Provider REST API

18 actions

Connect Claude to Mercury

Read bank accounts, balances, transactions, statements, recipients and receivables invoices. Toolspoke puts 18 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API token
Actions exposed: 18
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Mercury
Open the marketplace in your workspace, add Mercury to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Mercury shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Mercury asks for

API token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

API tokenRequired: Mercury → Settings → Tokens (app.mercury.com/settings/tokens) → Create an API Token, and choose Read Only. Paste the whole value, including the secret-token: prefix. Read Only covers every operation here except update_transaction and cancel_invoice, which need a Read and Write or Custom token.; secret-token:mercury_production_…

What Claude can do in Mercury

18 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 16Reads
Writes: 1Writes
Destructive: 1Destructive

Reads

Fetches data and changes nothing.

list_accounts
List the organization's Mercury deposit accounts with their current and available balances, status and kind. Takes no arguments, which is why it is the connection test: it proves the token reaches real account data, not only that it exists. The account id it returns is what every per-account operation takes.
get_account
Retrieve one account by id, with its balances, status and dashboard link.
list_account_cards
List the debit and credit cards issued against one account, with cardholder, status and last four digits.
list_account_statements
List the monthly statements for one account, optionally inside a date window. Returns statement metadata and ids, not the PDF.
list_transactions
List transactions across every account, newest first unless order says otherwise. Narrow it with start and end (creation date) or posted_start and posted_end (posting date) before anything else; a busy organization has thousands a month. Each row names the counterparty, the amount, the status and the category. Page with start_after, passing the last transaction id seen.
list_account_transactions
List the transactions on one account, filtered by date window, status or a search term. Pages by offset rather than cursor.
get_transaction
Retrieve one transaction by id, with its attachments, check images, category and the counterparty's details.
list_categories
List the organization's custom expense categories, whose ids update_transaction takes.
list_recipients
List the payment recipients saved on this organization - the people and companies it pays - with their default payment method and when each was last paid.
get_recipient
Retrieve one recipient by id, including its addresses and routing details.
list_credit_accounts
List the organization's Mercury credit accounts with their balances and limits.
list_treasury_accounts
List the organization's Mercury Treasury accounts with their balances.
get_organization
Retrieve the organization's legal business name, DBAs and subscription tier. The EIN is masked in the audit log.
list_customers
List the accounts-receivable customers this organization invoices, with their names, emails and addresses.
list_invoices
List accounts-receivable invoices with their customer, amount, due date and payment status.
get_invoice
Retrieve one accounts-receivable invoice by id, with its line items, recipients and payment state.

Writes

Creates or updates something on the other side.

update_transaction
Set or clear a transaction's note and custom category. A write rather than destructive: it changes bookkeeping metadata only, moves no money, and can be set back. Send null to clear a field.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

cancel_invoice
Cancel an accounts-receivable invoice. Destructive because Mercury documents it as irreversible: the customer can no longer pay it, and a cancelled invoice cannot be reopened.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 18 actions above are the whole of it. A call to any other name is refused before it reaches Mercury rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Mercury of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Mercury: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Mercury. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Mercury's own rate limits. A call that Mercury refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Mercury?

18 named actions: 16 that only read, 1 that write and 1 that delete or permanently alter something. They include list_accounts, get_account and list_account_cards. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Mercury connector need?

API token. The connector asks for api token. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Mercury connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 18 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Mercury connector not do?

The 18 actions above are the whole of it. A call to any other name is refused before it reaches Mercury rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Mercury of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Mercury. An agent has to ask. Toolspoke does not retry, queue or back off around Mercury's own rate limits. A call that Mercury refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Mercury's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Mercury?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More finance connectors

Browse all of them