This MCP server connects Actual Budget to Claude, enabling spending analysis and safe writes. The description states that delete operations are previewed and require confirmation before execution. The readme excerpt indicates npm availability, MIT licensing, and a Node.js requirement of version 20 or higher.
🛠️ Key Features
Spending analysis for Actual Budget data
Safe write behavior with delete previews and an approval step
Integrates Actual Budget with Claude via Model Context Protocol
🚀 Use Cases
Reviewing spending before making changes in Actual Budget
Confirming deletions through a preview/ask-first workflow
⚡ Developer Benefits
MCP server packaging for integration with Claude
Explicit safety behavior for destructive actions (preview + confirm)
⚠️ Limitations
Documentation excerpt is truncated and does not list additional tools or supported operations beyond safe deletes and spending analysis.
Talk to your budget. An MCP server that connects Actual Budget to Claude. Ask where the money went, get real analysis back, and let it write without holding your breath.
Asking a budget where the money went, and a delete that stops to ask for confirmation
Features
Real analysis, not just lookups - Projections, category trends, budget vs actual, and month summaries
Writes you can trust - Every delete previews what it will remove and waits for you to confirm; ACTUAL_READ_ONLY=1 hides the write tools from the model entirely (Safety)
Multi-currency that survives reality - Splits and residual reconciliation, not just a currency symbol
Recovers from an out-of-sync budget - repair_sync rebuilds the local sync state when @actual-app/api and your server disagree, the failure that otherwise leaves every tool erroring
Ask about your budget in plain language - "How much did I spend on food this month?" or "Am I over budget on anything?"
Create and manage transactions - Add expenses, transfers, and edits without opening the app
Manage categories, payees, and rules - Full CRUD without opening the app
Use names, not IDs - Say "Wallet" instead of a1b2c3d4-..., with helpful suggestions if ambiguous
Natural dates in English and Spanish - "last month", "este mes", "hace 3 meses", "yesterday"
Clean formatted output - Aligned tables and clear summaries, not raw JSON
Clear error messages - If something's wrong, you'll know exactly what to fix
Does it work with local models?
Yes. This is an MCP server, so it works with any client that speaks MCP, and the model
behind that client is the client's business, not this server's. Claude Desktop, Claude
Code, Cursor and VS Code are the ones documented below because they are the ones people
ask about, but anything that can run an MCP client, including a local setup pointed at
Ollama or LM Studio, talks to it the same way.
Your budget data goes to whatever model your client uses. If that matters to you, and for
a lot of people running Actual it does, a local model keeps it on your machine.
Does it work with ChatGPT?
No. ChatGPT's connectors only accept remote MCP
servers: a public HTTPS endpoint speaking SSE or Streamable HTTP. With
HTTP mode this server can be one. What we have read says their
connectors sign in through OAuth or not at all and cannot send the fixed token header
this version takes, and nobody here has tried it.
OpenAI does offer a tunnel for local servers, but it is limited to enterprise plans.
Making it work would mean exposing your Actual server to the internet, which is the
opposite of what most people running Actual want. Anything that can start a local MCP
process works instead: Claude Desktop, Claude Code, Cursor, VS Code, Gemini CLI, or your
own setup pointed at a local model.
If what you actually want is OpenAI's model, use Codex, which does run MCP servers
locally over stdio. Option 6 is the one command it takes.
The Desktop Extension needs nothing but Claude Desktop. It runs on the Node
that Claude Desktop ships, and the bundle carries a SQLite binary for every
platform it supports, so nothing is compiled either. Checked on Windows 11
with Claude Desktop 2.110.0 and Node removed from the machine.
Quick Start
On Claude Desktop, the shortest path is the
extension: no config file
to edit and no command to run. Otherwise, copy this into Claude Code or Claude
Desktop:
bash
Install the actual-budget-mcp MCP server from npm (https://github.com/henfrydls/actual-budget-mcp).
Configure it with these credentials:
- My Actual Budget server: http://localhost:5006
- Password: YOUR_PASSWORD
- Budget ID: YOUR_BUDGET_ID
Claude will configure everything for you.
Installation
Option 1: Claude Desktop extension (no config files)
A packaged Desktop Extension is available: install it and Claude Desktop asks
for your server URL, password and Sync ID in its own settings UI, with the
password and session token stored in your operating system's keychain rather
than a config file you have to edit.
On Windows, dragging is the way in: double-clicking the file opens Windows'
"select an app to open this file" dialogue instead, because Claude Desktop does
not register the .mcpb file type. Verified on a clean Windows 11 install with
Claude Desktop 0.14.10.
The extension carries everything it needs, so the first question you ask is
answered straight away rather than after an install you cannot see. It is a
large download, once, with a progress bar.
You do not need Node.js installed for this route. Claude Desktop runs the
extension on the Node it ships with. Checked by renaming Node out of the way on
a Windows 11 machine and asking a question anyway: the server started and
answered.
Earlier builds launched the package from npm instead. That made the download
small and moved it to the first run, where nothing showed progress: Claude
Desktop waited, decided the server was dead and said it could not connect, and
the extension started working on its own a few minutes later. The bundle now
includes Actual's SQLite binary for every platform it supports. They are N-API
binaries, so one per platform serves every Node version, and nothing has to be
chosen at startup.
Updating the extension
Installing a new version over an old one keeps the settings you filled in, with
one exception seen in practice: the saved server password was cleared when a
field's title changed between versions. If Claude cannot connect after an
update, open the extension's settings and check the password field before
looking anywhere else.
The button installs it with placeholder values. Open Cursor Settings > MCP
afterwards and replace the three: your server URL, your password, and your
budget's Sync ID. To do it all by hand instead, go to Cursor Settings > MCP >
Add new MCP server and add:
Codex has no extension or bundle format, so this one-liner is the shortest route
there is. codex mcp list shows it afterwards, and codex mcp remove actual-budget-mcp undoes it.
This is Codex the local agent, the CLI and the IDE extension. Codex in the
browser runs on OpenAI's machines and cannot reach an Actual server on your
network.
Option 7: Docker
The image speaks stdio like every other option, so your client starts the
container and owns its lifetime:
Inside the container, localhost is the container. Your Actual server is
not there. host.docker.internal (with the --add-host flag above, which is
what makes it resolve on Linux) reaches the host instead.
Mount /data. That is the budget cache. Without a volume, every start
re-downloads your entire budget from the server.
Option 8: From source (for contributors)
bash
git clone https://github.com/henfrydls/actual-budget-mcp.git
cd actual-budget-mcp
npm install
cp .env.example .env# Edit with your credentials
npm run build
npm run test:connection # Verify it works
Verify your setup
--verify reads the environment of the shell you run it in, and the install options above
put your credentials in your MCP client's configuration instead. So set them for the
command:
It connects, downloads the budget and prints how many accounts and category groups it
found. Running it without those variables reports them as missing, which is about the
command, not about your install.
After changing your client's configuration, restart the client. Claude Desktop, Claude
Code and the rest read MCP configuration at startup and will not pick up an edit until
they are restarted.
Running it for days at a time
Most clients start this server when you open them and stop it when you close
them, and nothing below matters. If you run it as a process that stays up, an
always-on chat bot or a service, it does.
The server downloads your budget once at startup and keeps a local copy. Before
every read, whether you asked through a tool or read actual://accounts, it
pulls whatever the Actual server has that the copy does not, so an edit you
make in the Actual app shows up in the next question you ask. You do not have
to restart it, and you do not have to run a bank sync to shake it loose.
Three limits keep that from costing a round trip on every call:
A copy pulled less than 60 seconds ago is treated as current, so a burst
of questions syncs once. Any sync counts, including the one a write does
before deciding whether to write.
A read waits at most 20 seconds for the pull. Past that it answers from
the local copy rather than hanging, and says so.
After a pull that fails or runs past that deadline, the next 60 seconds
of reads answer straight from the local copy instead of trying again. A
server that is down would otherwise charge every read the full wait, one
after another.
When the pull does not happen, because the Actual server is down, unreachable
or simply slow, the reply ends with a line saying it could not refresh, how old
the figures are, and what went wrong:
code
Could not refresh from the Actual server; these figures are from the last
sync, 14 minutes ago. Anything changed in the Actual app since then may be
missing. Reason: The budget's sync state is out of sync with the Actual
server, so no operation can run until it is repaired. Run the `repair_sync`
tool to rebuild the sync state (non-destructive), or repair it in the Actual
app under Settings > Show advanced settings.
That line is the point of it. A server that is down otherwise goes back to
answering with figures from hours ago and nothing says which. The reason is
there because these do not all want the same thing done about them: a network
blip clears on its own, an out-of-sync budget has to be repaired, and a refused
login needs your credentials looked at.
Writes are not affected: they already pull before the checks that decide
whether to write, so they do not pay for a second one.
Each client needs its own ACTUAL_DATA_DIR. Two processes sharing one local
copy will corrupt it, and a long-lived server makes that easier to do by
accident, because it is there all day for a second client to point at.
Running it over HTTP
By default this server speaks stdio: the client starts it, talks to it over
the pipe, and stops it. That works when the client runs on the same machine.
When it does not, set ACTUAL_HTTP_PORT and the server listens instead.
Setting that port is what asks for HTTP. Nothing changes for anyone who does
not set it, and the rest of the variables are read only once it is.
Two paths, two credentials
Path
What it offers
/mcp
the read tools, whatever the process is otherwise allowed to do
/mcp-write
every tool, and it is served only when ACTUAL_HTTP_WRITE_TOKEN is set
A write tool is not registered on the read path, so it cannot be called,
talked into being called, or spent context on. It is the same choice
ACTUAL_READ_ONLY makes, applied per path, and it means the default is a
deployment that cannot change anything: without a write token there is no
write path to find.
The two tokens have to differ. One credential for both paths is the same as
having one path, so the server says that and does not start.
The usual ACTUAL_SERVER_URL, ACTUAL_PASSWORD and ACTUAL_BUDGET_ID are read
the same way as over stdio.
openssl rand -hex 16 gives 32 characters, which is the shortest token this
server will start with. The server binds to 127.0.0.1, prints one line
saying where it is, and nothing outside the machine can reach it.
A tunnel is the shortest way to reach the server from a phone or from a
client that is not on your network. Both of these open an outbound
connection, so nothing is forwarded into your network, and both terminate
TLS for you. Keep the server on 127.0.0.1 and let the tunnel reach it
there. The address the tunnel prints is what a client connects to, and the
token still has to be sent with every request.
bash
cloudflared tunnel --url http://127.0.0.1:3000
That is a quick tunnel: no account, no domain, and a trycloudflare.com
address that lives as long as the process and changes every run. Cloudflare
says it is for trying things out. For something you keep, create a named
tunnel and point it at the same port.
bash
tailscale funnel --bg 3000
Funnel has to be turned on for the tailnet first, in its settings. --bg
keeps it running after the terminal closes.
Both of these were checked against their own documentation in October 2026.
They change; the addresses and flags above are worth a look before they are
copied.
On a local network
Binding anywhere other than loopback is refused unless you say that is what
you meant:
This server does not terminate TLS. Over plain HTTP on a local network
the token is sent in the clear, in a header, with every request, and anyone
who can see the traffic can read it and then read your budget. On a network
you do not control, put a reverse proxy or a tunnel in front and let it do
the encryption.
ACTUAL_HTTP_ALLOWED_HOSTS is the list of host names the server answers,
without the port: budget.local, not budget.local:3000. The server takes
the name out of the Host header and compares only that, so an entry with a
port matches nothing and every request comes back 403. Set it whenever you
bind wide: it is what keeps a page in a browser from reaching the server
through a name that resolves to your machine.
What it refuses
Refused
Why
A request with no token, or the wrong one
The token stands for the whole budget. It is compared in constant time, so a wrong one does not say how much of it was right
A token under 32 characters, before the port is opened
Nothing here limits how fast a token can be guessed
A request carrying an Origin header
No browser is a legitimate client of this server, and that header is how a page would try
A Host header that was not asked for
This is the DNS rebinding protection the MCP specification asks for
Binding off loopback without ACTUAL_HTTP_ALLOW_REMOTE
See the warning above
Everything that is wrong with the configuration is printed at once, before
anything is opened, so a deployment is not corrected one line and one restart
at a time.
Tool results are never written to the log, at any level. What this server
returns is your budget, and a log is a copy of it that nobody meant to keep.
Reaching it from claude.ai
A custom connector takes an HTTPS address, for example
https://budget.example.com/mcp. The token goes in Request headers, with
the scheme included, as Bearer <token>, together with No sign-in.
Anthropic's documentation says that Request headers section is in beta
and available to some organisations only. Where it is not there, a static
token cannot be sent and this version of the server has no other way in:
sign-in through OAuth is #273
and is not in this release.
chat offers the 18 everyday tools instead of all 44. Defaults to full. See Choosing a toolset
ACTUAL_HTTP_PORT
No
Serve MCP over HTTP on this port instead of stdio. Nothing else below is read until it is set. See Running it over HTTP
ACTUAL_HTTP_TOKEN
No*
The credential for the read path. *Required once ACTUAL_HTTP_PORT is set, and at least 32 characters
ACTUAL_HTTP_WRITE_TOKEN
No
A second credential, for the write path. Without it the server serves no write path at all
ACTUAL_HTTP_HOST
No
What to bind to. Defaults to 127.0.0.1
ACTUAL_HTTP_ALLOW_REMOTE
No
Set to 1/true/yes to bind somewhere other than loopback. Nothing here terminates TLS
ACTUAL_HTTP_ALLOWED_HOSTS
No
Host names to accept, comma separated and without the port, for a server that is not on loopback
Using a session token (OIDC servers)
If your Actual server signs you in through OIDC, there is no password to put in
ACTUAL_PASSWORD, because the server issues a session token instead. Set
ACTUAL_SESSION_TOKEN to that token and leave the password unset.
To find it, in the browser where you are signed in to Actual:
Open your browser's developer tools
Go to Application (Chrome/Edge) or Storage (Firefox)
Expand IndexedDB → the actual database → the asyncStorage store
Copy the value of the key user-token
It is stored in IndexedDB, not Local Storage, so looking there is why people
often cannot find it.
