Mercury MCP connector for AI agents

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

CALL ANY TOOL

Access accounts, transactions, recipients, invoices, and treasury data. Same tool interface, scoped to the authorizing Mercury account.

mercury_accounts_list

List all Mercury accounts and current balances.

mercury_transactions_list

Fetch transactions with filters for date, amount, and type.

mercury_recipients_list

Retrieve payment recipients saved to the account.

mercury_invoices_list

List invoices with status, amount, and due date.

mercury_treasury_get

Get treasury account details and yield information.

mercury_payment_initiate

Initiate a payment to a saved recipient.

Build your Agent

Drop the toolkit in, point it at the user, and your agent can query Mercury banking data without touching a credential.

// Scalekit AgentKit — framework-agnostic
import { ScalekitClient } from "@scalekit/sdk";

const client = new ScalekitClient();
const token = await client.connections.getToken("mercurymcp", userId);
const mcp = new MCPClient({ token });

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

const sk = new ScalekitClient();
const token = await sk.connections.getToken("mercurymcp", userId);
const client = new OpenAI();
const resp = await client.responses.create({ tools: [{ type: "mcp", server_url: mcpUrl, headers: { Authorization: `Bearer ${token}` } }] });

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

const sk = new ScalekitClient();
const token = await sk.connections.getToken("mercurymcp", userId);
const client = new Anthropic();
const resp = await client.beta.messages.create({ mcp_servers: [{ url: mcpUrl, authorization_token: token }] });

// Google GenAI SDK
import { GoogleGenAI } from "@google/genai";
import { ScalekitClient } from "@scalekit/sdk";

const sk = new ScalekitClient();
const token = await sk.connections.getToken("mercurymcp", userId);
const ai = new GoogleGenAI();
const resp = await ai.models.generateContent({ tools: [{ mcpServers: [{ serverUrl: mcpUrl, httpOptions: { headers: { Authorization: `Bearer ${token}` } } }] }] });

Try these prompts

Paste any prompt into your agent to start managing Mercury banking from your workflow.

"Show me all Mercury account balances and flag any that have dropped below $10,000 in the last 7 days."

"List all transactions over $5,000 from the past month and group them by recipient."

"Which invoices are overdue by more than 30 days, and what's the total outstanding amount?"

"Show me the current treasury yield rate and compare it to last month's average."

"Who are our top 5 payment recipients by total sent in the last quarter?"

SEE HOW AUTH WORKS

Users authorize Mercury once. Their banking credentials stay vaulted, every call is 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

Same per-user auth pattern across other finance and accounting connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with a security model and builds the connector on top.

Without Scalekit

With Scalekit

OAuth token management

Manual refresh loops

Auto-rotated, vaulted

Credential storage

Plaintext in env vars

AES-256, per-user

Per-user scoping

Shared service token

Scoped to authorizing user

Audit trail

None

90-day log, per call

Revocation

Delete and redeploy

One API call

“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 my agent need a Mercury API key?

No. Each user authorizes via OAuth. Scalekit vaults the resulting token and injects it per call. Your agent code never handles credentials.

What happens if a user revokes access?

The token is invalidated immediately. Subsequent calls return an auth error and no data is returned. The audit log records the revocation event.

Can I use this in a multi-tenant SaaS product?

Yes. Credentials are isolated per user. Each call resolves the token scoped to the user making the request, never a shared service account.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit