Changelog

Today we’re thrilled to introduce Knock Agent Toolkit and our new MCP server.

Knock Agent Toolkit

Agent Toolkit is a set of tools that enables your agents to send messaging across channels such as in-app, email, push, SMS, and chat apps (Slack, Microsoft Teams.) All messaging sent by the agent works within the guardrails of the messaging workflows and templates you configure in Knock.

const toolkit = await createAgentToolkit({
  permissions: {
    workflows: {
      trigger: ["comment-created", "task-completed", "welcome-user"],
    },
  },
});

Human-in-the-loop

An important part of building agents is enabling them to go to humans to provide input, verify work, and approve outputs. Agent Toolkit exposes a set of helper methods that make it easy to wrap your tool calls in asynchronous human approvals or inputs.

import { createToolkit } from "@knocklabs/agent-toolkit/ai-sdk";
 
const toolkit = createToolkit();
 
const classifyToolRequiringInput = toolkit.requireHumanInput(classifyWork, {
  workflow: "approve-classification",
  recipients: ["user_123"],
});

Our toolkit comes with built-in support for major agent frameworks and SDKs including Vercel AI SDK, LangChain, and OpenAI.

Knock MCP server

Anything you can do in the Knock dashboard you can now do using natural language.

We’re shipping a local MCP server that wraps Agent Toolkit and exposes the tools via the Model Context Protocol. The MCP server can be installed in any MCP-compatible client, including AI coding tools such as Cursor, Windsurf, or Claude Code.

We’re giving foundation models and tools like Cursor the ability to set up workflows, design emails, interact with Knock observability data, and much more.

Get started

You can get started today with Agent Toolkit and our MCP server by reading the documentation and installing the package via npm (@knocklabs/agent-toolkit).

The future is agentic. At Knock we’re thrilled to get the opportunity to partner with our customers and define how agents and humans work together.

To learn more, read the full announcement.