Clover MCP server for AI agents

Live

BEARER TOKEN

POINT OF SALE

Accounting & Finance

Clover gives your agent point of sale operations for a merchant: build orders and record payments, apply discounts, manage inventory items and stock, and look up customers, employees, shifts, and refunds.

  • Per-user credentials: each call uses the actual user's access token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Clover
agent · Acme Q3
Run
How many payments did the Main Street store take yesterday, and what was the total?
S
clover_payment_list
109ms
Retail ops agent
Main Street took 184 payments yesterday totaling $9,412, including $1,138 in tips.
Sources: Clover payments, 184 records
clover
184 payments
18:29
Message Claude...

Tools your retail ops agent reaches for on Clover, scoped per user.

CALL ANY TOOL
120 tools for point of sale on Clover: create orders and line items, record payments, apply discounts and service charges, manage inventory, stock, and tax rates, and look up customers, employees, and shifts.
clover_atomic_order_checkout
Atomic order checkout
Calculate the totals and taxes for an order cart without creating the order. Returns the calculated order totals with orderCart, total, subtotal, totalTaxAmount, taxSummaries, isVat. Use clover_atomic_order_checkout to preview totals before creating an order. Use clover_atomic_order_create to actually create the order. Get inventory item IDs from clover_item_list.
Parameters
Name
Type
Required
Description
merchant_id
string
Required
Clover merchant ID (mId) the request applies to. Find it in the Clover Merchant Dashboard URL or in Settings > Account & Setup.
order_cart
object
Optional
Order cart to put items, discounts, modifications and order-related information. Provide a JSON object, for example {"id": "ABC123DEF4567"} for a reference to an existing record.
clover_atomic_order_create
Create atomic order
clover_attribute_list
List attribute
clover_category_delete
Delete category
clover_category_get
Get category
clover_category_update
Update category
clover_credit_refund_list
List credit refund
clover_customer_create
Create customer
clover_customer_phone_number_delete
Delete customer phone number
clover_device_get
Get device
clover_employee_order_list
List employee order
clover_item_bulk_create
Create item bulk
clover_item_group_get
Get item group
clover_item_group_list
List item group
clover_item_modifier_group_associate
Item modifier group associate
clover_item_stock_update
Update item stock
clover_merchant_properties_get
Get merchant properties
clover_modifier_create
Create modifier
clover_modifier_delete
Delete modifier
clover_modifier_group_modifier_list
List modifier group modifier
clover_order_discount_create
Create order discount
clover_order_discount_list
List order discount
clover_order_get
Get order
clover_order_line_item_delete
Delete order line item
clover_order_line_item_update
Update order line item
clover_order_line_items_bulk_create
Create order line items bulk
clover_order_service_charge_remove
Remove order service charge
clover_payment_list
List payment
clover_refund_get
Get refund
clover_tag_list
List tag

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
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);

// Clover tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["clover"], toolNames: [
    "clover_order_list",
    "clover_payment_list",
    "clover_item_stock_list"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Summarize yesterday's orders and payments and flag items that are low on stock" }] });
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: ["clover"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Summarize yesterday's orders and payments and flag items that are low on stock" }],
  tools,
});

// Execute the tool call with the user's vaulted Clover access 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: ["clover"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize yesterday's orders and payments and flag items that are low on stock" }],
  tools,
});

// Tool call runs with the user's vaulted Clover access 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: ["clover"] }, pageSize: 100,
});

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

await agent.run("Summarize yesterday's orders and payments and flag items that are low on stock");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Clover tool. Click to copy, paste into your agent, done.
Orders and payments
Copy the prompt
Copied
Calculate the total and tax for 2 lattes and a blueberry muffin.
Copy the prompt
Copied
List orders over $200 from today.
Copy the prompt
Copied
Show refunds issued this week.
Inventory
Copy the prompt
Copied
Set the stock for Oat Milk to 24 and alert me when it drops below 6.
Copy the prompt
Copied
Add a new item called Cold Brew at $4.50.
Copy the prompt
Copied
List every item in the Pastries category.
Customers and staff
Copy the prompt
Copied
Look up the customer with the email jamie@example.com.
Copy the prompt
Copied
List the shifts Alex worked this week.
Copy the prompt
Copied
Which employee took the most payments today?
SEE HOW AUTH WORKS
Each user connects their own Clover access token once, and Scalekit sends it with every call. Access tokens stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Clover
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
2
Store
Their
Clover
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
3
Resolve
When your agent calls a
Clover
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
4
Audit
Every
Clover
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 accounting 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
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.
Test other agents
See the same per-user auth pattern across other accounting and finance connectors.
GTM
Revenue forecast agent
Score pipeline coverage against quota across Salesforce and HubSpot, post forecast commentary to Slack, log snapshots to Sheets.
GTM
CRM AI agent
Turn each Granola call transcript into a HubSpot record update, a drafted Gmail follow-up, and a Slack recap.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Clover access token looks fine in a demo. In production every order and inventory change 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 key
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Clover 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 Clover as the user or through a shared access token?
As the user. Each user connects their own Clover access token once, and Scalekit sends it with every call. Audit logs attribute every order, payment, and inventory change to that user, not a shared service account.
Where is the Clover access token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Clover?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the list and get tools for orders, payments, and inventory without clover_order_delete, which deletes an order permanently. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Clover 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.
Which Clover merchant does the agent work on?
The merchant passed as merchant_id on each call, as long as the user's Clover access token can reach it. clover_merchant_get returns that merchant's profile, and the order, payment, inventory, and customer tools act on its data.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""clover"": {
""url"": ""https://mcp.scalekit.com/clover"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.clover]
url = ""https://mcp.scalekit.com/clover""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""clover"": {
""url"": ""https://mcp.scalekit.com/clover"",
""type"": ""http""
}
}
}