts List, create, update, delete events
expenses.ts Totals, list, create
journal.ts List, create entries
tests/ Mirrors src/; mocks OFWClient.request via vi.spyOn
Auth flow
Auth resolution lives in src/auth.ts. Three paths, in priority order:
- Env vars present →
src/auth-password.tsdoes the legacy OFW Spring Security form login:GET /ofw/login.form— establishes a session cookiePOST /ofw/login— submits credentials, returns{ auth: "<token>" }
- Env vars absent (and
OFW_DISABLE_FETCHPROXYunset) →@fetchproxy/bootstrapreadslocalStorage["auth"]+localStorage["tokenExpiry"]once from the user's signed-inourfamilywizard.comtab, then closes the bridge. - Nothing configured → throws with both fixes spelled out.
Either path returns a Bearer token to OFWClient, which then operates from Node with Authorization: Bearer <token> — fetchproxy is not in the request hot path. On 401 the client re-resolves auth and replays once. Tokens are cached for 6h (env-var path) or until tokenExpiry (fetchproxy path).
Also see the fetchproxy README for extension install instructions.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。