Major Features
- Deploy servers directly from the Catalog: Go from discovery to a running managed server faster—and get clearer status that distinguishes “deployment complete” from when a server is actually ready after cold starts.
- MCP Watch (Shadow MCP discovery): Admins can now spot unmanaged MCP servers across devices, track discovery trends over time, and identify migration opportunities directly from Analytics.
- MCP Watch Re-analysis: Admins can now trigger re-analysis of discovered MCP servers directly from the UI.
- Microsoft Agent 365 Integration: Full OAuth broker support and catalog servers for Microsoft Agent 365.
- Server metrics dashboard: New per-server metrics tab with tool call health, usage, and performance charts to help troubleshoot issues faster.
- Agent Accounts (Beta): Register AI applications as agent accounts to authenticate programmatically and call MCP tools through Runlayer.
- Slack rollout improvements: Organization-wide Slack App installs make it easier to enable Slack notifications across the workspace, with support for multiple Slack apps per agent.
- Plugins improvements: Plugins now support OAuth authentication for safer, smoother connections in more environments.
- Safer deployment logs: Sensitive environment variables are now redacted in deployment logs by default.
- Faster audit logs at scale: More read-heavy operations (including audit logs) were optimized to keep the UI responsive under load.
- Improved tool security scanning performance: Added caching for tool list scanning to reduce repeated work and speed up scans.
- Updated ToolGuard: New threat detection capabilities and improved security scanner defaults.
- OAuth compatibility fixes: Better discovery and validation across providers, including fixes for edge-cases with client IDs and PKCE.
- Analytics improvements: Analytics graph now shows today’s tool calls for more up-to-date visibility.
- Bug fixes: Fixed PII scanner false positives on numeric IDs in URLs, OAuth token handling for tokens without expiration, and audit log validation for tool names with special characters.
Platform automation
Platform automation
- Agent Accounts (Beta): Register AI applications as agent accounts to authenticate programmatically (machine-to-machine or on-behalf-of) and call MCP tools through Runlayer.
- Microsoft Agent 365 Integration: Full OAuth broker support and catalog servers for Microsoft Agent 365.
- Runlayer self-MCP server: Run Runlayer itself as an MCP server for safe automation and debugging workflows.
- Security scanner management tools: New tools in Runlayer MCP for managing security scanner settings programmatically.
- MCP Catalog API service: Added a dedicated API for serving the catalog to downstream security scanners (API key authenticated).
- Catalog tool list support: Tool lists are now available alongside catalog data to support static analysis and compatibility checks.
Deploy & operations
Deploy & operations
- Deploy servers directly from the Catalog with Runlayer Deploy.
- Clearer deployment status that distinguishes “deployment complete” from actual server readiness after cold starts.
- Automatic redaction of sensitive environment variables in deployment logs.
- Ability to force a new deployment and trigger redeploys more explicitly.
- Backlinks from Deploy back to the originating Connector to make change tracking easier.
- Improved deployment performance and stability.
- Fixed audit log validation errors for tool names containing special characters.
Visibility & auditability
Visibility & auditability
- Server metrics: Tool call health, usage, and performance charts in the server details Metrics tab.
- MCP Watch dashboard: See shadow MCP discoveries, “managed available” migration opportunities, and trends over time in Analytics.
- MCP Watch re-analysis: Admins can now trigger re-analysis of discovered MCP servers directly from the UI.
- MCP Watch CLI: A CLI workflow to collect device-side MCP configuration scans.
- Broader MCP Watch client support: Added support for additional MCP clients (including Goose and Zed).
- MCP Watch in production: Expanded MCP Watch availability for production environments.
- Slack notifications improvements: Easier org-wide installs, richer message context (including tool input/output), support for multiple Slack apps per agent, and better support for common Slack deployment patterns.
- Analytics improvements: Analytics graph now shows today’s tool calls for more up-to-date visibility.
- Request correlation: Added request IDs to audit logs to make investigations and support workflows faster.
- More readable audit log records: Typed actor/resource fields and compatibility improvements for long-lived deployments.
- Audit log performance: Optimized database queries for faster audit log loading at scale.
- Better tracing: Added MCP method metadata and tool-call events to improve debugging and performance analysis.
Security & authentication
Security & authentication
- ToolGuard performance: Significant caching and scan optimizations to reduce repeated work and speed up security scanning.
- ToolGuard threat detection: Updated ToolGuard with new threat detection capabilities.
- Updated security scanner defaults: Improved default security scanner settings for better out-of-the-box protection.
