Activepieces MCP connector for AI agents

Tools your automation agent reaches for on Activepieces, scoped per user.

CALL ANY TOOL

Run workflow automation end to end: list flows, build new ones from a prompt, test, publish, and trace every failed run.

activepiecesmcp_ap_add_branch

Ap add branch

Add a conditional branch to a router step. Inserted before the fallback branch.

Parameters

Name

Type

Required

Description

branchName

string

Required

Display name for the new branch (e.g. "Branch 1")

flowId

string

Required

The id of the flow

routerStepName

string

Required

The name of the ROUTER step to add a branch to. Use ap_flow_structure to get valid values.

conditions

array

Optional

Conditions array (outer array = OR groups, inner array = AND conditions). Required for condition-type branches; omit to use an empty condition group.

activepiecesmcp_ap_build_flow

Ap build flow

activepiecesmcp_ap_change_flow_status

Ap change flow status

activepiecesmcp_ap_create_flow

Ap create flow

activepiecesmcp_ap_delete_branch

Ap delete branch

activepiecesmcp_ap_delete_flow

Ap delete flow

activepiecesmcp_ap_delete_step

Ap delete step

activepiecesmcp_ap_duplicate_flow

Ap duplicate flow

activepiecesmcp_ap_flow_structure

Ap flow structure

activepiecesmcp_ap_get_piece_props

Ap get piece props

activepiecesmcp_ap_get_run

Run ap get

activepiecesmcp_ap_insert_records

Ap insert records

activepiecesmcp_ap_list_ai_models

Ap list ai models

activepiecesmcp_ap_list_connections

Ap list connections

activepiecesmcp_ap_list_runs

Ap list runs

activepiecesmcp_ap_lock_and_publish

Publish ap lock and

activepiecesmcp_ap_manage_notes

Ap manage notes

activepiecesmcp_ap_read_step_code

Ap read step code

activepiecesmcp_ap_rename_flow

Ap rename flow

activepiecesmcp_ap_research_pieces

Ap research pieces

activepiecesmcp_ap_resolve_property_options

Ap resolve property options

activepiecesmcp_ap_retry_run

Run ap retry

activepiecesmcp_ap_search_actions

Ap search actions

activepiecesmcp_ap_search_triggers

Ap search triggers

activepiecesmcp_ap_setup_guide

Ap setup guide

activepiecesmcp_ap_test_step

Ap test step

activepiecesmcp_ap_update_branch

Ap update branch

activepiecesmcp_ap_update_record

Ap update record

activepiecesmcp_ap_update_step

Ap update step

activepiecesmcp_ap_validate_flow

Ap validate flow

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);

// Activepieces tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["activepiecesmcp"], toolNames: [
    "activepiecesmcp_ap_list_flows",
    "activepiecesmcp_ap_build_flow",
    "activepiecesmcp_ap_list_runs"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Which flows failed overnight?" }] });

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: ["activepiecesmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which flows are enabled right now?" }],
  tools,
});

// Execute the tool call with the user's vaulted Activepieces credential
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: ["activepiecesmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Build a flow that posts new Stripe payments to Slack." }],
  tools,
});

// Tool call runs with the user's vaulted Activepieces credential
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: ["activepiecesmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "activepieces_automation_agent",
  model: "gemini-2.5-pro",
  instruction: "Manage Activepieces flows for the signed-in user.",
  tools,
});

await agent.run("Why did the lead sync flow fail last night?");

Try these prompts

Copy any prompt into your agent. Each maps directly to an Activepieces tool. Click to copy, paste into your agent, done.

Flow operations

Copy the prompt

Copied

Which flows are enabled right now?

Copy the prompt

Copied

Disable the abandoned cart flow until we fix the coupon step.

Copy the prompt

Copied

Duplicate the onboarding flow and rename the copy to Onboarding v2.

Build and ship flows

Copy the prompt

Copied

Build a flow that posts new Stripe payments to #finance in Slack.

Copy the prompt

Copied

Test the welcome email flow with mock signup data.

Copy the prompt

Copied

Publish the lead sync flow if validation passes.

Debug runs

Copy the prompt

Copied

Which runs failed in the last 24 hours?

Copy the prompt

Copied

Why did the lead sync flow fail last night? Show the failing step.

Copy the prompt

Copied

Retry this morning's failed run and confirm it succeeds.

SEE HOW AUTH WORKS

Your users connect once. Their Activepieces credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Activepieces 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

Activepieces 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

Activepieces 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

Activepieces 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 automation connectors.

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.

Support and Ops Teams

Support ticket automation agent

Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Support and Ops Teams

Email-to-calendar agent

Reads scheduling intent out of Gmail threads, resolves the times everyone actually has free, and creates the event on the user's own Google Calendar. No shared service account.

Gmail

Google Calendar

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Activepieces token looks fine in a demo. In production every flow edit, publish, and delete looks like one service account, and you cannot tell who shipped the change that broke a live automation. 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.

Activepieces 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 Activepieces as the user or through a shared key?

As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every flow build, publish, and status change in your audit trail is attributed to a real user, not a shared service account.

Where is the Activepieces token stored?

In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically, and can be revoked from one dashboard.

Can I limit what the agent does in Activepieces?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example read-only run inspection without build, publish, or delete. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

Can the agent permanently delete flows or tables?

Only if you let it. Activepieces exposes destructive tools like ap_delete_flow and ap_delete_table, and deletion cannot be undone. Filter them out of listScopedTools for read-and-build agents, or keep them scoped so every delete is pre-checked and attributed to the user who asked.

On this page

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