Polymarket and Predict.fun historical tick data, plus backtest quotes and status, over MCP
ZenMoney is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
ZenMoney (Zen-money) finance for AI agents: transactions, reports, budgets, debts
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'ZENMONEY_TOKEN=${ZENMONEY_TOKEN}' --transport stdio krax1337-zenmoney-mcp '--' npx -y mcp-server-zenmoney
# 2 — ask your agent for something these tools do
# get_overview, list_accounts, list_categories and 19 more
It needs ZENMONEY_TOKEN: this reads it from your environment, so export it first.
ZenMoney costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts ZenMoney as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads ZENMONEY_TOKEN (ZenMoney API token, e.g. from https://zerro.app/token) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx ZENMONEY_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'ZENMONEY_TOKEN=${ZENMONEY_TOKEN}' --transport stdio krax1337-zenmoney-mcp '--' npx -y mcp-server-zenmoneyReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: ZENMONEY_TOKEN — ZenMoney API token, e.g. from https://zerro.app/token. You set it in your own client’s config, on your machine — this marketplace never holds it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
22 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Start here. Returns today's date, the user's main currency, net worth, active account balances, this month's income/expenses with top categories, upcoming planned operations and data freshness.
No parameter schema on file.
Accounts with balances, currency, credit limit, bank and flags. balance_main is the balance converted to the main currency. Totals cover in-balance accounts. Debt bookkeeping is in list_debts.
No parameter schema on file.
Category tree (ZenMoney "tags"; one nesting level) with ids, kind (expense/income/both) and number of uses in the last 12 months. Use names, "Parent / Child" paths or ids elsewhere.
No parameter schema on file.
Known payees/merchants ranked by number of transactions, with last date and the category usually used for them. Useful for consistent categorization and payee spelling.
No parameter schema on file.
Find transactions with filters (dates/period, type, accounts, categories incl. subcategories, payee, free text, amount, currency). Newest first by default, paginated. Also returns income/expense totals of all matches in the main currency (in-balance accounts only, like ZenMoney reports), so "how…
No parameter schema on file.
Aggregate expenses and/or income by category, parent category, payee, account or time (day/week/month/year) with totals, counts and shares. measure=both gives income, expense and net per group (cash flow). Transfers and debts are excluded; amounts are converted with current rates. By default only…
No parameter schema on file.
ZenMoney budget for a month: per category budget, actual, remaining, % used and still-planned operations, with subcategories and totals, in the main currency. Uses the profile's month start day. Rollover between months is not modelled.
No parameter schema on file.
Scheduled / recurring operations (ZenMoney reminders) that are still planned in a date range, with recurrence, overdue and forecast flags, plus expected expense/income totals.
No parameter schema on file.
Who owes whom: per-person debt balances from debt operations (positive = they owe you, negative = you owe them), per currency and in the main currency. Pass person to also get their debt transactions.
No parameter schema on file.
Category and merchant suggestions for payee names, from ZenMoney's suggestion service and from this user's own history.
No parameter schema on file.
Pull the latest changes from ZenMoney now (tools already auto-sync when data is older than the configured TTL). full=true re-downloads everything.
No parameter schema on file.
Record one or more transactions (expense, income, transfer between own accounts, debt_out / debt_in with a person). Amounts are positive in the account currency. Without a category, one is picked from this payee's history or ZenMoney suggestions (auto_categorize). Returns the created transactions,…
No parameter schema on file.
Change one or more existing transactions: amount, account, main category (null = uncategorized), payee, comment, date, original currency amount; transfers also to_account / to_amount. The type cannot change (delete and re-create instead). Use list_transactions to find ids.
No parameter schema on file.
Delete transactions by id (soft delete; restore_transactions brings them back).
No parameter schema on file.
Bring back deleted transactions (find them with list_transactions include_deleted=true). ZenMoney cannot undelete in place, so each comes back as a copy with a new id; already-restored ones are skipped.
No parameter schema on file.
Create a category, optionally as a subcategory of a top-level category (ZenMoney allows one nesting level).
No parameter schema on file.
Rename, move (parent null = top level), change kind, budget inclusion, mandatory flag or archive a category.
No parameter schema on file.
Delete a category. Its transactions and planned operations are moved to move_to (merge categories) or, with uncategorize=true, left without this category. Subcategories must be moved or deleted first.
No parameter schema on file.
Set exact monthly budget amounts (main currency) per category, for "total" (overall monthly budget) or "uncategorized". 0 removes that budget. Batch-friendly: e.g. copy last month's budgets to next month.
No parameter schema on file.
Create a cash, card, checking or e-money account. Bank-synced accounts are created by ZenMoney itself.
No parameter schema on file.
Rename, archive/unarchive, include in or exclude from balance, mark as savings, or change the credit limit. To fix a balance use adjust_account_balance.
No parameter schema on file.
Make an account balance match reality by recording the difference as an income or expense correction transaction (computed against freshly synced data).
No parameter schema on file.
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ZenMoney or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (22 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_overview | no tags | |
| list_accounts | no tags | |
| list_categories | no tags | |
| list_payees | no tags | |
| list_transactions | no tags | |
| summarize_transactions | no tags | |
| get_budget | no tags | |
| list_planned | no tags | |
| list_debts | no tags | |
| suggest_category | no tags | |
| sync | no tags | |
| create_transactions | state-write | state-write: declares readOnlyHint: false |
| update_transactions | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| delete_transactions | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| restore_transactions | state-write | state-write: declares readOnlyHint: false |
| create_category | state-write | state-write: declares readOnlyHint: false |
| update_category | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| delete_category | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| set_budgets | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| create_account | state-write | state-write: declares readOnlyHint: false |
| update_account | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| adjust_account_balance | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish ZenMoney can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.