- Tool list scan caching: Longer cache TTLs to reduce repeated tool list scans at scale.
- Lower token usage on large toolsets: Token reduction improvements for tool discovery/search flows.
- PII scanner accuracy: Fixed false positives (including numeric IDs in URLs).
- Safer proxying: Centralized and hardened sensitive-header stripping for proxied requests.
- Policy UX improvements: Refreshed policy dialogs and tables for clearer permissions and faster edits.
- Global policies fixes: More reliable create/edit flows and better group handling in policy assignment.
- OAuth discovery and validation: Improved discovery behavior across providers, including better fallbacks.
- OAuth edge-case fixes: Compatibility fixes for PKCE, redirect URIs, numeric client IDs, and tokens without expiration time.
- OAuth broker improvements: Expanded broker support, Microsoft Agent 365 vendor config, and more reliable behavior for upstream providers.
- Improved upstream OAuth handling: Better handling of upstream OAuth invalidation and edge cases.
Catalog & connectors UX
Catalog & connectors UX
- Updated Catalog (Discover) to the latest UI for faster browsing and clearer information density.
- Updated Connectors pages and Connector details to the latest UI, with improved layout and navigation.
- Improved authorization request flow (request access, reason capture, and follow-up permission prompts).
- Persisted search queries and connector filters when navigating between pages.
- More consistent tools and policies presentation (sorting, layout, and dialog improvements).
- Improved group management and group-related UX, including fixes and polish for common workflows.
- Expanded the catalog with new servers including Braintrust, Gong, Snowflake (OAuth), Lever, Workday, Salesforce (remote), Socket.dev, Scanner.dev, Amplitude, HuggingFace, BrowserUse, Heroku, CrowdStrike Falcon, and Microsoft Agent 365—plus refreshed metadata and icons.
- MCP Catalog fingerprints: Server and tool fingerprint identifiers for better tracking and deduplication.
- Better support for deploy-based servers inside catalog and registration flows.
- Improved small-screen behavior and table usability across multiple settings pages.
- Multiple UI polish fixes across dark mode, headers, spacing, and layout consistency.
- Connectors tab state now persists in the URL for easier sharing and navigation.
CLI & developer workflow
CLI & developer workflow
- CLI login via device flow for easier authentication from constrained environments.
- Added CLI cache clear command for simpler troubleshooting.
- Improved CLI scan output for faster investigation and clearer results.
- Multiple CLI releases with usability and stability improvements.
Major Features
- Permission Warnings: Users now see a warning before connecting an MCP client if they lack the necessary permissions.
- ToolGuard Area of Concern: Security violations now show the specific area of concern that triggered the detection.
- Added Pulumi and Parallel Search to the MCP catalog.
- CLI: New
pullcommand for downloadingrunlayer.yamldeployment configurations. - New optional MCP caching setting for
tools/listrequests to improve performance. - Increased rate limit to 1000 requests/hour for OAuth client registrations.
Major Features
- Visual Query Builder for Audit Logs: Advanced filtering UI for building complex queries.
- Security Alert Emails: Admins now receive email notifications when security violations occur, configurable in workspace settings.
- Added Grain, Fireflies, Iterable, Box, and Contentful to the MCP catalog.
- New guided onboarding flow for first-time users to configure their MCP clients and preferences.
- Runlayer Deploy now supports deploying arbitrary Docker images, not just MCP servers.
- Runlayer Deploy now includes a persistent NoSQL storage for deployed services.
- Verified icon now shown on trusted MCP servers that came from the catalog.
- Fixed PII Scanner false positives on ISO timestamps being detected as SSNs.
- CLI: Fixed edge-cases with token refresh and token expiration.
Major Features
- Server Disable/Enable: Admins can now disable MCP servers to temporarily prevent all access without deleting the server configuration.
- Alert Mode for Security Scanners: New “Alert” mode allows security scanners to log violations without blocking requests, useful for monitoring and tuning policies.
- Added MCP client name and version tracking to audit logs and analytics.
- Added Ramp to the MCP catalog.
- MCP tool annotations from servers are now displayed in the UI.
- Audit log drawer now shows the actual content that was blocked by security scanners.
Major Features
- Human-in-the-Loop Security Review: Admins can now review, approve, or reject security violations from the audit logs.
- Added Snowflake, ClickUp, and HubSpot to the MCP catalog.
- Added duplicate server detection to warn when creating a server with a configuration that already exists.
- Improved security violation error messages for non-admin users.
