yardstick-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@yardstick-mcpBreak down my spending by category for the last three months."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
yardstick-mcp
Talk to your Yardstick money in plain language. This is an MCP server that lets an AI assistant like Claude read your Yardstick data, so instead of tapping through the app you can just ask: "how much did I spend on eating out last month?", "what's my net worth?", "which subscriptions am I still paying for?"
It runs on your own machine and, out of the box, it can only read: your data goes to your assistant and nowhere else, and nothing can be changed. If you want it to add things for you as well, there's an opt-in switch for that. More on all of this in How your data is handled below, because with a tool that can see your finances you should expect a straight answer before you install anything.
What you can ask
Once it's connected, your assistant can answer things like:
"What's my net worth, and how has it changed over the last year?"
"Break down my spending by category for the last three months."
"How much do I spend at Tesco in a typical month? Is that a lot compared to similar people?"
"List my accounts and their balances."
"Find every transaction over £200 since June."
"How many months of outgoings could I cover from my current balances?"
It can read your accounts, transactions, holdings (assets and liabilities), net worth and your monthly financial vitals. It can never move money or make a payment. By default it can't change anything at all, so there's nothing it can do that you'd need to undo.
Related MCP server: Lunch Flow MCP Server
Before you start
You'll need:
Node.js 20 or newer. Check with
node --version; if you haven't got it, nodejs.org has installers.A Yardstick account.
Install
1. Sign in
npx -y yardstick-mcp loginYour browser opens on Yardstick's normal sign-in page. Approve it, and you'll see a "you can close this tab" message. That's it, you're signed in. Your session is saved under ~/.config/yardstick-mcp/ (readable only by you) and refreshes itself from then on, so this is a one-time step. To sign out again, run yardstick-mcp logout.
2. Connect your assistant
Pick the one you use.
Claude Desktop. Open your config file (Settings → Developer → Edit Config, or ~/Library/Application Support/Claude/claude_desktop_config.json on a Mac) and add:
{
"mcpServers": {
"yardstick": {
"command": "npx",
"args": ["-y", "yardstick-mcp"]
}
}
}Restart Claude Desktop. You'll see the Yardstick tools appear, and you can start asking questions.
Claude Code. One command:
claude mcp add yardstick -- npx -y yardstick-mcpAny other MCP client. Anything that speaks MCP over stdio works the same way: run yardstick-mcp as the command with no arguments. Check your client's docs for where its server config lives.
Not on npm yet? Until the package is published, run it from a checkout instead: clone the repo,
pnpm install && pnpm build, then usenode /path/to/yardstick-mcp/dist/cli.jswherever the instructions above saynpx -y yardstick-mcp.
3. Ask something
Try "what's my net worth?" to check it's working. If the assistant says it isn't signed in, run the login step again; sessions last until you log out or revoke them, but this is the first thing to retry.
Environments
By default the tool talks to production, your real Yardstick account, and if that's you, you can skip this section. For the Yardstick team and testers it can point at staging, uat or local (a dev stack on localhost:8080) instead: add --env <name> to the command, or set env=<name> in the server's environment (handy where env vars are easier to pass than arguments, e.g. claude mcp add yardstick -e env=local -- npx -y yardstick-mcp). The shorthands prod, stage, dev and development also work.
Each environment is its own world with its own sign-in and its own stored session. Sessions are kept side by side, so you can be signed in to several at once and configure them as separate servers:
{
"mcpServers": {
"yardstick": {
"command": "npx",
"args": ["-y", "yardstick-mcp"]
},
"yardstick-uat": {
"command": "npx",
"args": ["-y", "yardstick-mcp", "--env", "uat"]
}
}
}Or in Claude Code:
claude mcp add yardstick-uat -- npx -y yardstick-mcp --env uatSign in to the matching environment first:
npx -y yardstick-mcp login --env uatSign-in works out of the box on all four; each environment's client id is built in (uat and local share one, since they share a sign-in instance).