Treat the token like a password: it grants the same access. It also expires; if
it does, the server says so and tells you to issue a new one, rather than
blaming a password you do not have.
Which URL and port
It depends on how you run Actual, and picking the wrong one gives a connection
error that does not explain itself:
How you run Actual
URL
Self-hosted sync server (Docker, a VPS, etc.)
http://localhost:5006, or wherever you host it
The desktop app
http://localhost:5007
The desktop app runs its own sync server on port 5007, and only while the app
is open. Close the app and nothing is listening, so the server cannot connect.
That embedded server also binds to 127.0.0.1 only. It is reachable from the
same machine and from nowhere else, so if Claude runs somewhere other than the
machine with the app, for example another computer or a virtual machine, you need
an SSH tunnel or a port forward. Pointing at the host's LAN address will not
work.
Where the cache is kept
Unless you set ACTUAL_DATA_DIR, the budget cache goes to the standard data
directory for your system:
OS
Default location
Linux
$XDG_DATA_HOME/actual-budget-mcp, or ~/.local/share/actual-budget-mcp
macOS
~/Library/Application Support/actual-budget-mcp
Windows
%APPDATA%\actual-budget-mcp
It is a cache, not your data: deleting it only forces a fresh download on the
next run. It lives outside the temp directory on purpose, so a reboot does not
throw it away and make the next startup re-download your whole budget.
Finding your Budget ID
Open Actual Budget
Open Settings: click the arrow next to your budget name, or use the sidebar, More, then Settings
Click Show advanced settings
Copy the Sync ID
Take the Sync ID, not the Budget ID. Actual shows both, one under the other, and they
are both UUIDs. ACTUAL_BUDGET_ID wants the one labelled Sync ID, despite the name of
the variable. Using the other one gives you Budget "..." not found on the server, which
reads as though you mistyped it when the value was simply the wrong field.
If Sync ID shows (none), that budget has never been synced to a server. This server
talks to Actual through its sync server, so a local-only budget cannot be used until you
sync it.
Privacy Policy
Data collection. This server collects nothing. It has no telemetry, no
analytics and no usage reporting, and none is planned: it reads personal
finances, and a tool that does that should not be phoning home. There is no
account to create and nothing to opt out of.
Usage and storage. The server talks to one place: the Actual Budget server
whose URL you configure. Your budget is cached on your own machine, in the data
directory documented under Where the cache is kept,
so that it does not have to be downloaded on every start. Nothing is written
anywhere else.
Your credentials are handled by your MCP client, not by this server. Claude
Desktop stores the password and session token in your operating system's
keychain; the server receives them as environment variables at launch, uses them
to connect, and never writes them to disk.
Third-party sharing. None. No data is sent to the author, to any analytics
service, or to any third party. The only network connection the server opens is
to your own Actual server.
Two things worth naming because they are also true: the model you are talking to
(Claude, or whichever client you use) necessarily sees the budget data you ask
about, under that provider's own terms; and installing via npx downloads the
package from npm, which is an ordinary package download and involves no budget
data.
Data retention. The cache lives on your machine until you delete it. Deleting
it loses nothing, since it is a copy of what is on your Actual server; the next
run downloads it again. Uninstalling the server leaves nothing behind except
that directory, which you can remove.
Transactions this server writes carry an id it generates
Every transaction, split and transfer created through this server is given a
UUID before it is sent, and that id is what the server uses to find the row
again if the write reports an error. It is the transaction's own id, not
imported_id, so Actual's deduplication of imported files still works on these
rows exactly as it does on any other.
Nothing about this is visible in Actual, and it changes nothing for you. It is
documented because it is a real difference from writing the same transaction by
hand.
Safety
Three things protect your budget from an agent acting on a vague instruction.
Deletes preview before they delete
Every delete tool refuses to destroy anything on the first call. It reports what
would be lost and stops there. Deleting takes a second, deliberate call:
The preview covers every row that can be deleted, which is the point of it:
dated ahead of today, older than the rest of the budget, one part of a split,
or in a closed account. Those four used to preview as blank and delete anyway,
so the guard was asking you to confirm nothing. An id that matches no
transaction is now refused rather than reported as deleted.
Tools that find their target by name (delete_account, delete_category,
delete_category_group, delete_payee) also require confirm_name with the
exact name. That is where deleting the wrong thing actually happens: asking for
"Adicionales" can resolve to "Ingresos Adicionales". Tools that take an exact id
(delete_transaction, delete_rule) need only confirm: true.
A transaction that already exists is not created twice
create_transaction looks before it writes. If the account, the date and the
amount all match something already in the budget, it creates nothing and shows
you what is there:
code
create_transaction(account: "Checking", amount: -50, date: "2026-06-05")
→ A transaction like this one already exists, so nothing was created:
2026-06-05 -50.00 Checking Claro
id: 0b6d516e-...
Same account, same date, same amount. If this is a second, genuine payment
rather than the same one recorded twice, call again with allow_duplicate: true.
create_transaction(account: "Checking", amount: -50, date: "2026-06-05", allow_duplicate: true)
→ Transaction created
Two identical coffees on one card on one day are a real thing, so the flag
exists and one extra call is the whole cost. This is a change from 0.9.x, where
the second call created a second row without saying anything.
The check syncs first, so it sees what another client wrote and not only what
this one did. That is the case it is for: two agents against one budget, neither
able to see the other. reconcile_currency_residual takes the same flag, for
the same reason, and syncs before reading the balance it computes from.
It is not returned as an error. The delete tools set isError on their
preview so that a repeated call cannot destroy anything by accident. This one
does the opposite, deliberately: a repeated call creates nothing at all, and an
agent that reads isError treats being asked as being refused and retries,
which is what duplicates. Deletes flag; this one does not.
What it costs. One extra round trip per create_transaction, whether or not
a duplicate is found. Against a server on the same machine that is not
measurable. Against a remote server it roughly doubles the time per write:
measured at 80 ms of round-trip latency, 87 ms becomes 171 ms for a single
create, and 22 creates in a row go from 1.9 s to 3.8 s. Passing
allow_duplicate: true skips the sync as well as the check, so a bulk import
that has already been deduplicated elsewhere pays nothing.
Offline and hung servers. If the sync fails the check still runs against the
local copy and the write is not blocked, so an offline session keeps working
with a weaker check rather than no writes. It says so on stderr, with the
reason, so a weakened check is never silent.
A server that accepts the connection and then never answers used to be the slow
case: the Actual library sets no timeout of its own, so the call fell back to
Node's own five-minute header timeout, and there are two places that can happen,
before the write and after it. ACTUAL_HTTP_TIMEOUT_MS, below, now ends those
waits at 60 seconds by default (#99).
What it does not catch:
A rule that rewrites the amount or the date of the row as it is stored,
since the stored row then no longer matches what was asked. Renaming rules,
the common kind, make no difference to it.
A transaction that arrives between the check and the write. The sync
narrows that window; it does not close it. This looks before it writes, which
is not the same as doing both at once.
create_transfer and create_split_transaction, which do not run the check
yet, and an opening balance from create_account. Tracked in #98.
reconcile_currency_residual and rows that are not marked cleared
It compares against every transaction in the account up to today, which is what
it has always done. A bank statement generally shows only what has posted, so
if the account holds rows nobody has ticked off, the two figures may not be
measuring the same thing.