- Skip scanning image and audio content in tool responses for better performance.
- Various Projects page UI improvements.
Major Features
- Runlayer Deploy, a new way to deploy MCP servers via Runlayer’s managed infrastructure. Learn more.
- UI improvements including server drawer fixes and policy management enhancements.
Major Features
- Runlayer CLI
deploycommand: A new command for deploying Docker-based services to your Runlayer infrastructure. - Token Masking Scanner: Sensitive tokens are now redacted instead of blocked, providing better experience while maintaining security.
- Added a new setting to control whether employees can submit new MCP servers for admin approval and browse the Catalog to install MCPs. Enabled by default.
- Redesigned User Details page.
- Various UI improvements and bug fixes.
Major Features
- Policy Based Access Controls: Complete rewrite of the authorization engine with advanced condition-based policies.
- Support for policy conditions with operators like
contains,matches,in, and logical combinations. - Enhanced policy evaluation engine for fine-grained access control.
- Constraints over MCP client and MCP server attributes. Example: enforce internal-only email domains for Gmail MCP.
- OAuth Refresh Token Rotation: Automatic rotation of OAuth refresh tokens for improved security.
- Support for policy conditions with operators like
- Redesigned Pages: Completely redesigned settings, audit logs and users pages.
- OAuth from MCP Clients: Enables authenticating to upstream OAuth servers directly from MCP clients like ChatGPT, Claude, Cursor and others.
- Server Configuration Drawer: New streamlined interface for viewing and editing MCP servers.
- Audit Logs Redesign: Improved table layout and navigation.
- UI improvements including sticky headers and various bug fixes.
- MCP Prompts Support: Full integration with the MCP prompts specification.
- Enhanced Catalog: Added popularity-based sorting.
- Server Editing: Ability to edit server name and description from details page.
- Multiple UI improvements including calendar component, hover interactions, and analytics enhancements
- Expanded Client Support: Added ChatGPT, Gumloop, and additional AI platforms as supported MCP clients.
- Client-specific connection instructions and configuration examples.
- Setup guides for each platform’s MCP integration requirements.
- Improved OAuth Error-handling: Improved OAuth connection flow to surface clearer, fine-grained error messages, to help debug issues.
- Improved Prompt Guard v2: Updated to newer model version for better prompt attack detection.
- Improved Security Feedback: Enhanced security violation messages with better context for troubleshooting blocked requests.
- OAuth Compatibility: Added support for longer auth tokens from origin MCP servers.
- Local MCP Servers v2: Use local MCP servers with the same security, authz, observability and auditing as remote MCPs.
- Management API: Automate server and user provisioning via REST API with API key authentication. Full documentation at
/docs. - MCP Details Redesign:
- Rebuilt server details with tabbed navigation, client-specific setup instructions (Claude, Codex, others), and one-click deeplinks.
- Improved server card layouts and visual hierarchy for faster navigation and configuration access.
- Official MCP Registry Schema: Migrated catalog to standardized MCP registry schema. Ensures ecosystem compatibility and automatic validation.
- Improved Error messages and Timeouts:
- Enforced strict timeouts on all MCP operations. Prevents hung requests with predictable error messages.
- Captures stderr output, exit codes, and connection errors for faster troubleshooting of MCP server failures.
- Made analytics available for non-admin users, showing only their usage data
- Added Vercel, Intercom, Clockwise, Figma, Pagerduty & Pipedream to the MCP servers catalog
- Enhanced catalog page with improved links and navigation
- Fixed missing stdio arguments for local servers
- Fixed API 403 errors in Server Permissions tab
- Improved SCIM sync reliability for directory events older than 30 days
- Fixed problem with non-admin users visiting Permissions tab causing API Error
- Fixed SCIM sync initialization for organizations with directory activations older than 30 days
- Resolved issue where SCIM sync couldn’t initialize properly if the initial directory activation event was more than 30 days in the past
- Enhanced event retrieval logic to search through historical events when needed
- Improved sync reliability for long-established directory integrations
- Completely revamped SSO and SCIM implementation
- Added support for syncing Users and Groups from SCIM
- Added support for role mapping, to map IdP Groups to Runlayer roles
- Groups are editable (CRUD) when SCIM is disabled; read-only when SCIM is enabled
- Add a new AUTH_API_KEY secret (or
auth_api_keyvariable if you’re using the Terraform stack). Runlayer support will provide you with this value. - Update the value of the
auth_client_idvariable to the new client ID. Runlayer support will provide you with this value.