When it's connected to anything other than production, the server tells the assistant it's looking at test data, so staging numbers don't get presented as your real finances.
The tools
Your assistant picks these automatically; you don't need to name them. For reference:
Tool | What it gives you |
| Assets, liabilities and net worth, broken down by group, class, liquidity and how liabilities are secured |
| Month-end asset totals over time, for charting the trend |
| Your connected accounts with their latest balances |
| Everything on your balance sheet: property, pensions, investments, savings, mortgages, loans |
| One holding in full, with its valuation history and (for a liability) its terms and payments |
| Your transactions, filtered by date, amount, merchant, category or free text |
| Totals grouped by merchant, category, type or period, worked out on the server |
| How much of your history is categorised (so you know how complete an answer will be) |
| Where you spend most, by number of visits and total spend |
| Your spending at one merchant, with an anonymous benchmark of what similar people spend |
| Income and spending by category, month by month |
| Monthly surplus, steady outgoings, wealth added and how many months your savings would cover |
| Search the category list to find the right ones to filter by |
A couple of conventions, in case you're reading the raw output: money comes back both as an exact whole-number amount in minor units (pence) and as a ready-formatted string like £1,234.56, and spending amounts are always positive with the direction shown separately, so "money out" doesn't come through as a negative number.
Letting it add things
There's an optional set of tools for putting things into Yardstick: adding a holding (a property, a pension, a loan) and recording what it's worth. Handy for "add my flat, worth about £250k, I own half of it" rather than filling in a form.
They're off unless you ask for them, because most people install this to ask questions and shouldn't have an assistant able to edit their records by accident. Turn them on with --allow-writes:
claude mcp add yardstick -- npx -y yardstick-mcp --allow-writesor YARDSTICK_ALLOW_WRITES=true in the server's environment. That adds four tools: list_economic_units and get_asset_taxonomy (both read-only, they work out where a holding belongs and which classifications are valid), plus create_holding and add_valuation.
Worth knowing before you switch it on. There's no undo through this tool, so removing something means going into the app. There's also no duplicate protection: creating the same holding twice gives you two of them, so if you're not sure whether something worked, ask the assistant to list your holdings rather than try again. Your assistant should confirm the details with you before each write, and the tools are marked so your client can prompt you for approval; keep those prompts switched on. Still nothing here can move money or make a payment: the strongest thing it can do is add a record to your balance sheet.
How your data is handled
Fair question to ask of anything that can see your bank data. The short version:
It runs on your machine. There's no yardstick-mcp server in the middle. The tool talks straight to the Yardstick API, as you, and hands the results to your assistant.
It's read-only by default. Nothing can be changed unless you opt in to writes, and even then the most it can do is add a holding or record a valuation. It can never spend or move money, and it has no way to delete anything.
You only ever see your own data. The tool signs in as you and sends no account identifier of its own; the Yardstick API decides what you can see from your sign-in alone, exactly as the app does. You can't point it at someone else's account, and it can't accidentally return one either. (This was checked with an independent security review before release.)
No telemetry. The tool phones nothing home. It makes no network calls except to Yardstick and to Yardstick's sign-in provider.
Your session stays local. Sign-in tokens are stored under
~/.config/yardstick-mcp/, in files only your user account can read.
The one judgement that's yours: your assistant sees whatever data it fetches. Connect an assistant you're happy having read your finances, the same way you'd think twice before pasting a bank statement into any app.
Configuration
Most people never need to set any of these; they're here for other environments and advanced setups.
Variable | What it does | Default |
| OAuth client id for sign-in | built in per environment |
| Expose the tools that add holdings and valuations; same as |
|
| Which Yardstick to use: |
|
| Point at a specific API base URL | set by |
| Point sign-in at a specific domain | set by |
| The API version the tool targets |
|
| Only if your OAuth client is a confidential one | none |
| OAuth scopes to request |
|
| Local port the sign-in redirect comes back on |
|
| Use this bearer token as-is and skip sign-in | none |
| A command that prints a bearer token, run when one's needed | none |
| Which OAuth token to send: |
|
| Where the session is stored |
|
| HTTP mode only: this server's public URL | request Host |
Troubleshooting
"Not signed in to Yardstick." Run the login step. If you've moved machines or logged out, you'll need to sign in again there.
