Mercury MCP. Get instant access to balances, transaction logs, and payees.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Mercury connects your AI agent directly to your business bank accounts. It lets you check real-time account balances, pull filtered transaction histories, list all payment recipients, and retrieve full statements—all without logging into the web dashboard.
You get instant cash flow visibility right from your chat client.
What your AI agents can do
Create recipient
Sets up a new payee for ACH or wire payments, which is required before sending money.
Get account
Retrieves foundational details and metadata for a specific Mercury bank account.
Get transaction
Fetches the full details of one specific transaction record by ID or criteria.
Retrieves the combined, real-time balance across all linked Mercury accounts.
Pulls lists of transactions that can be filtered by date range or specific dollar amounts.
Lists existing recipients or creates a new payee record for future payments.
Fetches essential banking details like routing numbers and full bank account identifiers.
Retrieves comprehensive lists of past payments or downloadable statements.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Mercury MCP Server: 10 Tools for Financial Data Access
These tools allow your agent to perform core banking operations, including listing accounts, checking balances, managing recipients, and pulling transaction history.
019d75d2create recipient
Sets up a new payee for ACH or wire payments, which is required before sending money.
019d75d2get account
Retrieves foundational details and metadata for a specific Mercury bank account.
019d75d2get transaction
Fetches the full details of one specific transaction record by ID or criteria.
019d75d2get treasury balance
Provides a high-level overview and total balance across all linked treasury accounts.
019d75d2list accounts
Returns a list of every active bank account associated with the Mercury business profile.
019d75d2list payments
Retrieves a history of all payments that have been successfully sent out from your accounts.
019d75d2list recipients
Shows the list of payment payees currently saved in your system.
019d75d2list statements
Retrieves a list of available bank statements, allowing you to pull historical reports.
019d75d2list team members
Lists all authorized team members associated with the Mercury account.
019d75d2list transactions
Pulls a paginated list of recent transactions, which you can then filter for deeper analysis.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Mercury, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Mercury connects your AI agent right into your business bank accounts. It lets you manage startup finances conversationally, giving your agent direct read-only access to all your banking data without forcing you to log into the web dashboard. You get instant cash flow visibility directly from your chat client.
To check your overall financial picture, you can pull a combined, real-time balance across every single linked Mercury account using get_treasury_balance. If you just want foundational details for one specific bank account—like the routing numbers or full identifiers—you run get_account.
You'll find that checking your cash position is simple. You can see a list of every active business account associated with your profile by calling list_accounts. For tracking how money moves, you pull detailed transaction lists using list_transactions, which lets you filter down the results by date range or specific dollar amounts to analyze spending patterns.
If you need deep details on just one payment event, use get_transaction with the ID. To see a history of every outgoing payment your business made, run list_payments.
Managing who gets paid is just as easy. You can pull up the list of all saved payment payees by running list_recipients. If you need to send money to someone new, you'll first have to set them up using create_recipient, which handles both ACH and wire payments.
When it comes to historical records, you've got a couple of options. You can pull down downloadable bank statements by calling list_statements to review past activity. If you just need the full list of transactions that have happened, you run list_transactions. Finally, if your team structure changes, you can get a roster of authorized staff members by using list_team_members.
How Mercury MCP Works
- 1 Subscribe to the Mercury integration on Vinkius.
- 2 Generate an API token from your Mercury dashboard (Settings → API Tokens).
- 3 Ask your AI agent a specific question—like 'What were my transactions over $10k last month?'—and it calls the necessary tools.
The bottom line is: you talk to your agent, and it handles all the complex API calls needed to get you the data.
Who Is Mercury MCP For?
This is for Founders who need instant cash flow visibility before investor meetings. It's essential for Operations Managers tired of manually cross-referencing bank dashboards, and Bookkeepers who want to automate daily transaction reconciliation from their dev environment.
Needs an instant snapshot of the cash runway or total capital position without logging into a web browser.
Monitors multi-account cash flow and payment activity across different Mercury accounts from one single interface.
Automates daily balance checks or confirms vendor details by listing/creating recipients.
What Changes When You Connect
- Never switch tabs for a cash position check. Calling
get_treasury_balancegives you the combined total immediately, which is critical when running investor reports. - Stop manual reconciliation. Use
list_transactionsto pull recent spending data filtered by date or amount directly into your workflow, saving hours of spreadsheet work. - Setting up new payees used to be tedious. Now, calling
create_recipientlets you add a vendor's bank info and get it logged instantly for future payments. - Need the full audit trail? Instead of searching through multiple web pages, use
list_statementsto pull specific historical reports into your agent’s context. -
get_accountgives you immediate access to fundamental banking details—routing numbers, account IDs—which is necessary when writing code that interacts with external financial services.
Real-World Use Cases
Preparing for an investor call
The founder needs the total cash position right now. Instead of logging into Mercury and clicking through three different dashboards, they ask their agent: 'What's the current treasury balance?' The agent calls get_treasury_balance and returns a single, definitive number.
Reconciling payroll spending
The bookkeeper needs to verify all payments over $5k this month. They prompt the agent: 'Show me large transactions from May.' The agent runs list_transactions and filters the results, providing a clear list of AWS bills or major vendor payments.
Onboarding a new contractor
The ops manager needs to pay a new freelance developer. They use their AI client to run two steps: first, call list_recipients to check the current list, then create_recipient with the new vendor's details, ensuring the payment can go out.
