Stripe MCP Connector for AI Agents

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

CALL ANY TOOL

Manage subscriptions, search and execute any Stripe API operation, recommend integration patterns. Same toolkit, every framework, no auth plumbing.

stripemcp_atlas_company_formation

Atlas company formation

Stripe Atlas: start or resume a Delaware C corp/LLC formation. Set action to: - "list": check for existing applications before "create", using an authorized account. Returns applications the current user can access as primary representative. Show any matches to the user. Applications with submitted_at are already submitted; offer to resume only drafts or create a separate company. - "create": create a new Atlas application, which also creates a new Stripe merchant required for Atlas. You can call "create" from a sandbox or testmode account; the new Stripe account is always a live account. Follow the returned authorization instructions. - "retrieve": load the formation and next step on the authorized Atlas account. - "advance": save step and data. Follow next_step_instructions and next_step_schema; steps can be revisited. For a chosen merchant_id, get stripe_context from list_available_accounts_or_orgs. That tool checks session access, not application existence. If the account is missing, authorize it with manage_stripe_accounts and refresh the account list before retrieving its formation. Drafts only: submission, signing, payment, and personal tax IDs happen in the Dashboard. Creation is not idempotent. After a timeout or unclear failure, don't retry "create"; use "list" and "retrieve" before resending only missing changes using returned IDs.

Parameters

Name

Type

Required

Description

action

string

Required

List accessible Atlas applications, create a new one, retrieve the current formation, or save a formation step. One of: `list`, `create`, `retrieve`, `advance`.

livemode

boolean

Required

Whether to operate in livemode (true) or test mode/ sandbox (false). Must match the livemode of the stripe_context account.

stripe_context

string

Required

The account to target for this request. Use the `stripe_context` value returned by list_available_accounts_or_orgs.

data

object

Optional

Answers matching the returned next_step_schema. Required for advance except validate, where it is ignored. Omit for list, create, and retrieve.

step

string

Optional

Required for advance; use the step returned by retrieve. Omit for list, create, and retrieve.

stripemcp_list_available_accounts_or_orgs

List available accounts or orgs

stripemcp_manage_stripe_accounts

Manage stripe accounts

stripemcp_search_stripe_documentation

Search stripe documentation

stripemcp_send_stripe_feedback

Send stripe feedback

stripemcp_send_stripe_mcp_feedback

Send stripe mcp feedback

stripemcp_stripe_analytics

Stripe analytics

stripemcp_stripe_api_details

Stripe api details

stripemcp_stripe_api_read

Read stripe api

stripemcp_stripe_api_search

Search stripe api

stripemcp_stripe_api_write

Write stripe api

stripemcp_stripe_implementation_planner

Stripe implementation planner

Build your Agent

Drop the toolkit in, point it at the user, and your agent can manage Stripe subscriptions and call any Stripe API from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["stripemcp"], toolNames: ["stripemcp_list_available_accounts_or_orgs", "stripemcp_stripe_api_write", "stripemcp_stripe_api_search"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["stripemcp"], toolNames: ["stripemcp_list_available_accounts_or_orgs", "stripemcp_stripe_api_write", "stripemcp_stripe_api_search"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["stripemcp"], toolNames: ["stripemcp_list_available_accounts_or_orgs", "stripemcp_stripe_api_write", "stripemcp_stripe_api_search"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/stripemcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start managing Stripe from your workflows.

Billing actions

Copy the prompt

Copied

Pause subscription [sub_id] until [date].

Copy the prompt

Copied

Refund the last charge for customer [cus_id].

Copy the prompt

Copied

Upgrade [cus_id] from monthly to annual plan with prorated credit.

Reporting & search

Copy the prompt

Copied

Find all disputes opened in the last 7 days.

Copy the prompt

Copied

Show MRR by plan for active subscriptions.

Copy the prompt

Copied

List customers with failed payments this month.

SEE HOW AUTH WORKS

Users authorize Stripe once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Stripe 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

Stripe 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

Stripe 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

Stripe 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 payments 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 room sync

Pulls opportunity context from Salesforce, captures key decisions from Slack, and syncs a running summary to the deal room doc in Google Drive, but only when the deal actually changed.

People Ops and HR teams

Offer letter routing agent

Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.

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.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Stripe MCP today. Others 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 Stripe as the user or a shared service account?

As the user. Each Stripe account authorizes once and Scalekit resolves their credential at request time. All API calls are attributed to that user.

Where is the Stripe OAuth token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Refresh is automatic. Tokens never appear in prompts or LLM context.

Can I prevent the agent from executing destructive API calls?

Yes. Use listScopedTools to restrict the agent to read-only operations (account info, search, details) without granting execute_stripe_api.

What happens when a user revokes Stripe access?

The connection is invalidated on the next tool call. Subsequent requests fail closed with a clear error.

Is this safe to use for production billing workflows?

Yes. Per-user credential isolation, scope enforcement before every call, and a 90-day audit trail are built in. Every Stripe operation executes as the authorizing user with their Stripe permissions.

What other MCP connectors does Scalekit support?

Scalekit runs the QuickBooks MCP server, Xero MCP server, and HarvestAPI MCP server on the same per-user auth, token vault, and audit trail. Browse 600+ connectors in the MCP connector directory.