{"id":"dgdev91-java-mcp-sql-server","name":"java-mcp-sql-server","homepage":null,"repo_url":"https://github.com/DGdev91/java-mcp-sql-server","category":"ai-ml","subcategories":[],"tags":["ai-ml","mcp","sql","postgresql","mysql","mariadb","oracle","sqlserver","sqlite","java","data-access","database-exploration"],"what_it_does":"Provides an MCP server (Java 21+) that connects to relational databases via JDBC and exposes tools to list schemas/tables, inspect table structure, query table data, and execute custom SQL (optionally restricted to SELECT). Supports stdio (local launch) and HTTP/SSE (remote connection) modes.","use_cases":["Database exploration for LLM/MCP agents (schemas, tables, columns, primary keys)","Read-only data querying for investigation and research","Building agent workflows that translate user intent into SQL with controlled tool access"],"not_for":["Production systems requiring strong authN/authZ, auditability, and hardened security controls out of the box","Write-heavy workloads or multi-tenant environments without additional network controls and least-privilege DB accounts","Handling sensitive regulated data without verified compliance controls"],"best_when":"You control the database credentials, run locally (stdio) or within a trusted network (HTTP/SSE), and mostly need read/inspection SQL capabilities for development or controlled internal use.","avoid_when":"You need internet-exposed remote access, fine-grained per-user permissions, or strong reliability guarantees without additional operational hardening; also avoid when you cannot enforce SELECT-only (or can’t constrain downstream SQL execution).","alternatives":["Other MCP database tools/servers (if available)","Direct SQL connectors via application code (agent calls your backend API)","Using database-aware ORMs/tools with your own API layer and policy enforcement","Commercial database copilots/agents with audited connectors"],"af_score":51.0,"security_score":31.8,"reliability_score":23.8,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T20:01:08.622440+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":"http://localhost:3000/mcp","has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Environment-variable DB credentials (JMCP_DB_USERNAME, JMCP_DB_PASSWORD) for database login"],"oauth":false,"scopes":false,"notes":"No user-facing auth mechanism is documented for the MCP server itself; access control appears to rely on network exposure and the underlying database credentials/privileges."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":null},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":51.0,"security_score":31.8,"reliability_score":23.8,"mcp_server_quality":72.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":85.0,"rate_limit_clarity":0.0,"tls_enforcement":20.0,"auth_strength":25.0,"scope_granularity":10.0,"dependency_hygiene":50.0,"secret_handling":60.0,"security_notes":"TLS/auth for the MCP HTTP/SSE endpoint are not documented; security likely depends on running locally/trusted networks. Authentication to the database is via username/password env vars, and no per-user authorization/scopes are described. Execution includes a potentially write-capable SQL tool when the select-only flag is disabled, so principle-of-least-privilege at the DB user is critical. Rate limits, audit logging, and structured error/code guidance are not described.","uptime_documented":0.0,"version_stability":35.0,"breaking_changes_history":30.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Potentially dangerous capability: execute_query can run non-SELECT statements when JMCP_QUERY_SELECT_ONLY=false; agents may attempt writes if tool usage is not constrained.","HTTP/SSE mode implies remote network access; without documented MCP-layer auth, ensure you run behind a firewall/reverse proxy with access control.","Credential handling is via environment variables; agents or operators must ensure secrets are not leaked through logs or misconfiguration."]}}