It does not decide that for you. It reports it:
code
Currency residual reconciled:
Account: Card (USD)
Was: -120.00
includes 1 row not marked cleared, -20.00
cleared rows alone come to -100.00, and against that
figure the adjustment would have been 100.00.
Check which of the two the balance you gave is measuring.
Target: 0.00
Adjustment: 120.00
Nothing appears when every row is marked cleared.
Comparing against the cleared rows instead was considered and measured against
a real budget first. Most rows that were not marked cleared turned out to have
been sitting there for weeks, and none of them had come from a bank: they were
rows nobody had ticked off, not items in flight, which clear in a day or two.
Reconciling against the cleared figure would have booked all of that as an
adjustment into a residual category, which is the failure this is about reached
from the other side. So the figure stays as it is and you get both numbers.
reconcile_account, which writes nothing, reads the same two numbers and takes
balance_counts to choose between them.
reconcile_currency_residual and dates
It refuses a date in the future for the adjustment it writes. Its whole promise
is to bring the account to the balance the bank reports now, and a row that
takes effect later does not do that. It also could not be made to behave: the
balance counts transactions up to today, so a future-dated adjustment never
entered it and every run booked another one.
"Today" here is the server's today. A client in a timezone ahead of the server
can be told its own date is in the future; omitting date, or passing "today",
uses the same clock as the check and always works. create_transaction has no
such restriction, so recording a purchase dated ahead, which is what you want
when a card posts a weekend purchase on the next business day, still works
there.
When the account holds transactions dated after today, it asks which they
are. Actual's balance stops at today; your bank's figure may not. A card
purchase made at the weekend is commonly posted with the following business
day's date, so the bank has already counted something the balance has not, and
the difference would otherwise be booked as currency drift.
So reconcile reports those rows and books nothing until you say which reading
you gave it:
code
reconcile_currency_residual(account: "Card", target_balance: -140, category: "Cashback")
→ No adjustment was booked for Card.
This account holds 2 transactions dated after today, so the balance Actual
reports and the balance your bank reports are not measuring the same thing.
2026-09-28 -40.00 WEEKEND-PURCHASE (came from the bank, so the bank counts it)
2026-10-26 -80.00 SCHEDULED-LATER
Balance to today: -100.00
Those rows come to: -120.00
Balance counting them: -220.00
You said the bank says: -140.00
Which is it?
future_rows: "exclude" the bank has not posted them yet.
Adjustment would be -40.00.
future_rows: "include" the bank has posted them already, ...
Adjustment would be 80.00.
The choice is yours, because in general nothing says which a row is. Where
something does, it is said: a row that arrived from the bank is one the bank
obviously counts, and a row entered here and not reconciled may be one it has
not seen. Neither settles it, both narrow it. Rows are listed oldest first, so
the nearest one, the one most likely to have been posted, is the first you read.
Accounts with nothing dated ahead are unaffected and never see the question. A
row dated exactly today counts as present, not as ahead, because the balance
already includes it.
Whichever you choose is recorded on the adjustment itself, as
FX residual adjustment (counting 2 transactions dated after today), so a row
booked on the wrong reading can be found later instead of being a puzzle.
Measured before this existed: an account at -100.00 to today, a -40.00 purchase
dated ahead that the bank had posted, a -80.00 transfer scheduled for later that
it had not, and a bank figure of -140.00. It booked -40.00 and left the account
summing to -260.00 where the bank ends at -220.00. The adjustment was exactly
the purchase, recorded a second time, in a category that calls it drift.
It also refuses a date that does not exist, such as 2026-09-31 or
2026-02-30, rather than calling it a future one. Other tools still accept an
impossible date and store it verbatim; that is older than this and unchanged.
It also syncs three times on the happy path: once before reading the balance,
once inside the create it delegates to, and once to push. Two of those are
consecutive pulls, so a remote server pays a redundant round trip.
Read-only mode
Set ACTUAL_READ_ONLY=1 and the server exposes only the 17 read, analysis and
repair tools. The write tools are not registered at all, so they never
appear in tool discovery, and an agent cannot be talked into calling something it
cannot see.
repair_sync stays available on purpose: it repairs sync state rather than
budget data, and hiding it would leave a desynced budget with no way to recover.
Writes are enabled by default. Read-only is opt-in.
More than one budget
One budget is the default and needs nothing: ACTUAL_BUDGET_ID is the sync id
of the budget this server opens, and no tool asks which budget a call is for,
because there is nothing to choose.
ACTUAL_BUDGET_IDS lists every budget the server serves, comma separated,
when there is more than one. Two things appear when it is set, and only then:
A tool called list_budgets, which names them by the sync id a caller
passes, with the open ones marked. A budget's own name is inside its file,
so it appears once the budget has been opened at least one time, and stays
afterwards: one that has never been opened is listed by id alone. It lists
what you configured and nothing else: a budget on the account that is not
in the list cannot be reached by asking for its id.
An optional budget_id on every tool. Left out, a call is for the budget in
ACTUAL_BUDGET_ID.
The Actual library opens one budget per process, so the server opens a child
process per budget and routes each call to the one that holds it. Three stay
open at once by default, and a fourth budget closes the one that went longest
without a call, never one with a call in flight. A budget that goes 15 minutes
without a call closes on its own. ACTUAL_BUDGET_WORKERS and
ACTUAL_WORKER_IDLE_MINUTES change those two numbers.
Opening a budget takes about a second on a small file, so the first call for a
budget waits. If it is still not open after ACTUAL_WORKER_READY_SECONDS, the
call answers that the budget is still opening and asks you to try again, rather
than hanging past the client's own one minute timeout. For a write, the answer
says that nothing was sent to the budget, so repeating it cannot write twice.
When every budget this server keeps open is busy, a call for another one
waits for room and is then told that everything is busy, in the same words
and with the same promise: nothing was read or written, and nothing was sent.
A write that takes longer than this server waits for one is the other way
round, and says so plainly: the worker is still applying it, so check the
budget before repeating it rather than sending it twice.
list_budgets is where a deployment with several budgets finds out what it
is talking to. Each budget is listed with the name its own worker read out of
the file, [open] while a worker holds it and (closed) once that worker
has gone, and a budget nobody has opened yet is listed by its id alone. If a
worker found that your Actual server and this server's Actual library differ
on major or minor, the line says which budget that was and both versions, and
one sentence at the end says what it means. Nothing refuses to open over it:
Actual's minor is the month, so a server that updates itself is a minor ahead
of this one every time Actual releases.
The resources (actual://accounts and the other two) are not offered when
there is more than one budget. A resource is a URI and nothing else: it has
nowhere to say which budget it is about, and answering from the default one
would be a second, quieter answer that contradicts the tools. The tools take
budget_id, so they are the one way to ask.
Each budget gets its own directory under ACTUAL_DATA_DIR, named after its
sync id, so the ids have to be ids: a list with a path in one of them is
refused at startup rather than writing a budget cache somewhere else. Two
processes cannot share one budget cache. If more than one of the budgets is
encrypted, ACTUAL_ENCRYPTION_PASSWORDS maps sync id to password:
Each budget is given its own password and nothing else: the map itself never
reaches the processes that open the budgets. With one encrypted budget,
ACTUAL_ENCRYPTION_PASSWORD on its own still works.