The browser didn't open during sign-in. The command also prints the sign-in URL; paste it into a browser yourself.
"Could not listen on 127.0.0.1:33418." Something's using that port. Set YARDSTICK_OAUTH_REDIRECT_PORT to a free one, but note the port has to be registered on the OAuth client, so if you're not the one who set that up, ask whoever did.
The assistant can't see the tools. Make sure you restarted it after editing the config, and that node --version is 20 or higher. In Claude Desktop, Settings → Developer shows whether the server started and any error it hit.
A tool says the session expired. Sign in again with yardstick-mcp login. Sessions refresh on their own, so if this keeps happening, your session may have been revoked on Yardstick's side.
Running a shared server (experimental)
There's also an HTTP mode, for building a hosted connector rather than running per-person on a laptop:
yardstick-mcp serve --http --port 3555It serves MCP over Streamable HTTP at /mcp, and every request has to carry its own bearer token, which is passed straight through to the Yardstick API; the process keeps no credentials of its own. It's experimental: run it behind TLS, and set YARDSTICK_PUBLIC_URL to its real address. docs/AUTH.md has the detail.
Development
pnpm install
pnpm build
pnpm testThe tests run the whole server against a fake Yardstick API, so they need no account and no network. docs/AUTH.md covers how sign-in works and how to set up an OAuth client for testing against staging.
Licence
Available Tools
13 toolsaggregate_transactionsAggregate transactionsARead-only
Group and total transactions server-side: by merchant, category, code and/or one of day/month/year. Returns per-group counts, totalAmountMinor (magnitude of all items) and netAmountMinor (credits minus debits, signed). Minor units; with no period filter the last 3 months are used. The go-to tool for questions like "top categories by spend this quarter" or "monthly spend at Tesco".
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | End of period, exclusive. RFC3339 or "YYYY-MM-DD". | |
| from | No | Start of period, inclusive. RFC3339 or "YYYY-MM-DD". | |
| page | No | ||
| size | No | Page size, default 50, max 200. | |
| type | No | DEBIT = money out, CREDIT = money in. | |
| codes | No | Transaction codes, e.g. DIRECT_DEBIT, TRANSFER, PURCHASE. | |
| query | No | Free-text search across merchant name and description. | |
| sortBy | No | Default: totalAmount. | |
| groupBy | Yes | Grouping keys; at most one of day/month/year. | |
| minItems | No | Only return groups with at least this many transactions. | |
| merchantId | No | ||
| monthStart | No | A single calendar month "YYYY-MM"; alternative to from/to. | |
| categoryIds | No | Only items the user has categorised with these category ids. | |
| hasCategory | No | true = only user-categorised items; false = only items without one. | |
| merchantName | No | Exact merchant name (case-insensitive). | |
| sortDirection | No | Default: desc. | |
| maxAmountMinor | No | ||
| minAmountMinor | No | Minimum amount in minor units (inclusive). Amounts are unsigned. | |
| linkedToHoldingId | No | Only items linked to this holding. | |
| effectiveCategoryIds | No | Only items whose effective category (user-set, else auto-suggested) is one of these ids. |
get_categorisation_statsGet categorisation statsARead-only
How much of the user's transaction history is categorised: counts and minor-unit totals for user-categorised, auto-categorised (suggestion pending) and uncategorised items, split by direction. Useful for judging how complete category-based analysis will be.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
get_holdingGet holding detailARead-only
One holding in full: its valuation history, and for liabilities the terms (rate, term, secured-on links) and recorded payments.
