Spring AI 1.1.0-M3 Release Notes

🎯 Highlights

Model Context Protocol (MCP) Java SDK 0.14.0 Upgrade

This release primarily focuses on upgrading to the Model Context Protocol (MCP) Java SDK version 0.14.0, bringing significant improvements to Spring AI's MCP integration capabilities. Key enhancements include:

Enhanced Resource Template Management: Improved resource template API consistency and management capabilities
Robust Error Handling: Better resilience for MCP server interactions with proper handling of non-compliant responses and edge cases
Spec Compliance Improvements: Proper resource not found handling and fixes for Content-Length: 0 responses
Client-Side Validation: New tool output schema validation and caching for improved client reliability
API Refinements: Better JSON type handling, consistent naming conventions, and optional lastModified field support in Annotations

These foundational improvements strengthen Spring AI's MCP implementation, providing a more reliable and feature-rich Model Context Protocol experience.

Additional Updates

This release also includes 7 new features, 11 bug fixes, 9 documentation improvements, and 16 other improvements across the Spring AI ecosystem.

⭐ New Features

MarkdownDocumentReader now supports processing multiple documents in a single operation 499ab3e
Added Azure Cosmos DB integration for chat memory persistence 1a35e8a
Improved error handling with fallback messages when tool execution encounters blank errors f2d57cc
Added support for the latest Claude models with improved naming conventions in the Anthropic integration #4516
Added metadata filtering capabilities to GemFireVectorStore for more precise vector search queries 78c5e00
Added MCP resource template support to server auto-configurations, enabling enhanced Model Context Protocol capabilities 97ac810
Introduced builder pattern support across the Mistral module for improved API usability b8dfc09

🪲 Bug Fixes

Improved tool/function calling reliability by adding a special warning when LLMs change tool names during execution #4349
Resolved issues with JsonSchemaGenerator when processing method input parameters, particularly for Mistral AI integration #4524
Corrected property access syntax in StTemplateRender for proper template rendering 0cea262
Corrected test configuration issues for MistralAI integration 4408c46
Fixed inconsistency where parameterized render(Map) failed to handle Resource in variables compared to no-arg render 0fd9fd5
Resolved issues with Jackson module loading by not using the Thread Context ClassLoader #4515 via #2921
Enhanced robustness of mergeToolUseEvents in StreamHelper and fixed handling of thinkingBlock.signature in event-to-response conversion 9907b2c
Removed unused member variables to improve code maintainability #4489
Fixed Ollama auto-configuration issues to ensure proper initialization b915413
Resolved an issue in the OllamaApiHelper component 5d8907f
Cleaned up the initializeContainer method by removing redundant parameters and assignments 84efb6a

📓 Documentation

Added comprehensive security reference documentation for Model Context Protocol integration #4532
Updated documentation to include Z.ai international site information and GLM-4.6 model support #4539
Updated documentation to reflect Spring Boot 3.5 release availability #4530
Improved documentation formatting by using inline literals 54f5127
Added documentation for metadata filtering capabilities in GemFireVectorStore d83c826
Corrected typo in ollama-embeddings.adoc documentation 9555a61
Corrected example code error in ChatMemory documentation for CassandraChatMemoryRepository #4476
Fixed example code errors in multimodality documentation #4475
Fixed incorrect class reference in MCP-related documentation #4466

🔨 Dependency Upgrades

Model Context Protocol (MCP) Java SDK 0.14.0

Primary motivation for this release - Upgraded to MCP Java SDK 0.14.0 and mcp-annotations to 0.5.1 #4531

This major upgrade brings critical improvements to Spring AI's MCP integration:

Resource Template Management: Refactored resource template API for better consistency and usability
Error Resilience: Enhanced server error handling with proper management of non-compliant notification responses and Content-Length: 0 scenarios
Spec Compliance: Proper resource not found handling according to MCP specification
Client Validation: Added tool output schema validation and caching capabilities
JSON Handling: Fixed JsonTypeInfo.DEDUCTION to avoid unnecessary includes
API Consistency: Corrected MCP_SESSION_ID naming convention for consistent identifier style
Annotations Enhancement: Added optional lastModified field to Annotations record

For complete details, see the MCP Java SDK 0.14.0 release notes.

Other Dependency Updates

Upgraded Apache Tika to 3.2.3 from 3.2.1 and jsoup to 1.21.2 from 1.21.1, resolving CVE-2025-54988 #4504
Upgraded the Couchbase client SDK to a newer version 351fbbb

🔩 Build Updates

Improved test coverage for KnuddelsRuntimeHints d0c9e86
Migrated to AssertJ's assertThatExceptionOfType for better test readability #4544
Fixed indentation for environment variables and added tracing to git checkout operations 0f436b4
Improved logging consistency with type-assured parameter binding 17c8e9e
Expanded test coverage for Milvus vector database integration d016b10
Improved test coverage for MCP tool callback builder functionality 46b9170
Improved test coverage for Mistral AI bindings properties processor #4483
Added autoconfigure-mcp-server-common to Bill of Materials for improved dependency management f907196
Refactored McpToolUtils to use builder pattern instead of deprecated constructors 8a2d86b
Improved test coverage for MultiQueryExpander, StreamHelper, and Query classes #4473
Added missing operator and edge case tests for AzureAiSearchFilterExpressionConverter #4467
Added comprehensive null safety and configuration tests for Azure OpenAI embeddings and Google GenAI runtime hints #4456

🔐 Security

Resolved security vulnerability CVE-2025-54988 through dependency upgrades of Tika and jsoup #4504

🙏 Contributors

Thanks to all contributors who made this release possible:

spring-projects/spring-ai v1.1.0-M3 Spring AI 1.1.0-M3 on GitHub