{"id":"cdatasoftware-veeva-mcp-server-by-cdata","name":"veeva-mcp-server-by-cdata","homepage":null,"repo_url":"https://github.com/CDataSoftware/veeva-mcp-server-by-cdata","category":"devtools","subcategories":[],"tags":["mcp","stdio","jdbc","data-access","veeva","llm-tools","read-only"],"what_it_does":"Provides a local, read-only MCP server that wraps the CData JDBC Driver for Veeva so an MCP client (e.g., Claude Desktop) can list tables/columns and run SQL SELECT queries via simple MCP tool calls using JSON-RPC over stdio on the same machine.","use_cases":["Enable Claude/Desktop (MCP) users to query live Veeva data without writing SQL","Discover available Veeva tables and columns via tools","Run SELECT queries (read-only) through an MCP tool interface for analyst/research workflows"],"not_for":["Use as a network-exposed service (stdio only, same-machine clients)","Writing/updating/deleting data (described as read-only)","Cases requiring a hosted/remote MCP endpoint or load-balanced availability"],"best_when":"You want local interactive querying of Veeva data from an MCP client, with the user providing JDBC/driver configuration and credentials on the same host.","avoid_when":"You need fine-grained access controls, auditability, or robust multi-user security guarantees for remote usage; or you require guaranteed pagination/streaming for large result sets.","alternatives":["CData managed MCP platform (CData Connect AI) for remote capabilities","A direct JDBC client or custom service that executes parameterized queries","Other MCP servers or BI connectors for Veeva (if available)"],"af_score":48.5,"security_score":43.8,"reliability_score":22.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:41:22.097104+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":["Underlying CData JDBC Driver authentication (may include OAuth via the JDBC driver connection string)","Driver licensing step via the CData JDBC Driver installer JAR"],"oauth":true,"scopes":false,"notes":"The MCP server itself appears to rely on the JDBC driver configuration in the .prp file; README notes OAuth may require browser authentication when building the JDBC connection string."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Pricing for the CData JDBC driver and/or managed MCP offering is not specified in the README content provided; server is distributed under MIT but driver licensing is required."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":48.5,"security_score":43.8,"reliability_score":22.5,"mcp_server_quality":75.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":55.0,"rate_limit_clarity":10.0,"tls_enforcement":60.0,"auth_strength":45.0,"scope_granularity":20.0,"dependency_hygiene":50.0,"secret_handling":45.0,"security_notes":"Security posture is largely delegated to the underlying CData JDBC driver and to how credentials are stored in the .prp file (not detailed here). The MCP server is local-only via stdio, reducing network exposure, but there is no evidence of fine-grained tool-level authorization, row-level filtering controls, or explicit secret-handling/log redaction guidance in the provided README. TLS is not directly applicable to stdio transport; JDBC connection security depends on the JDBC driver configuration.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":20.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Server uses stdio and can only be used by clients running on the same machine","Tooling exposes run_query with SQL; agents should avoid overly broad SELECTs that could return very large result sets","Read-only nature: some agents may attempt write-style operations that the server/tooling may not support"]}}