| Name | Required | Description | Default |
|---|---|---|---|
| holdingId | Yes | Holding id from list_holdings. |
get_merchant_summaryGet merchant summaryARead-only
Spending profile for one merchant over a window (1m, 3m, 6m, 1y or all): visits, totals, averages, first/last visit, and an anonymous cohort benchmark of what similar users spend there (null when unavailable). Get merchantId from search_transactions or get_top_merchants.
| Name | Required | Description | Default |
|---|---|---|---|
| window | No | Default: 3m. | |
| merchantId | Yes |
get_net_worthGet net worthARead-only
The user's current net worth: total assets, total liabilities and accessible (liquid) assets, with breakdowns by asset group, asset class, liquidity, liability type and liability security. Values are integer minor units (fields ending Minor) with pre-formatted display strings alongside.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
get_net_worth_historyGet net worth historyARead-only
Month-end asset totals over time (with a by-group breakdown per month), for charting how wealth has changed. Note: history covers assets only; liabilities are not included. Defaults to the last 12 months.
| Name | Required | Description | Default |
|---|---|---|---|
| months | No | Calendar months as "YYYY-MM". Defaults to the last 12 months. |
get_spending_breakdownGet spending breakdownBRead-only
Per-month income and spending totals broken down by category (minor units, with category labels resolved). Only user-confirmed categories are bucketed; everything else is in uncategorised. Views: mine = the user alone, shared = joint finances, partner = partner's share, all = whole household; household views are null for users without a household.
| Name | Required | Description | Default |
|---|---|---|---|
| months | No | Calendar months as "YYYY-MM". Defaults to the last 3 months. |
get_top_merchantsGet top merchantsARead-only
The user's most visited merchants by spend (DEBIT items), with visit counts and category. valueMinor is total spend in minor units over the window.
| Name | Required | Description | Default |
|---|---|---|---|
| month | No | Calendar month "YYYY-MM". Defaults to the last 3 months. | |
| minVisits | No | Only merchants with at least this many visits. |
get_vitalsGet financial vitalsARead-only
The user's monthly financial vitals (minor units): monthlySurplus (incomings, outgoings and what's left), steadyOutgoings (with rolling average), addingWealth (amount moved into savings/investments) and emergenciesCovered (months of average outgoings the month-end cash balance would cover). Each section has {personal, household} views; household is null without one.
| Name | Required | Description | Default |
|---|---|---|---|
| months | No | Calendar months as "YYYY-MM". Defaults to the last 6 months. |
list_accountsList accountsARead-only
The user's connected bank accounts with their latest balances. Pseudo accounts represent manually tracked money rather than a live bank connection.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
list_categoriesSearch categoriesARead-only
Find category ids to filter by. The taxonomy has around 180 entries, so pass query to search it rather than pulling the lot: "eating out", "fuel", "childcare", "rent". The search covers each category's label, description and its built-in search terms, so everyday words find the right one. Add type: "DEBIT" for spending or "CREDIT" for income.
Categories are hierarchical (Group > Subgroup > Leaf) and you filter on the leaf ids. A word like "food" spans several branches (eating out, groceries, takeaways), so check the labels and use every id that fits the question. isNetNeutral marks categories left out of spending analysis, such as transfers between the user's own accounts.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | DEBIT = spending categories, CREDIT = income categories. | |
| query | No | Case-insensitive search across label, description and search terms. Omit only when you genuinely need the whole taxonomy. | |
| includeInactive | No | Also return retired categories. Default false. |
list_holdingsList holdingsARead-only
All holdings on the balance sheet: assets (property, pensions, investments, savings, valuables) and liabilities (mortgages, loans, credit cards). ownershipPercent is the user's share; latestValue is the most recent valuation.