Both the tool and the parameter cost context on every connection, so neither
appears when there is one budget. Measured with two budgets configured, the
full set goes from 39.7 KiB to 47.6 KiB of tool descriptions, which is 7.9 KiB
more, a fifth again. With ACTUAL_BUDGET_IDS unset, what a client is sent is
byte for byte what it was sent before any of this: no extra tool, no extra
parameter, and no child process.
Serving them to more than one client
Several budgets and HTTP mode are the same
deployment in practice: one server somewhere that several people, or several
clients, point at. The two work together without anything new. The read path
and the write path are the same process, the budget each call is for is the
budget_id it names, and which tools exist is decided per path, so a
credential that may only read cannot write in any budget rather than in some
of them.
What a worker is started with is built rather than inherited, which matters
once this runs in a container: TZ, the proxy variables and the certificate
paths are passed down, because they are facts about the machine and a budget
is full of dates, while the HTTP port and its credentials are not, because a
worker has no door of its own.
The volume is the point of the whole file. ACTUAL_DATA_DIR is /data in
the image, each budget gets its own directory under it, and without
somewhere to keep them every restart downloads every budget again. Binding
the port to 127.0.0.1 keeps it on the host; ACTUAL_HTTP_HOST=0.0.0.0 is
about the inside of the container, where 127.0.0.1 would be unreachable
from anywhere, and ACTUAL_HTTP_ALLOW_REMOTE=1 is this server asking you to
mean it. Off loopback it also wants ACTUAL_HTTP_ALLOWED_HOSTS: the
hostnames clients put in the Host header, without ports, since the
check ignores the port. Get it wrong and every request comes back 403 Invalid Host, which is the failure that looks like a broken token. Both
tokens are at least 32 characters.
In Kubernetes
The same thing, with four things worth knowing before you write the manifest:
One replica. Two processes sharing one budget cache is what drives a
budget out of sync, so a second replica on the same volume does not share
it: it steps aside to a directory of its own and downloads everything
again. If you need more throughput, give each replica its own volume and
its own budgets, not a copy of the same ones.
The image runs as uid 1000 (node), so the volume needs
securityContext: {runAsUser: 1000, fsGroup: 1000} or the first write to
/data fails.
Probe the port, not a path. Every path answers 401 without a
credential, by design, so a tcpSocket probe is the honest one. An
httpGet probe works too if you treat 401 as healthy.
Size it per budget that stays open.ACTUAL_BUDGET_WORKERS is how many
processes hold a budget at once, each one a Node process with a budget in
it, so the memory this needs is that number times one budget, not one.
ACTUAL_HTTP_ALLOWED_HOSTS is the names clients actually use, without
ports: the Service name inside the cluster, and whatever host an Ingress
answers to. The Secret holds ACTUAL_PASSWORD,
ACTUAL_HTTP_TOKEN,
ACTUAL_HTTP_WRITE_TOKEN and, if your budgets are encrypted,
ACTUAL_ENCRYPTION_PASSWORDS. strategy: Recreate rather than a rolling
update, for the same reason there is one replica: during a rollout the old
pod still holds the volume.
Choosing a toolset
Every connection is sent the whole tool list before anything is asked. Measured
with scripts/measure-toolset.mjs, which registers the real tools and asks a
real client for tools/list:
ACTUAL_TOOLSET
Tools
tools/list
full (default)
44
39.7 KiB
chat
18
17.4 KiB
chat with ACTUAL_READ_ONLY=1
8
5.7 KiB
full with ACTUAL_READ_ONLY=1
17
12.5 KiB
chat is the everyday set: reading the budget, recording and categorising
transactions, and moving budgeted money between categories. What it leaves out
is setting up and repairing a budget, which is creating and deleting accounts,
categories, groups, payees and rules, along with reconcile_currency_residual
and repair_sync.
It is worth setting for two reasons, and the second is the bigger one: the
context is spent whatever the conversation turns out to be about, and a model
choosing between 44 descriptions picks the wrong tool more often than one
choosing between 18.
The prompts go with the tools they call. Each one is a short script naming
three or four tools, so a prompt whose tools are not offered is not offered
either. With chat that leaves none of them, and a server with no prompts
does not advertise prompts at all: prompts/list answers that the method is
not supported, rather than with an empty list.
The two settings narrow together rather than fighting: read-only decides which
tools exist, ACTUAL_TOOLSET decides which of those are offered.
Tools (44)
One more, list_budgets, exists only when this server is configured for more
than one budget, so it is not counted here: see
More than one budget.
Read (11)
Tool
Description
Example prompt
list_accounts
All accounts with balances
"Show me all my accounts"
get_budget_month
Budget for a specific month
"What does my March budget look like?"
get_transactions
Transactions with filters
"Show me transactions from last week over 5000"
get_category_balance
Category history across a window of months
"How did food look in the three months to June?"
get_budget_summary
Executive budget overview
"Give me a budget summary for February"
get_categories
All category groups and categories, with include_hidden for the hidden ones
"What categories do I have?"
get_payees
All payees in the budget
"List all my payees"
get_schedules
Recurring payments: what is due next, how much, and whether the last one posted
"What bills are coming up?"
reconcile_account
Compare an account against a bank figure and explain the gap
"My checking statement says 12,500.00, what am I missing?"
get_rules
All transaction rules
"Show me my rules"
balance_history
Account balance over time
"Show balance history for my checking account"
Parameters
get_budget_month - month (optional): YYYY-MM or natural language ("this month", "last month", "enero 2025")
reconcile_account - account (required) | expected_balance (required): what the bank says | as_of (optional): the date that figure is from, defaults to today; transactions after it are not counted | balance_counts (optional): all (default) counts uncleared rows too, cleared_only does not | lookback_days (optional, default 90). Reads only, books nothing. Lists what might explain a difference, strongest signal first: a charge entered twice, the amount sitting on another account, a row dated past the cutoff, and last a bare amount match. Combinations are not searched on purpose, because on an ordinary account some pair sums to almost any round figure. When nothing explains it, it says so.
get_transactions - account (optional): account name | start_date / end_date (optional): YYYY-MM-DD or natural language | category (optional): category name, matched on any part of it, or a full category ID | payee (optional): payee name | min_amount / max_amount (optional): filter by amount | notes_contains (optional): text to find in the notes, case-insensitive, matching the note of the split a transaction belongs to as well; searches every date unless you give a range | uncategorized (optional): only transactions with no category, leaving out split parents, transfers between accounts on the same side of the budget, and off-budget accounts; searches all dates unless you give a range | limit (optional, default 50)
get_category_balance - category (required): category name or ID | months (optional, default 3): how many months the window covers, and the default is a default, not a limit | month (optional): the month the window ends in, defaulting to this month, so a past period can be asked for directly
get_budget_summary - month (optional): YYYY-MM or natural language. A group with nothing budgeted against it gets no percentage: a share of a non-positive budget has no correct reading, so the row says what it is instead.
balance_history - account (required): account name or ID | start_date (optional, default 3 months ago) | end_date (optional, default today)
Analysis (5)
Tool
Description
Example prompt
budget_vs_actual
Budgeted vs spent per category
"Am I over budget on anything this month?"
spending_projection
End-of-month spending forecast
"Will I stay within budget this month?"
category_trends
Spending trends over a window of months
"What were my trends in the six months to June?"
spending_by_category
Spending breakdown by category
"Show me spending by category for February"
monthly_summary
Income vs expenses vs savings
"How have my finances been the last 3 months?"