- Add support for custom NPM configurations and private package repositories
- Auto-add an ALLOW policy for the admin who created a server
- Prevent OAuth flow from ending prematurely if the popup needs to show an approval screen
- Fixed OAuth connection status for servers with refresh tokens
- Connections with valid refresh tokens are no longer incorrectly marked as expired in the UI
- Added integration support for Codex CLI
- Renamed “My Servers” to “MCPs” throughout the interface for clearer terminology
- Fixed OAuth token refresh functionality for MCP servers
- Resolved issue where expired OAuth tokens would not automatically refresh
- Improved authentication reliability for OAuth-enabled servers
- Enhanced session persistence for uninterrupted server connections
- Fixed an issue where the IAM permissions needed for Prompt Guard V2 were not being applied correctly
- Fixed editing servers throwing an error.
- Removed caching from user API endpoints.
- Manual OAuth Configuration: Support for MCP servers without Dynamic Client Registration (DCR)
- Configure OAuth client credentials directly for servers that don’t support automatic registration, like Github
- Client secrets are encrypted at rest
- Automatic detection when manual setup is required with guided UI flow
- OAuth flow now supports version 2025-06-18 of the MCP specification
- Catalog now has two entries for Github: one with OAuth and one with PAT token authentication
- Add Support for Local Servers
- Run MCP servers directly on your local machine without network dependencies
- Visual indicators distinguish local servers from hosted infrastructure
- Add local server Atlassian to Catalog
- Enhanced Prompt Attack Detection: New security scanner with improved accuracy and lower latency
- Labeled as Prompt Guard V2 in the security settings UI and turned on by default; legacy scanner renamed to “Prompt Guard (Legacy)”
- Advanced prompt attack detection system for better threat identification
- Infrastructure optimizations for faster response times
- Fixed a client-side caching bug where the version update banner would show up when it shouldn’t
- Fix JSON format not initializing correctly on server edit page
- Linear MCP Server: Updated to use HTTP streaming endpoint
- Role-Based Tool and Resource Visibility: Enhanced permission system with intelligent filtering
- Tools and resources are now filtered based on user permissions in list views
- Users only see items they have access to, eliminating confusing access denied scenarios
- Improved performance through optimized policy evaluation
- Replaced automatic admin bypass with proper role-based access control
- RSS-Enabled Changelog: Automatic RSS feed generation
- Users can now subscribe to changelog updates via RSS
- Cleaner, more minimal changelog format with categorized updates
- Improved readability with description labels for each version
- Improve E2E tests that test MCP server creation
- Enhanced CI/CD Pipeline: Improved build reliability for more stable deployments
- Raw JSON Server Configuration: Introduced dual editing modes (Form and JSON) for server configuration
- Toggle between intuitive form interface and powerful JSON editor
- Paste
.envcontent to automatically populate environment variables - Real-time validation with clear error messages
- Comprehensive testing for enhanced reliability
- OAuth Connection Handling: Fixed issue where tools and resources were fetched even when OAuth was not properly connected
- Improved Proxy Architecture: Enhanced performance through optimized middleware implementation
- Central Icon System: Implemented comprehensive icon system for improved visual consistency
- Enhanced visual hierarchy and user experience
- Consistent iconography across the platform
- MCP Server Validation: Added intelligent retry logic for improved reliability
- Automatic retry with smart intervals
- Enhanced OAuth discovery and error categorization
- Reduced false negatives from temporary network issues
- Load Testing Framework: Introduced comprehensive performance testing capabilities
- Configurable test scenarios for various workloads
- SSE response validation and compliance checks
- Performance benchmarking for scalability validation
- Per-Server Security Settings: Granular security controls for individual servers
- Override specific security scanners while maintaining global defaults
- Admin-only security configuration interface
- Flexible Inherit/Block/Alert/Allow options
- V2 Design Implementation: Major visual refresh
- New logo system and comprehensive icon library
- Component library with Storybook integration
- Consistent theming with design tokens
- Version Update Notifications: Smart in-app update system
- Automatic detection of new versions
- Dismissible notifications with user preferences
- Responsive design with theme support
- Global Security Scanner Settings: Centralized security configuration
- Unified security policy management
- Configurable scanner thresholds
- Enhanced governance capabilities
- Enhanced Version Management: Improved version tracking across deployments
- Security Scanner Optimization: Major performance improvements
- Consolidated scanning architecture for faster response times
- Optimized ML-based security scanning
- Maintained full security detection capabilities