{"id":"cdatasoftware-amazon-athena-mcp-server-by-cdata","name":"amazon-athena-mcp-server-by-cdata","homepage":null,"repo_url":"https://github.com/CDataSoftware/amazon-athena-mcp-server-by-cdata","category":"ai-ml","subcategories":[],"tags":["mcp","amazon-athena","jdbc","llm-integration","data-analytics","local-stdio"],"what_it_does":"Provides a local, read-only MCP server that wraps a CData JDBC Driver for Amazon Athena, exposing Athena tables/columns and SELECT query execution as MCP tools for AI clients (e.g., Claude Desktop).","use_cases":["Ask natural-language questions over live Athena data without writing SQL","Retrieve table/column metadata for Athena","Run read-only SELECT queries through an MCP tool interface","Data exploration and lightweight analytics over Athena-backed datasets"],"not_for":["Running untrusted or user-supplied SQL without controls","Automated write/CRUD workflows (server is described as read-only)","Production deployments requiring centralized, multi-tenant network APIs (it uses stdio and local hosting)"],"best_when":"You want a developer-controlled, local MCP bridge from an AI desktop client to Athena via JDBC, primarily for read/analytics queries.","avoid_when":"You need robust server-side access controls, multi-client remote hosting, or fine-grained per-user authorization at the MCP layer.","alternatives":["Use the AWS Athena console or Athena APIs directly","Use a server-side JDBC/SQL gateway with a web API + auth (REST/GraphQL)","Use CData’s managed MCP platform (CData Connect AI) if you need remote access","Build a lightweight custom MCP server around Athena/Athena SDK with strict query validation"],"af_score":49.2,"security_score":39.2,"reliability_score":27.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:58:44.680239+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":["Uses a local .prp connection properties file for the underlying CData JDBC Driver authentication (may involve OAuth depending on the JDBC connection configuration)"],"oauth":false,"scopes":false,"notes":"The README indicates the underlying JDBC connection may use OAuth for the data source, but it does not specify MCP-level auth, scopes, or token handling inside this MCP server."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing details for the repo are provided. The CData JDBC driver licensing is required per the README."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":49.2,"security_score":39.2,"reliability_score":27.5,"mcp_server_quality":70.0,"documentation_accuracy":80.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":55.0,"rate_limit_clarity":0.0,"tls_enforcement":60.0,"auth_strength":35.0,"scope_granularity":20.0,"dependency_hygiene":50.0,"secret_handling":35.0,"security_notes":"Security controls appear to rely primarily on the underlying CData JDBC driver configuration in a local .prp file; the MCP server itself (per README) does not describe transport security, per-tool authorization, scopes, logging redaction, or secret management. The `run_query` tool accepts arbitrary SQL, so risk of data exfiltration and expensive queries exists unless the SQL input is constrained/validated by the operator or client.","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":["Server communicates via stdio and is only usable by clients running on the same machine.","The tool `run_query` takes a SQL string; agents may generate overly broad/expensive queries if not constrained.","README emphasizes read-only intent; agents should be prevented from attempting data-modifying SQL."]}}