Agentic AI Platform Change Log

MCP / tool calling / API

Extensions are now generally available for every incident.io Investigations customer, bringing the skills engineers have written and the tools their team has built, including internal MCP servers, into Nexus so investigations and the @incident agent can use them. Every tool is classified as read, write or destructive, and teams decide where each one can run.

Teams can point the incident agent at homegrown systems without waiting for a native integration, while per tool classification keeps control over what an investigation may change.

Integrations

A new incident.io plugin bundles its remote MCP server with skills that teach agents how to use it, and is listed in the Claude Code, Cowork and Cursor plugin marketplaces. It supports several plugin formats and updates itself as new skills ship.

Teams running coding or ops agents can give them incident, alert, on call and investigation access with a one line install, and admins can push it to a whole workspace.

Workflow orchestration

incident.io launched an update enhancing workflow automation and the actionability of its AI Agent. The release introduces a secure secrets store for workflows, the ability to sign workflow webhook requests, and triggers based on alert creation or resolution. Furthermore, the AI Agent has been upgraded to independently resolve incidents, direct escalations, and suggest both custom fields and timestamps during an active response.

Engineering and SRE teams can now orchestrate more complex and secure automations without hardcoding credentials in webhooks. The expanded AI Agent capabilities reduce manual overhead during incidents by allowing responders to execute critical workflow steps conversationally.