Mercury MCP connector for AI agents

Tools your finance agent reaches for on Mercury, scoped per user.

CALL ANY TOOL

35 read-only tools for business banking data in Mercury: accounts, transactions, cards, statements, invoices, customers, recipients, treasury, and webhooks.

mercurymcp_getaccount

Getaccount

Retrieve details of a specific Mercury account by its ID.

Parameters

Name

Type

Required

Description

accountId

string

Required

Mercury account ID. Get it from Get Accounts.

mercurymcp_getaccountcards

Getaccountcards

mercurymcp_getaccounts

Getaccounts

mercurymcp_getaccountstatements

Getaccountstatements

mercurymcp_getattachment

Getattachment

mercurymcp_getcard

Getcard

mercurymcp_getcustomer

Getcustomer

mercurymcp_getinvoice

Getinvoice

mercurymcp_getorganization

Getorganization

mercurymcp_getrecipient

Getrecipient

mercurymcp_getrecipientinvite

Getrecipientinvite

mercurymcp_getrecipients

Getrecipients

mercurymcp_getsaferequests

Getsaferequests

mercurymcp_gettransaction

Gettransaction

mercurymcp_gettransactionbyid

Gettransactionbyid

mercurymcp_gettreasury

Gettreasury

mercurymcp_gettreasurystatements

Gettreasurystatements

mercurymcp_gettreasurytransactions

Gettreasurytransactions

mercurymcp_getusers

Getusers

mercurymcp_getwebhook

Getwebhook

mercurymcp_getwebhooks

Getwebhooks

mercurymcp_listcards

Listcards

mercurymcp_listcategories

Listcategories

mercurymcp_listcredit

Listcredit

mercurymcp_listinvoiceattachments

Listinvoiceattachments

mercurymcp_listinvoices

Listinvoices

mercurymcp_listmerchants

Listmerchants

mercurymcp_listrecipientinvites

Listrecipientinvites

mercurymcp_listrecipientsattachments

Listrecipientsattachments

mercurymcp_listsendmoneyapprovalrequests

Listsendmoneyapprovalrequests

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Mercury MCP tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mercurymcp"], toolNames: [
    "mercurymcp_getaccounts",
    "mercurymcp_listtransactions",
    "mercurymcp_listinvoices",
    "mercurymcp_gettreasury"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "List transactions over $5,000 from last month across all accounts" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mercurymcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "List transactions over $5,000 from last month across all accounts" }],
  tools,
});

// Execute the tool call with the user's vaulted Mercury token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mercurymcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "List transactions over $5,000 from last month across all accounts" }],
  tools,
});

// Tool call runs with the user's vaulted Mercury token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mercurymcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "finance_agent",
  model: "gemini-2.5-pro",
  instruction: "Mercury MCP tools scoped to this user",
  tools,
});

await agent.run("List transactions over $5,000 from last month across all accounts");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Mercury MCP tool. Click to copy, paste into your agent, done.

Accounts and statements

Copy the prompt

Copied

List all our Mercury accounts.

Copy the prompt

Copied

Get last month's statement for the operating account.

Copy the prompt

Copied

Show our treasury accounts and their recent transactions.

Transactions and cards

Copy the prompt

Copied

List transactions over $5,000 from last month across all accounts.

Copy the prompt

Copied

Show every card on the operating account.

Copy the prompt

Copied

Get this transaction by ID with its attachments.

Invoices and recipients

Copy the prompt

Copied

List our invoices and the customers they were sent to.

Copy the prompt

Copied

Show pending send money approval requests.

Copy the prompt

Copied

List recipient invites that are still pending.

SEE HOW AUTH WORKS

Each user signs in to Mercury once; Scalekit stores and refreshes their tokens. Every call is scope checked, and every action is logged.

Authorize

Your user connects

Mercury MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Mercury MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Mercury MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Mercury MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other banking and finance connectors.

GTM and RevOps Teams

Revenue forecast commentary

Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Mercury token looks fine in a demo. In production every banking query looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Mercury today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Mercury as the user or through a shared account?

As the user. Each user signs in to Mercury once, and Scalekit stores and refreshes their tokens. Audit logs attribute every banking query to that user, not a shared service account.

Where is the Mercury OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Mercury?

Yes. Filter by tool name in listScopedTools, for example only the account and transaction tools for a reconciliation agent. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Mercury access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent move money in Mercury?

No. All 35 Mercury MCP tools are read-only. The agent can read accounts, transactions, cards, statements, invoices, recipients, treasury, and approval requests, but it cannot send payments or change anything in Mercury.