Auditing account setup
A developer needs to write code that interacts with Mercury APIs. They ask the agent: 'What are my primary routing and account numbers?' The agent calls get_account and provides the required metadata for immediate use.
The Tradeoffs
Treating data as static text
The developer copies a list of 50 transactions from the web dashboard into a spreadsheet to analyze spending. They then have to manually filter by date and calculate totals.
→
Ask your agent to run list_transactions with specific filters (e.g., 'last month' or 'over $10k'). The data comes clean, structured, and ready for immediate analysis.
Assuming one call is enough
The user asks the agent only to 'check payments.' The agent returns a vague list without context on who was paid or when.
→
You need multiple tools. Ask for: 1) list_recipients (to see who's available), and then 2) list_payments (to see what actually went out).
Ignoring the total picture
The user only checks one account balance on the web dashboard, missing funds held in a separate reserve or treasury account.
→
Always call get_treasury_balance first. It gives you the single source of truth for your total cash position across all Mercury accounts.
When It Fits, When It Doesn't
Use this MCP Server if your financial process requires chaining multiple actions: listing recipients, checking balances, and then pulling specific transactions to build a report. This is ideal for automation where data flow matters.
Don't use it if you just need general information that doesn't involve the API (e.g., 'What does Mercury do?'). For simple lookups of non-financial data or complex, multi-stage logic outside the scope of banking primitives, you should use a specialized workflow engine or database connector instead. If your goal is simply to read financial records and perform basic arithmetic on them, this server works perfectly.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Mercury. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually checking accounts is a massive time sink.
Right now, getting a full picture of your business finances means jumping between tabs. You log into the dashboard to check Account A's balance. Then you open another tab for Transactions B to see spending patterns. If you need to know your total available cash across all accounts and then cross-reference it with payments made last week, you're clicking through a dozen pages just to gather data.
With this MCP Server, the agent does that work for you. You simply ask: 'What is our current cash position, and what were the largest five transactions in June?' The agent executes `get_treasury_balance` and then calls `list_transactions`, giving you the full answer without any context switching.
Mercury MCP Server: Instant financial data retrieval.
You stop needing to copy-paste transaction details or manually cross-reference account numbers. You don't have to wait for bank reports; the agent fetches live, structured data instantly using tools like `list_accounts` and `get_transaction`.
It’s a single conversation that handles complex financial logic. The result is accurate, actionable data delivered straight into your chat environment.
Common Questions About Mercury MCP
How do I get my Mercury API token? +
Log in to your Mercury account at app.mercury.com. Go to Settings → API Tokens and click Create Token. Choose the token type (Read Only for balance checks, or Read and Write for managing recipients). Copy the token immediately — it will only be shown once. Paste it into the configuration field below, and you're ready. No code, no SDK, no webhooks.
Can my AI agent check my startup's runway instantly during a board meeting? +
Absolutely. Just ask your AI agent 'What's my current balance across all Mercury accounts?' and it returns real-time balances for every account — checking, savings, and treasury — in seconds. No tab-switching, no logging in, no waiting for the dashboard to load.
What if I need to review recent transactions for month-end close? +
Ask your AI agent to pull transactions from any date range. It retrieves each transaction with amount, counterparty, status, and date — perfect for reconciliation. You can filter by account, ask for Wire vs ACH breakdowns, or request only transactions above a specific threshold, all without exporting CSVs.
Is this suitable for companies with multiple Mercury accounts? +
Yes. The integration retrieves data across all accounts linked to your API token — operating accounts, savings accounts, and treasury balances. Perfect for venture-backed startups managing multiple entities, holding companies, or finance teams tracking cash positions across subsidiaries.
When using the Mercury tools, how do I manage read versus write access for `create_recipient`? +
You control this through your API token permissions. Your agent needs a restricted scope that only permits necessary actions—like reading balances or adding recipients—and nothing more.
What happens if my AI client makes too many calls to `list_transactions`? +
If you hit rate limits, your agent will receive a specific HTTP 429 error code. You need to build backoff logic into your workflow; the response details exactly when you can try again.
How can I use `get_transaction` to filter for niche data, like transactions from a specific merchant category? +
The tool accepts structured parameters beyond just dates and amounts. You pass filters that specify categories or keywords in the counterparty notes to narrow down results precisely.
What is the best way to process detailed bank data using `list_statements`? +
The tool fetches comprehensive statement metadata, which your agent can then parse. This lets you pull structured details from raw bank statements for deeper reconciliation than simple transaction lists.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Bill.com
Equip your AI agent with direct access to BILL — manage invoices, approve payments, and track vendor bills without opening the AP dashboard.
Recharge Alternative
Manage subscription commerce via Recharge — handle customers, subscriptions, addresses, and delivery schedules directly from your AI agent.
Bold
Automate payments via Bold Colombia — manage terminals, process transactions, generate payment links, and track settlements from any AI agent.
You might also like
Cisco Meraki
Manage cloud-managed networking via Cisco Meraki — track devices, monitor clients, and audit network health directly from any AI agent.
Webshare
Manage residential and datacenter proxies, rotation settings, and authorized IPs on Webshare — the fast and affordable proxy network.
Volcengine Speech Synthesis
The massive 'TikTok Voice' TTS API — generate natural speech with ByteDance's iconic voice models.