Spring AI Summary
SpringAI，LLM，MCP，Embedding
What is Spring AI Summary?
Spring AI Summary is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to springai，llm，mcp，embedding
SpringAI，LLM，MCP，Embedding
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- SpringAI，LLM，MCP，Embedding
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx spring-ai-summaryConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Spring AI Summary
Spring AI Summary is an educational reference repository demonstrating how to integrate the Spring AI framework with multiple LLM providers — including DeepSeek, Doubao, and OpenAI — covering chat, tool calling, vector database embeddings, RAG pipelines, MCP server patterns, and autonomous agent implementations. Built on Spring Boot 3.3.6 and Spring AI 1.0.0, it serves as a hands-on learning resource for Java developers who want to add AI capabilities to existing Spring applications without leaving the Spring ecosystem. Each feature is implemented as a separate module so developers can study one pattern at a time.
Prerequisites
- JDK 21 or later installed
- Maven 3.6+ (or mvnd for faster builds)
- Docker Desktop running (required for Milvus vector database and Nacos service registry modules)
- API keys for the LLM provider(s) you want to test: DeepSeek, OpenAI, or Doubao
- Git to clone the repository
Clone the repository and compile
Clone the spring-ai-summary repository and compile all modules, skipping tests on the first build to verify your environment is set up correctly.
git clone https://github.com/java-ai-tech/spring-ai-summary.git
cd spring-ai-summary
mvn clean compile -DskipTestsConfigure your API key
Edit the application.yml or application.properties file in the module you want to run. Set your LLM provider API key. The DeepSeek module config is shown as an example — never hardcode keys in source; use environment variables.
# src/main/resources/application.properties (DeepSeek example)
spring.ai.deepseek.api-key=${DEEPSEEK_API_KEY}
spring.ai.deepseek.base-url=https://api.deepseek.com
spring.ai.deepseek.chat.options.model=deepseek-chatSet your API key as an environment variable
Export the required API key before starting the application so it is injected via Spring's environment variable substitution.
export DEEPSEEK_API_KEY=your_actual_api_key_here
# or for OpenAI:
export SPRING_AI_OPENAI_API_KEY=your_openai_keyRun a chat module
Navigate into the spring-ai-chat module and start the Spring Boot application. The module exposes REST endpoints you can test with curl.
cd spring-ai-chat
mvn spring-boot:runTest the running application
Send a test request to the chat endpoint and verify you get an LLM response. You can also check token usage metrics via the Actuator endpoint.
# Test chat
curl "localhost:8081/api/deepseek/chatWithMetric?userInput=Who are you?"
# Check token usage metrics
curl localhost:8081/actuator/metrics/ai.total.tokensSpring AI Summary Examples
Client configuration
This project exposes its own HTTP API rather than connecting as a client. Use this curl pattern to call the running Spring Boot service.
{
"mcpServers": {
"spring-ai-summary": {
"command": "java",
"args": ["-jar", "/path/to/spring-ai-summary/spring-ai-mcp/target/spring-ai-mcp.jar"]
}
}
}Prompts and API calls to try
Use these curl commands or equivalent HTTP requests to explore the different Spring AI modules.
- curl "localhost:8081/api/deepseek/chatWithMetric?userInput=Explain Spring AI in one paragraph"
- curl "localhost:8081/api/openai/chat?message=What is vector similarity search?"
- curl localhost:8081/actuator/metrics/ai.completion.tokens
- curl localhost:8081/actuator/metrics/ai.prompt.tokens
- "Ask Claude: read the spring-ai-tool-calling module and explain how function calling is implemented"Troubleshooting Spring AI Summary
Build fails with 'Java 21 required' or source compatibility errors
Ensure your JAVA_HOME points to JDK 21+. Run 'java -version' to check. If you have multiple JDKs, set JAVA_HOME explicitly: 'export JAVA_HOME=$(/usr/libexec/java_home -v 21)' on macOS.
Application fails to start with 'Connection refused' to Milvus or Nacos
The vector database and service registry modules require Docker services. Run 'docker compose up -d' in the relevant module directory (check for a docker-compose.yml) before starting the Spring Boot application.
API key errors or 401 Unauthorized from the LLM provider
Ensure the environment variable is exported in the same shell session where you run 'mvn spring-boot:run'. Check that the variable name matches exactly what is referenced in application.properties (e.g., DEEPSEEK_API_KEY).
Frequently Asked Questions about Spring AI Summary
What is Spring AI Summary?
Spring AI Summary is a Model Context Protocol (MCP) server that springai，llm，mcp，embedding It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Spring AI Summary?
Follow the installation instructions on the Spring AI Summary GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Spring AI Summary?
Spring AI Summary works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Spring AI Summary free to use?
Yes, Spring AI Summary is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Spring AI Summary Alternatives — Similar Coding Agents Servers
Looking for alternatives to Spring AI Summary? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Spring AI Summary in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Spring AI Summary?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.