journalize MCP server
dev.journalize/journalizejournalize.devstreamable-httpv1.0.0Scanned
Agent-native double-entry accounting ledger with x402 micropayments
11 tools: 1 do something that can't be undone, 3 change things and 7 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the journalize MCP server can do
The journalize MCP server is published by journalize.dev, a domain the MCP Registry verified. It has 11 tools. It can do things that cannot be undone, such as sending, paying or publishing (register) and create or change data (3 tools: submit_directive, submit_batch and export_ledger), but cannot delete data. 7 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
11 tools
Can't be undone 1Claude Code: ask
registerGenerate a new Ed25519 keypair for ledger identity.No findings
Why it is in this group
- The description's first verb is "generate": a word for a change.
- The description says "cannot be recovered".
Description, as the server wrote it Generate a new Ed25519 keypair for ledger identity. Returns the private key exactly once — it is never stored server-side and cannot be recovered if lost. This is a SEPARATE keypair from whatever wallet you use to authorize x402 payments (payment auth and ledger identity are two independent signing domains — see payments.py).
Changes things 3Claude Code: ask
export_ledgerExport the full ledger as literal Beancount text — a portable snapshot for fava/bean-report/etc., not the live store.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Export the full ledger as literal Beancount text — a portable snapshot for fava/bean-report/etc., not the live store. Shares a combined free allowance of 2 with get_balance_sheet, get_income_statement, and get_trial_balance (the "report tier") — not 2 free calls for each of those four separately.
submit_batchSubmit up to 1000 directives atomically — all persist together or none do.No findings
Why it is in this group
- The name "submit_batch" says "submit": a word for a change.
Description, as the server wrote it Submit up to 1000 directives atomically — all persist together or none do. Priced 10x a single write, regardless of batch size within the cap. Always paid — the free-trial allowance (see submit_directive) applies to single writes only, never to batches, even if you haven't used any free writes yet. Paid.
submit_directiveSubmit one Beancount directive (open, transaction, close, balance, price, note, document — any type).No findings
Why it is in this group
- The name "submit_directive" says "submit": a word for a change.
Description, as the server wrote it Submit one Beancount directive (open, transaction, close, balance, price, note, document — any type). Paid, except your first 20 accepted writes per registered key, which are free (this specific tool only — submit_batch is always paid, even for your first call). Call with no payment_header first: if free writes remain, this succeeds immediately; otherwise you'll get price/asset/recipient back, so you can retry with payment_header set to your signed X-PAYMENT-equivalent payload (fresh nonce required on the retry — each call is independently signed).
Only reads 7Show 7 read-only tools
get_account_balanceBalance of a single account.No findings
Why it is in this group
- The name "get_account_balance" says "get": a word for reading.
Description, as the server wrote it Balance of a single account. Settles at the same fixed price whether the account exists or not — an "unknown account" answer is still a valid, billable response (no per-error pricing discount). No free-trial allowance for this specific tool, unlike list_directives (same price, but list_directives has 2 free calls and this doesn't) — the free tier applies to browsing (list_directives, list_accounts) and the report tier, not per-account lookups.
get_balance_sheetFull realize() balance sheet — often served from cache.No findings
Why it is in this group
- The name "get_balance_sheet" says "get": a word for reading.
Description, as the server wrote it Full realize() balance sheet — often served from cache. Settles at the same fixed price regardless of cache hit/miss. Shares a combined free allowance of 2 with export_ledger, get_income_statement, and get_trial_balance (the "report tier") — not 2 free calls each.
get_income_statementIncome statement, period-scoped by since/until (ISO date strings, both optional — omitted means whole history).No findings
Why it is in this group
- The name "get_income_statement" says "get": a word for reading.
Description, as the server wrote it Income statement, period-scoped by since/until (ISO date strings, both optional — omitted means whole history). Always books full history first, then clamps the output to the requested period (never filters input dates — see reports.py for why). Shares a combined free allowance of 2 with export_ledger, get_balance_sheet, and get_trial_balance (the "report tier") — not 2 free calls each.
get_trial_balanceTrial balance, period-scoped same as income statement — same underlying compute, priced and audited as its own resource.No findings
Why it is in this group
- The name "get_trial_balance" says "get": a word for reading.
Description, as the server wrote it Trial balance, period-scoped same as income statement — same underlying compute, priced and audited as its own resource. Shares a combined free allowance of 2 with export_ledger, get_balance_sheet, and get_income_statement (the "report tier") — not 2 free calls each.
list_accountsList all opened accounts with their currency constraints and booking method.No findings
Why it is in this group
- The name "list_accounts" says "list": a word for reading.
Description, as the server wrote it List all opened accounts with their currency constraints and booking method. No booking pass involved. Your first 2 calls per registered key are free (a separate allowance from list_directives' and the report tier's — see those tools).
list_directivesList raw directives (optionally filtered by account/date range).No findings
Why it is in this group
- The name "list_directives" says "list": a word for reading.
Description, as the server wrote it List raw directives (optionally filtered by account/date range). No booking involved — cheapest paid tool. `since`/`until` are ISO date strings (YYYY-MM-DD). Your first 2 calls per registered key are free (independent of the write/accounts/report allowances — see list_accounts, get_balance_sheet).
validate_directiveFree dry-run: parse+book text against your full history without persisting or charging anything.No findings
Why it is in this group
- The name "validate_directive" says "validate": a word for reading.
Description, as the server wrote it Free dry-run: parse+book text against your full history without persisting or charging anything. Still requires a valid signature (identity/replay protection is not a billing concern).
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:52 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://journalize.dev/mcp: tools/list returned 11 tools to an anonymous client, including register (irreversible), submit_directive (write), submit_batch (write), export_ledger (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http journalize https://journalize.dev/mcpclaude mcp add --transport http journalize https://journalize.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__journalize__validate_directive",
"mcp__journalize__list_directives",
"mcp__journalize__list_accounts",
"mcp__journalize__get_account_balance",
"mcp__journalize__get_balance_sheet",
"mcp__journalize__get_income_statement",
"mcp__journalize__get_trial_balance"
],
"ask": [
"mcp__journalize__submit_directive",
"mcp__journalize__submit_batch",
"mcp__journalize__export_ledger",
"mcp__journalize__register"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as journalize. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.journalize/journalize/verify?hash=2c9e0ceffdcc1bfbd1979c3ac419da7f5475e11008e1d451c6a25eecdb5a9bf6" | jq -e '.changed == false'Pinned hash 2c9e0ceffdcc, from Nov 15, 2026, 02:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.journalize/journalize/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.journalize/journalize)Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.
journalize MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the journalize MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the journalize MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the journalize MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: register.
What tools does the journalize MCP server have?
- 11 tools: 1 irreversible, 3 write, 7 read. register, submit_directive, submit_batch, export_ledger, validate_directive, list_directives, list_accounts, get_account_balance and 3 more.
Does the journalize MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the journalize MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the journalize MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.