| Name | Required | Description | Default |
|---|---|---|---|
| nature | No | Only return assets or only liabilities. |
search_transactionsSearch transactionsARead-only
Search the user's bank transactions with filters and pagination. Amounts are unsigned minor units; type gives direction (DEBIT = money out). Each item carries its effective category (user-confirmed, else auto-suggested) with a resolved label. For totals over many transactions prefer aggregate_transactions.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | End of period, exclusive. RFC3339 or "YYYY-MM-DD". | |
| from | No | Start of period, inclusive. RFC3339 or "YYYY-MM-DD". | |
| page | No | 1-indexed page, default 1. | |
| size | No | Page size, default 25, max 200. | |
| type | No | DEBIT = money out, CREDIT = money in. | |
| codes | No | Transaction codes, e.g. DIRECT_DEBIT, TRANSFER, PURCHASE. | |
| query | No | Free-text search across merchant name and description. | |
| sortBy | No | Default: date. | |
| merchantId | No | ||
| monthStart | No | A single calendar month "YYYY-MM"; alternative to from/to. | |
| categoryIds | No | Only items the user has categorised with these category ids. | |
| hasCategory | No | true = only user-categorised items; false = only items without one. | |
| merchantName | No | Exact merchant name (case-insensitive). | |
| sortDirection | No | Default: desc. | |
| maxAmountMinor | No | ||
| minAmountMinor | No | Minimum amount in minor units (inclusive). Amounts are unsigned. | |
| linkedToHoldingId | No | Only items linked to this holding. | |
| effectiveCategoryIds | No | Only items whose effective category (user-set, else auto-suggested) is one of these ids. |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
13 tool updates
v0.2.0- First observed
aggregate_transactions - First observed
get_categorisation_stats - First observed
get_holding - First observed
get_merchant_summary - First observed
get_net_worth - First observed
get_net_worth_history - First observed
get_spending_breakdown - First observed
get_top_merchants - First observed
get_vitals - First observed
list_accounts - First observed
list_categories - First observed
list_holdings - First observed
search_transactions
TDQS
Scored across 13 tools
Each tool targets a distinct resource and query type: categorisation stats, net worth, holdings, transactions search vs aggregate, merchant list vs single merchant summary, spending breakdown, vitals, and category lookup. Even closely related tools like get_top_merchants and get_merchant_summary differ clearly by collection vs single entity.
All tool names use a consistent snake_case verb_noun pattern. The verbs are semantically accurate: 'get' for single/computed values, 'list' for collections, 'search' for filtered queries, and 'aggregate' for grouped totals. No mixed conventions or vague names.
With 13 tools, the server is well-scoped for a personal finance analytics domain. Each tool covers a distinct aspect (transactions, holdings, net worth, categories, merchants, vitals) without redundancy or bloat, fitting comfortably in the ideal 3-15 range.
The surface covers the core analytics workflows: transaction search and server-side aggregation, merchant profiling, category discovery, spending breakdowns, net worth with history, holdings detail, and monthly vitals. Minor gaps exist, like no explicit tool for individual transaction details or liability history, but these are not critical for the stated purpose.
Related MCP Connectors
Ask your AI about your own accounts, debts, budgets and goals. OAuth sign-in, read-only by default.
Read-only access to your own bank, card and brokerage accounts for Claude, ChatGPT and other AI agents: balances, transactions, spending, subscriptions, cashflow and investment holdings. It can never move money.
Read-only personal finance for AI agents: budgets, receipts, net worth, bills. OAuth 2.1.
Connect AI agents to bank accounts, transactions, balances, and investments.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to access and analyze MonarchMoney personal finance data through natural language queries. Provides comprehensive financial insights including account balances, transaction analysis, budget tracking, and spending patterns with enterprise-grade security.11MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to access financial data from 20,000+ banks across 40+ countries, allowing users to query account balances, transactions, and spending patterns through natural language.4MIT
- AlicenseAqualityDmaintenanceProvides AI assistants with secure, read-only access to over 15,000 financial institutions across the US and Europe via the Model Context Protocol. It enables users to query account balances, transactions, and spending breakdowns through natural language conversation.5152 npm52MIT
- AlicenseBqualityAmaintenanceEnables AI assistants to interact with YNAB budgets, performing read-only queries by default and optional write operations like creating transactions and managing categories through natural language.45580 npm44MIT