{"id":"stylepatrick-spring-ai-mcp-server-client","name":"spring-ai-mcp-server-client","homepage":null,"repo_url":"https://github.com/stylepatrick/spring-ai-mcp-server-client","category":"devtools","subcategories":[],"tags":["ai-ml","spring","spring-boot","mcp","mcp-server","mcp-client","sse","tool-calling","java","openai"],"what_it_does":"Provides a demo Spring AI MCP (Model Context Protocol) server that exposes simple tool/function-calling (math: sum/multiply) over SSE, and a client component that connects to that MCP server and offers a REST endpoint (/question) to accept user questions and produce model completions using OpenAI.","use_cases":["Demonstrate or prototype MCP server/client integration with Spring AI","Expose specific backend functions/tools (e.g., math utilities) to an LLM via MCP","Build a simple interactive service that accepts user input via REST and routes execution through MCP tool calling","Learning/reference implementation for SSE-based MCP transport with Spring Boot"],"not_for":["Production deployments requiring robust authn/authz, rate limiting, and hardened error handling by default","Use cases needing full-featured tool marketplaces, complex pagination, or standardized API contracts beyond the demo"],"best_when":"You want a minimal reference implementation to understand Spring AI MCP integration and tool-calling flow (SSE + function callbacks) quickly.","avoid_when":"You need enterprise-grade security controls, clear rate limiting/error semantics, or long-term backward-compatibility guarantees based on documented release practices (not evidenced here).","alternatives":["Other MCP server/client examples in Spring AI or other frameworks","Direct REST/GraphQL integration with tool endpoints (instead of MCP)","Use an MCP gateway/proxy or managed agent tooling that includes auth/rate limiting out of the box"],"af_score":38.8,"security_score":38.0,"reliability_score":20.0,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:59:47.646819+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":["Java"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["OpenAI API key for the client component (application.yml)"],"oauth":false,"scopes":false,"notes":"No auth for the described MCP/SSE endpoints or the client REST endpoint is documented in the README content provided."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing for the project itself is stated; OpenAI API usage may incur costs from the client component."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":38.8,"security_score":38.0,"reliability_score":20.0,"mcp_server_quality":55.0,"documentation_accuracy":60.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":35.0,"rate_limit_clarity":10.0,"tls_enforcement":60.0,"auth_strength":25.0,"scope_granularity":10.0,"dependency_hygiene":45.0,"secret_handling":55.0,"security_notes":"TLS enforcement for SSE/REST endpoints is not stated; Spring Boot defaults may apply but should not be assumed from the README. Auth is not documented for MCP server/SSE or the client REST endpoint; OpenAI API key is used by client via configuration. TRACE logging for MCP-related packages is enabled in example config, which can increase risk of sensitive data in logs if left on.","uptime_documented":0.0,"version_stability":35.0,"breaking_changes_history":20.0,"error_recovery":25.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["README indicates SSE + MCP; agent reliability may depend on SSE connection stability and timeouts (not documented).","Logging level is configured to TRACE for MCP components; running at TRACE in production can leak sensitive data or increase log noise if not managed carefully.","Auth/rate limiting for the REST endpoint and SSE endpoints is not documented; agents should not assume protection is present."]}}