Parameters
budget_vs_actual - a category whose net for the month is positive says money came in rather than being listed as under budget, and is left out of the under-budget total. month (optional): YYYY-MM or natural language | group (optional): filter by category group
spending_projection - money coming in is not projected as going out, and the headline counts categories already over budget, including those with nothing budgeted at all. month (optional): YYYY-MM or natural language
category_trends - category (optional): specific category or top spending if omitted | months (optional, default 6): how many months the window covers, and the default is a default, not a limit | month (optional): the month the window ends in, defaulting to this month. Months earlier than the budget file are named in the reply rather than ending the call
spending_by_category - start_date / end_date (optional): date range | include_income (optional, default false) | limit (optional, default 20). It counts each half of a split against its own category and leaves off-budget accounts out, using the same sum as the month cross-check. The share column is a share of spending, so a category whose net for the period is positive (a refund, a reimbursement) is still listed but carries no share, and the footer separates spending, money in and the net. Otherwise a single incoming row shrinks the denominator and the shares add up to more than 100%.
monthly_summary - months (optional, default 3): number of months to show
Write: Transactions (13)
Tool
Description
Example prompt
create_transaction
Add a new transaction
"I spent 500 on groceries from Wallet today"
create_transactions
Add several at once, all or nothing
"Record these 22 movements from the 18th"
create_split_transaction
One charge across several categories
"Split that 3,000 charge: 2,000 groceries, 1,000 household"
Move budgeted money between categories, creating no transaction
"Move 125.50 from Pending Refunds to Family"
hold_for_next_month
Keep part of a month's unassigned money for the next month
"Hold 5,000 of what is left for next month"
set_category_carryover
Carry a category's overspending forward instead of taking it off the top
"Let Groceries carry its own overspending from now on"
recategorize_transaction
Move to another category
"Move that transaction to Entertainment"
create_transfer
Transfer between accounts
"Transfer 10,000 from Checking to Savings"
reconcile_currency_residual
Clear accumulated FX-rate residual
"Reconcile my USD card to 250.00 USD"
run_bank_sync
Sync with linked banks
"Sync my bank transactions"
Parameters
create_transactions - transactions (required): an array of {account, amount, payee?, category?, date?, notes?, cleared?, imported_id?} | allow_duplicate (optional). This is the way to record more than one. Every row is resolved and checked before anything is written, and if any row is unusable nothing is created: the reply names the rows that failed and why, and says the rest were fine but not written either. Calling create_transaction many times in parallel is what this replaces: nine at once took the server down, which is how that limit was learned. A row whose payee names one of your accounts becomes a transfer, by the same rule create_transaction uses, and the reply lists those rows at the end with what each did to your budget. Two rows that are the two sides of one movement, which is what reading a card payment off both statements gives you, are refused as one movement written twice; so is a transfer whose other side is already in the target account, imported from the bank. That holds when the card statement calls it something like "PAYMENT RECEIVED" rather than naming the account, and when the two banks post it a day apart, which is usual when they are different banks. Two days apart counts as two movements. Two payments of the same amount from the same account on different days are not affected: that comparison is still the exact date. A row whose imported_id is already in the budget is refused, so resending a batch cannot duplicate it.
create_transaction - account (required): account name | amount (required): negative for expenses, positive for income | payee (optional): naming one of your accounts makes it a transfer and creates the matching row there | category (optional): a category means this is an ordinary purchase rather than a transfer, but only when both accounts are on budget, for when a shop shares an account's name; if either account is off budget it stays a transfer, since money is crossing the edge of the budget | date (optional) | notes (optional) | cleared (optional) | allow_duplicate (optional): create it even though one with the same account, date and amount exists
delete_transaction - transaction_id (required) | confirm (optional): must be true to delete; without it the tool only previews
update_budget_amount - category (required) | amount (required) | month (optional) | mode (optional): absolute (default) sets the budgeted figure, delta adds the amount to what is already there and may be negative. A delta is what an ordinary adjustment is: with rollover and spending in the way, setting an absolute figure means working out a number like 24,545.50 first, and nothing about that number shows it was computed wrongly.
transfer_between_categories - from (required): category to take from | to (required): category to give to | amount (required): positive | month (optional, defaults to the current month). Refuses an income category at either end (Actual marks income per category, so one can sit in a spending group), a month that is not YYYY-MM with the month between 01 and 12, and moving a category to itself. Actual's own handler accepts all three and silently loses, destroys or invents money. Covering an overspent category is allowed and reported.
hold_for_next_month - amount (required): added to whatever is already held, 0 releases the whole hold | month (optional, defaults to the current month). Actual's own call adds rather than sets and holds what the month has without saying so, so the reply gives the total held and says when it held less than was asked for, or nothing at all. An amount that rounds to zero is refused rather than treated as a release. Envelope budgets only: a tracking budget has no money to assign and nothing to hold.
set_category_carryover - category (required) | enabled (required) | month (optional, defaults to the current month). Not one month: Actual writes the flag into every month from the one given to the last month it has created, so the reply says which of them changed, where it reaches, and that months created later start without it. That last month is one past what Actual's API will list or read, so it is written and the reply says it could not be checked. Refuses an income category, which has no overspending to carry, and a tracking budget, which has no envelopes to carry it into.
create_split_transaction - account (required) | amount (required): total, must equal the sum of the splits | splits (required): two or more {category, amount, notes} | payee, date, notes, cleared (all optional)
reconcile_currency_residual - compares against every row up to today, and says how much of that figure is not marked cleared and what the adjustment would have been without it. account (required) | category (required): where to book the adjustment | target_balance (optional, defaults to 0) | payee, notes (optional) | date (optional, today or earlier; a future date is refused) | allow_duplicate (optional): book it even though a transaction of that amount is already on that day | future_rows (optional): exclude or include, whether the balance you gave already counts transactions dated after today
run_bank_sync - account (optional): sync specific account or all if omitted. From Actual 26.11 the reply says how many transactions came in and how many matched rows that were already there, and lists the new ones with their account; on an older library it says the sync ran, which is all that library reports.
