{"id":"jasondeepny-mysql-mcp-server","name":"mysql-mcp-server","homepage":null,"repo_url":"https://github.com/Jasondeepny/mysql-mcp-server","category":"devtools","subcategories":[],"tags":["mcp","stdio","mysql","springboot","java","database","agent-integration","devtools"],"what_it_does":"Provides an MCP server (stdio-based) that connects to MySQL databases using a Spring Boot Java application. The README indicates multiple data sources support and shows running the server via a packaged JAR with Spring datasource configuration passed as JVM system properties.","use_cases":["Enable an MCP-capable agent to execute MySQL-related operations (queries, schema exploration, etc.) via stdio transport","Connect to one or more MySQL data sources from an agent workflow","Run locally/within a controlled environment where database credentials can be supplied to the process"],"not_for":["Production deployments without proper hardening, credential management, and least-privilege controls","Publicly exposed services where database credentials or overly-privileged access could be abused","Teams needing a well-specified REST/HTTP API contract or SDKs"],"best_when":"You want a local stdio MCP integration for agent-driven database workflows and you can control database access tightly (networking + least-privilege + secret handling).","avoid_when":"You cannot safely supply DB credentials to a long-running process, or you need strong, documented error/rate-limit semantics and stable, versioned API contracts.","alternatives":["Use an existing, well-documented MySQL database connector tool via MCP (if available)","Build/host a dedicated backend service with a REST/GraphQL API that wraps database operations and enforces policy/limits","Use database-specific agent tooling (SQL execution tools) that implement strict query allowlists and result limits"],"af_score":30.5,"security_score":22.0,"reliability_score":27.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:50:49.455015+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["No explicit auth mechanism described for the MCP transport","Database authentication is supplied via Spring datasource username/password JVM properties (per README snippet)"],"oauth":false,"scopes":false,"notes":"The README shows supplying database credentials via -Dspring.datasource.username/password. There is no documented auth layer for the MCP server itself (e.g., API key, OAuth, IP allowlist)."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information provided (repository metadata only)."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":30.5,"security_score":22.0,"reliability_score":27.5,"mcp_server_quality":45.0,"documentation_accuracy":30.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":60.0,"rate_limit_clarity":0.0,"tls_enforcement":20.0,"auth_strength":30.0,"scope_granularity":10.0,"dependency_hygiene":30.0,"secret_handling":20.0,"security_notes":"Transport is stdio (not inherently TLS-based); README does not mention securing the MCP channel. Database credentials are supplied via -Dspring.datasource.password, which can be exposed via process listings/logging if not carefully managed. No evidence provided for least-privilege scopes, query restrictions, auditing, or structured error redaction.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":50.0,"error_recovery":20.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Credentials are passed as JVM system properties; agents or orchestration layers may accidentally log command lines or crash dumps containing secrets.","Because the README provides no MCP tool/schema details, an agent may not know available tools/arguments without additional documentation or inspecting the code.","Lack of documented safety/policy (query allowlists, max rows, timeouts) could lead to expensive or destructive queries unless the implementation enforces constraints."]}}