Search overlay panel for performing site-wide searches

Build Your Next Big Thing on Heroku. Sign Up Now!

MCP On Heroku

Code Execution Sandbox for Agents on Heroku

Large language models are good at writing code. Data from Anthropic shows that allowing Claude to execute scripts, rather than relying on sequential tool calls, reduces token consumption by an average of 37%, with some use cases seeing reductions as high as 98%.

Untrusted code needs a secure and isolated place to execute. We solved this with code execution sandboxes (powered by one-off dynos), launched alongside Heroku Managed Inference and Agents in May 2025.

Building AI-Powered Observability with Heroku Managed Inference and Agents

If you’ve ever debugged a production incident, you know the drill: IDE on one screen, Splunk on another, Sentry open in a third tab, frantically copying error messages between windows while your PagerDuty keeps buzzing.

You ask “What errors spiked in the last hour?” but instead of an answer, you have to context-switch, recall complex query syntax, and mentally correlate log timestamps with your code. By the time you find the relevant log, you’ve lost your flow. Meanwhile the incident clock keeps ticking away.

The workflow below fixes that broken loop. We’ll show you how to use the Model Context Protocol (MCP) and Heroku Managed Inference and Agents to pipe those observability queries directly into your IDE, turning manual hunting into instant answers.

Building Agents With Heroku AI and Pydantic AI

Building production-grade AI applications can be complex, but with Heroku and Pydantic AI, developers gain a powerful and reliable solution for integrating advanced AI capabilities. Heroku makes it easy to integrate AI into your applications with Heroku Managed Inference and Agents. With a single click, you can attach powerful Large Language Models like Anthropic’s Claude 4 Sonnet to your apps. Heroku AI also provides built-in tools like secure code execution and an OpenAI-compatible API that you can drop directly into popular frameworks and SDKs.

Introducing the Heroku AI Platform as a Service (AI PaaS)

Today, we are pleased to announce the evolution of Heroku to an AI Platform as a Service (AI PaaS). GenAI has changed how we build software (vibe coding), the kind of technology we use (Cursor, LLMs), the type of software we make (agents), and redefined what it means to be a developer in this new world.

In a recent Salesforce study, 84% of developers with AI say it helps their teams complete their projects …

Heroku AI: Heroku Remote MCP Server

Today, we’re thrilled to announce a new way in which agents can access the Heroku platform using the Heroku Remote MCP Server, now available at https://mcp.heroku.com/mcp.

This new remote server is an expansion of our earlier stdio-based MCP server and comes with secure OAuth authentication. It’s designed to provide a secure, scalable, and incredibly simple way for agents to interact with the Heroku platform and use tools to perform actions such as creating a Heroku …

Heroku AI: Managed Inference and Agents is now Generally Available

Many of the most exciting experiences we’re beginning to rely on every day are powered by AI; whether it’s conversational assistants, personalized recommendations or code generation, these experiences are powered by inference systems and intelligent agents. Behind the scenes, developers offload complex decisions, automate tasks, and compose intelligent applications using large language models and tool execution flows. Together, these AI-powered primitives are becoming a key complement to traditional application development, enabling a new wave of …

Heroku AI: Build and Deploy Enterprise Grade MCP Servers

Agents hold immense power, but their true potential shines when they connect to the real world, fetching data, triggering actions, or leveraging external tools. The Model Context Protocol (MCP) offers a standardized way for AI agents to do this.

MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various …

How I Improved My Productivity with Cursor and the Heroku MCP Server

Generative AI has been one incredible tool to improve my productivity not only for work but for personal projects too. I use it every day, from generating stories and images for my online role playing games to solving code and engineering problems and building awesome demos. Lately I’ve leaned into Cursor as my go‑to AI coding companion. Its inline suggestions and quick edits keep me moving without context‑switching. Connecting Cursor to my apps through the …

Introducing the Official Heroku MCP Server

We’re excited to announce the launch of the Heroku MCP Server, designed to bridge the gap between agent-driven development and Heroku’s AI PaaS. Having defined the platform experience for apps in the cloud, Heroku extends our developer and operator experience to AI capabilities. With the Heroku MCP Server, you can now expose Heroku’s robust platform capabilities as a set of intuitive actions accessible to AI agents through Model Context Protocol (MCP).

The Heroku MCP server enables AI-powered applications like Claude Desktop, Cursor, and Windsurf to directly interface with Heroku, unlocking new levels of automation, efficiency, and intelligence for managing your custom applications.

Subscribe to the full-text RSS feed for MCP On Heroku.