Write: Categories (6)
Tool
Description
Example prompt
create_category
Create a new category
"Create a category called Gym in Variable Spending"
create_category - name (required) | group (required): group name or ID
update_category - category (required): name or ID | name (optional): new name | hidden (optional): true/false
delete_category - category (required) | transfer_to (optional): category to move transactions to | confirm + confirm_name (required to delete)
create_category_group - name (required)
update_category_group - group (required): name or ID | name (optional): new name | hidden (optional): true/false
delete_category_group - group (required) | transfer_to: category for the orphaned transactions, required unless the group is empty | confirm + confirm_name (required to delete)
update_payee - payee (required): name or ID | name (required): new name
delete_payee - payee (required): name or ID | confirm + confirm_name (required to delete)
create_rule - condition_field (required): payee, payee_name, category, category_group, account, amount, notes, imported_payee | condition_op (required): is, isNot, oneOf, notOneOf, contains, gt, lt, etc., where oneOf and notOneOf take a list, on payee, category, category_group, account, payee_name and imported_payee only | condition_value (required): for payee or category, a name or ID | action_field (required): category, payee, notes, account | action_value (required): for payee, category or account, a name or ID that already exists. Setting account moves the transaction, which a later import of the same movement does not recognise, so a bank sync can leave a duplicate, and a row moved off budget loses its category | stage (optional). contains, doesNotContain and matches are refused on payee, category, category_group and account: Actual stores those as ids, so the comparison runs against the id and the rule fires on the wrong transactions. For text, imported_payee holds the text the row arrived with, from your bank or from whoever created it here, and it is the one that catches the first charge from a shop you have not seen before. payee_name compares against the payee's current name, but only once that payee exists, so it misses that first charge. Measured both ways. get_rules reads every id field back as a name, lists included, and marks any rule already saved the other way, as well as any holding a name where an id belongs, which never fires.
delete_rule - rule_id (required) | confirm (required to delete)
Write: Accounts (3)
Tool
Description
Example prompt
create_account
Create an on- or off-budget account
"Create an off-budget account called Family Investment with 10,000"
delete_account
Delete an account and its history
"Delete the ZZ Test account"
update_account
Rename an account
"Rename Main Checking to Everyday Account"
delete_account needs two keys. It destroys the account's entire transaction
history, so a single call never deletes. The first call only previews what
would be lost (name, balance, transaction count) and suggests closing the
account instead, since closing retires it while keeping its history. To actually
delete, call again with confirm: trueandconfirm_name set to the
account's exact name. While it declines, the tool reports isError: true, so a
confirmation prompt is never mistaken for a completed deletion.
Parameters
create_account - name (required) | offBudget (optional, default false) | initialBalance (optional): human amount, creates the "Starting Balance" transaction. (Actual models accounts as on/off-budget only, so there is no account type.)
update_account - account (required): name or ID | name (required): the new name. Renames only. Budget status (offbudget) and closing are deliberately not exposed: moving an account in or out of the budget changes every month's totals at once, and closing has its own flow in the app that asks where the remaining balance goes. A name already used by another account is refused, because Actual allows duplicates and then neither account can be resolved by name.
delete_account - account (required): name or ID | confirm (required to delete): must be true | confirm_name (required to delete): the account's exact name
Maintenance (1)
Tool
Description
Example prompt
repair_sync
Repair an out-of-sync budget
"Repair the sync, everything is failing"
If tools start failing with a sync error, the budget's sync state is
inconsistent with the server. repair_sync rebuilds that state without
touching budget data. Note that deleting the local ACTUAL_DATA_DIR does
not fix this, because the inconsistency is in the sync state, not the cache.
It checks the server is there first. Two different problems fail the same
way: a broken sync state, and a server that is not running — which for the
desktop app means the app is closed, since its server on port 5007 only runs
while it is open. repair_sync only fixes the first, so if nothing is
listening it says so and changes nothing, rather than spending a repair on a
problem that is "the app is not running".
Parameters
repair_sync - no parameters
Environment
ACTUAL_HTTP_TIMEOUT_MS (optional, default 60000) - how long to wait for your Actual server to start replying. The reply itself is then free to take as long as it takes, so a slow budget download is not cut off. Without this, a server that accepts the connection and never answers holds every write for five minutes, which is Node's own limit.
A value below 1000, above what a timer can hold, or Infinity is brought to the nearest limit rather than used, with a line on stderr saying which and why. A value that is not a number, or is zero or negative, leaves the default in place without saying anything: there is nothing useful to tell someone who never set it.
What it reaches, read off the SDK rather than assumed:
SimpleFIN, Pluggy, Akahu and Enable Banking set their own limit on the call that fetches transactions, so this setting does not shorten them. It is 60 seconds, except for SimpleFIN syncing several accounts at once, which is 300 seconds and is what the default bank sync does. Those limits cover the whole reply, not just the start of it, which is why they are larger than this one.
GoCardless sets none, so its transaction download is governed by this setting. Raise it if your bank is slow and a sync is being cut off.
Everything else the server does, which is every ordinary read and write against your own Actual server.
If you installed the .mcpb extension, the same setting is in its configuration as Server reply timeout (ms).
One case it does not cover, deliberately: a server that sends its headers and then stops sending the body. The deadline has already been met by then, so what ends that request is Node's own five-minute body timeout. Covering it would mean putting a deadline on the transfer itself, which is what cut off healthy downloads before this was fixed.
Prompts
Built-in prompt templates that guide Claude through multi-step financial analysis:
Prompt
Description
monthly-review
Complete budget review for any month: spending vs budget, overspending, suggestions
spending-check
Quick check: are you on track this month?
spending-patterns
Deep analysis of spending trends and patterns over multiple months
Use them in Claude Desktop by clicking the prompt icon, or in Claude Code by asking Claude to use them.
Resources
Pre-loaded data that Claude can reference without calling tools:
Resource
URI
Description
Accounts
actual://accounts
All accounts with balances
Categories
actual://categories
Category groups and categories with IDs
Payees
actual://payees
All payees sorted alphabetically
Usage Examples
Here are real prompts you can use:
code
"How much did I spend in February?"
"Show me my top 5 spending categories this month"
"Am I over budget on anything?"
"I spent 1,200 on electricity from my checking account yesterday"
"What's my savings rate this month?"
"Show me all transactions from Wallet in the last 30 days"
"Transfer 5,000 from Checking to Savings"
"What are my spending trends for food over the last 6 months?"
"Create a category called Gym in Variable Spending"
"Rename the Gym category to Fitness"
"Create a rule: when payee is Netflix, set category to Suscripciones"
"How have my finances been the last 3 months?"
How is this different?
Compared to other Actual Budget MCP servers:
Feature
actual-budget-mcp
Others
Natural language dates
"last month", "este mes", "hace 3 meses"
Only YYYY-MM-DD
Name resolution
Type "Wallet" instead of UUIDs
Requires exact IDs
Output format
Aligned tables, readable text
Raw JSON
Error messages
Clear instructions on how to fix
Generic errors
Analysis tools
Budget vs actual, projections, trends
Not available
MCP Prompts
3 guided analysis workflows
Limited or none
MCP Resources
Accounts, categories, payees pre-loaded
Not available
Bilingual dates
English + Spanish
English only
Transfers
Two linked sides, matching transfer_id, no category, same as the app
Often one-sided or miscategorised
Deletes
Preview, then an explicit confirmation
Run immediately
Out-of-sync recovery
repair_sync rebuilds the local sync state
Reinstall and hope
API version
@actual-app/api 26.x (current)
Often outdated
Security
This server connects to your Actual Budget instance using the credentials you provide
Credentials are passed as environment variables and never stored by the MCP server
All communication with your Actual Budget server happens locally (or to your self-hosted server)
The server only accesses budget data through the official @actual-app/api library
No data is sent to third parties
Over HTTP a bearer token is required, at least 32 characters, compared in constant time, and a request from a browser is refused outright
This server does not terminate TLS. On anything other than loopback, put a reverse proxy or a tunnel in front of it, or the token travels in the clear
Troubleshooting
Stuck on something that is not listed here? Tell me what tripped you up. A sentence is enough, and a failed setup looks identical to no setup at all from my side.
