Memberstack MCP connector for AI agents

CALL ANY TOOL

Nine tools covering app creation, environment switching, context management, and schema discovery for the full Memberstack API surface.

memberstackmcp_createapp

Createapp

Create a new Memberstack app (project) with isolated members, plans, data tables, and gated content. Only use when the user explicitly requests a new app. After creation the session context automatically switches to the new app.

Parameters

Name

Type

Required

Description

name

string

Required

Name for the new app. Maximum 24 characters.

stack

string

Required

Platform/stack for the app. Accepted values: WEBFLOW, VANILLA, WORDPRESS.

templateId

string

Optional

Webflow template ID to scaffold the app from. Only applicable for WEBFLOW stack.

wordpressPageBuilder

string

Optional

WordPress page builder plugin. Accepted values: GUTENBERG, ELEMENTOR, DIVI, BEAVER_BUILDER, BRICKS, CORNERSTONE, OTHER.

memberstackmcp_currentapp

Currentapp

memberstackmcp_currentuser

Currentuser

memberstackmcp_explore_tools

Explore Tools

memberstackmcp_get_tool_schema

Get Tool Schema

memberstackmcp_getmemberstackenvironment

Getmemberstackenvironment

memberstackmcp_listapps

Listapps

memberstackmcp_switchapp

Switchapp

memberstackmcp_switchmemberstackenvironment

Switchmemberstackenvironment

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="memberstackmcp")

mcp = MultiServerMCPClient({
    "memberstackmcp": {
        "url": "https://mcp.scalekit.com/memberstackmcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

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

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "memberstackmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/memberstackmcp
// Pass: Authorization: Bearer + token

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

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "memberstackmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/memberstackmcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="memberstackmcp")
# Connect to MCP at https://mcp.scalekit.com/memberstackmcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Discover & inspect

Copy the prompt

Copied

List all my Memberstack apps and tell me which environment each one is currently using.

Copy the prompt

Copied

Show me all available tools in the members category so I know what member operations I can automate.

Configure & switch

Copy the prompt

Copied

Switch my active app to the staging app and then switch the environment to SANDBOX so I can safely test.

Copy the prompt

Copied

Create a new Memberstack app called 'Community Portal' on the Webflow stack and confirm it switched to that app automatically.

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

1

Authorize

Your user connects

Memberstack 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

2

Store

Their

Memberstack 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

3

Resolve

When your agent calls a

Memberstack 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

4

Audit

Every

Memberstack 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 connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

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.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

“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 Memberstack MCP as the user or as a shared key?

Scalekit resolves a per-user credential for each call. The Memberstack MCP audit log shows the real user identity, not a shared service account.

Where is the Memberstack MCP token stored?

In Scalekit's AES-256 encrypted vault, isolated per tenant. Tokens are auto-refreshed before expiry and revocable from a single dashboard without code changes.

Can I limit what the agent is allowed to do in Memberstack MCP?

Pass a toolNames filter to listScopedTools. Scalekit enforces the allowed set before every API call — the agent cannot invoke tools outside the approved list.

What happens when a user revokes Memberstack MCP access?

The token is invalidated at the next tool call. The agent fails closed rather than falling back to a shared key. Other users are unaffected and the revocation event is logged with a timestamp.

Can the agent switch a Memberstack app to LIVE mode and make writes against production member data?

Yes, if the tool is in the approved list and the user's credential has LIVE access. To prevent unintended production writes, pass a toolNames filter that excludes switchMemberstackEnvironment or restrict the allowed environment values at the application layer. Scalekit logs every tool call with the resolved user identity, so any environment switch is traceable.

Memberstack MCP

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