Remote MCP, Global Steering, Sequential Hooks, and Simplified Trusted Commands
This release expands MCP capabilities with remote server support and one-click installation, introduces global steering rules and project-specific agent configuration, and refines agent workflows with improved hook execution, command trust, and targeted file context.
Remote MCP Support
Connect to MCP servers hosted anywhere on the internet via Streamable HTTP, accessing cloud services and APIs without local installation.
Global Steering Rules
Define global steering rules that apply across all your workspaces.
AGENTS.md Support
Support for the AGENTS.md standard to define guidelines, coding standards and architectural patterns. Add an AGENTS.md file to any configured steering file location, or to the root folder or any subfolder of your workspace, and they will be identified as workspace steering files.
One-Click MCP Installation
Simplified MCP server setup with automatic installation—get started with MCP tools faster than ever. View servers →
Environment Variable Expansion in MCP
Use environment variables in your MCP server configurations for flexible, environment-specific setups.
Targeted File Context in specs
![## Use Case 3: Extending User Preferences
**Scenario**: Add a "preferredPaymentMethod" field to UserPreferences
**Targeted Context Needed**:
#IIfile:src/types/app.ts:127-143]]
This shows just the UserPreferences interface, which is what needs modification. The agent doesn't need to see:
- The full User interface (lines 115-126)
- Payment method enums (lines 105-112)
- Subscription types (lines 158-180)
**Result**: Faster, more accurate implementation with less context pollution.](/images/changelogs/v0.5.0/targeted-context.png?h=e6ee3581)
Reference specific line ranges when adding files to context (e.g., `#[[file:src/utils/helper.ts:10-25]]`), giving you precise control over what the agent sees and enabling more focused implementations.
Agent Workflow improvements
Sequential Hook Execution: Run multiple agent hooks when a file matches multiple hook patterns, enabling more flexible automation workflows with sequential execution.
Simplified Trusted Commands: Command approval now uses pattern-based trust exclusively, providing consistent and predictable behavior. Automatic read-only command approval and dangerous pattern detection have been removed in favor of explicit pattern matching you control.
Enhanced MCP Debugging: Improved parsing and validation of MCP JSON files, ensuring more reliable server connections and better error handling. When configuration errors occur on save, Kiro MCP logs open automatically with an
Ask Kirobutton to debug issues with the agent.
Bug Fixes
File Management in Supervised Mode: Files no longer close automatically when rejecting changes, preserving your workspace state.
Improved terminal integration reliability: Enhanced shell integration to ensure Kiro's terminal execution maintains compatibility across different shell environments such as bash, zsh, and fish.
Chat Input Responsiveness: Fixed issue where chat input became unresponsive after adding code with
Ctrl+L.Autofix Behavior: Removed automatic formatting and autofix after edits to prevent unintended changes.