"Could not connect to Actual Budget server"
Make sure Actual Budget is running (open the app or start the server)
Check that ACTUAL_SERVER_URL is correct
Run npx -y actual-budget-mcp --verify to test your connection
"Authentication failed"
Your server requires a password. Set ACTUAL_PASSWORD in your config
If you forgot the password, reset it in Actual Budget under Settings > Server
"Budget not found"
Check your ACTUAL_BUDGET_ID. Find it in Settings > Show advanced settings > Sync ID
"Budget file is encrypted"
Set ACTUAL_ENCRYPTION_PASSWORD with your encryption password
"Ambiguous name: matches X, Y"
Be more specific. Instead of "Main", try "Main Checking" or "Main Savings"
Node.js Requirement
The server exits immediately, or dies with no message at all
From 0.10.1 the minimum is Node 22.14. Actual's SQLite library is built
against N-API 10, which arrives in that release; on an older Node the binary
loads and then segfaults when the budget is opened. Measured on 22.13.1:
exit code 139, no message, no stack, nothing in any log. A host that restarts
the server would do it forever.
The server now checks this at startup and says so instead of crashing, but
only from 0.10.1 on.
Solution: run Node 22.14 or newer, or use the Docker image, which carries
its own.
"ReferenceError: navigator is not defined"
@actual-app/api referenced the navigator global through 26.6. That global
only exists on Node.js 21+, so importing the library on Node.js 20 threw
before the server could start. 26.8 dropped the reference.
Solution: Run Node.js 22.14 or newer.
Your Actual apps stop opening the budget after using this server
Opening a budget runs any migration the library has and the file does not,
and the next sync uploads the result. From 0.10.1 this server carries Actual
26.10, so pointing it at a 26.9 server migrates the budget to the newer
format, and an Actual app still on 26.9 then cannot open it. Measured: 59
migrations become 60.
Actual's own apps do exactly the same when they update; the difference is
that this one can reach your budget before you have updated anything else.
The other direction is the same problem seen from the other end: an Actual
server ahead of this server's library holds a budget that may carry
migrations the library does not have, and a tool then fails with a message
about a file rather than about a version.
The server says so on startup, before it downloads anything, whichever of
the two is behind, and list_budgets says it again in its answer, because
a server your client starts in the background has nobody reading its log.
It says it and opens the budget anyway: Actual's minor is the month, so a
server that updates itself is a minor ahead of this one every time Actual
releases, and refusing to work on that would be worse than the warning.
Solution: keep your Actual server and this server on the same Actual
version. If you have already hit it, update whichever is behind and the
budget opens again, with nothing lost.
"version `GLIBC_2.34' not found", or the budget never opens on an older Linux
Actual's SQLite binary for Linux is built against glibc 2.34, so it does
not load on Debian 11, Ubuntu 20.04 or RHEL 8, whose glibc is older. Measured
against Debian 11's libc: version 'GLIBC_2.33' not found.
There is no override for this: a package.json override does not reach an
npx install, and the binary is what the library ships.
Solution: run the Docker image, which carries its own glibc, or a
distribution with glibc 2.34 or newer (Debian 12, Ubuntu 22.04, RHEL 9).
"gyp ERR! find Python" when installing from source
Installing from a clone runs npm ci, and npm builds any package that ships
a binding.gyp, which better-sqlite3 does even though it needs no
building: the binary it uses is already in the package.
Solution:npm ci --ignore-scripts. Nothing is lost; that is what the
extension and the Docker image do.
Node Version Managers (fnm, nvm, volta)
MCP server shows "Server disconnected" in Claude Desktop
Claude Desktop doesn't source your shell profile (.bashrc, .zshrc), so version managers like fnm, nvm, and volta won't work with the default npx command. This applies to a manual npx entry in the config file, not to the Desktop Extension, which carries its own dependencies.
Solution: Use the absolute path to node in your config. Find it with:
Contributions are welcome! Please open an issue or submit a pull request.
bash
git clone https://github.com/henfrydls/actual-budget-mcp.git
cd actual-budget-mcp
npm install
npm run build
npm test# Run unit tests
npm run test:connection # Needs .env configured
URL of your Actual Budget server, for example http://localhost:5006
ACTUAL_PASSWORDsecret
Password for your Actual Budget server. Not needed if you set ACTUAL_SESSION_TOKEN
ACTUAL_SESSION_TOKENsecret
Session token for servers behind OIDC, which have no password. Use instead of ACTUAL_PASSWORD; if both are set, the token wins
ACTUAL_BUDGET_IDrequired
Your budget's Sync ID, found under Settings > Show advanced settings
ACTUAL_ENCRYPTION_PASSWORDsecret
Only needed if your budget file is end-to-end encrypted
ACTUAL_BUDGET_IDS
Every budget this server serves, comma separated, when it is more than one. Each tool then takes a budget_id, and each budget is opened in a process of its own
ACTUAL_ENCRYPTION_PASSWORDSsecret
A JSON object of budget sync id to encryption password, for when more than one of the budgets is encrypted. Each worker is given its own and never the map
ACTUAL_BUDGET_WORKERS
How many budgets stay open at once. Defaults to 3. A fourth budget closes the one that went longest without a call
ACTUAL_WORKER_IDLE_MINUTES
How long an open budget with nothing to do stays open. Defaults to 15
ACTUAL_WORKER_READY_SECONDS
How long a call waits for a budget that is still opening before it answers that it is still opening. Defaults to 45
ACTUAL_READ_ONLY
Set to 1 to hide every write tool from the model, exposing only reads and analysis
ACTUAL_TOOLSET
Set to chat to offer the 18 everyday tools instead of all 44, which is 17.4 KiB of tool descriptions instead of 39.7 KiB on every connection. Defaults to full
ACTUAL_DATA_DIR
Directory for the local budget cache
ACTUAL_HTTP_TIMEOUT_MS
How long to wait for your server to start replying, in milliseconds. Defaults to 60000; raise it if a GoCardless bank sync is being cut off
ACTUAL_HTTP_PORT
Serve MCP over HTTP on this port instead of stdio. Only for a server you run yourself and point clients at: a client that starts this package itself speaks stdio and cannot reach it once this is set
ACTUAL_HTTP_TOKENsecret
The credential for the read path, /mcp. Required once ACTUAL_HTTP_PORT is set, and at least 32 characters
ACTUAL_HTTP_WRITE_TOKENsecret
A second credential, for the write path, /mcp-write. Without it the server serves no write path at all
ACTUAL_HTTP_HOST
What to bind to. Defaults to 127.0.0.1; inside a container that is unreachable, so 0.0.0.0 together with ACTUAL_HTTP_ALLOW_REMOTE
ACTUAL_HTTP_ALLOW_REMOTE
Set to 1 to bind somewhere other than loopback. Nothing here terminates TLS, so put something in front of it that does
ACTUAL_HTTP_ALLOWED_HOSTS
Hostnames to accept in the Host header, comma separated and without ports, for a server that is not on loopback. Anything else is answered 403