tdsql-mcp 1.4.1__tar.gz → 1.4.2__tar.gz

{tdsql_mcp-1.4.1 → tdsql_mcp-1.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tdsql-mcp
-Version: 1.4.1
+Version: 1.4.2
 Summary: MCP server for Teradata Vantage — SQL execution and native analytics function reference for AI agents
 Project-URL: Homepage, https://github.com/ksturgeon-td/tdsql-mcp
 Project-URL: Repository, https://github.com/ksturgeon-td/tdsql-mcp

{tdsql_mcp-1.4.1 → tdsql_mcp-1.4.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "tdsql-mcp"
-version = "1.4.1"
+version = "1.4.2"
 description = "MCP server for Teradata Vantage — SQL execution and native analytics function reference for AI agents"
 readme = "README.md"
 requires-python = ">=3.10"

{tdsql_mcp-1.4.1 → tdsql_mcp-1.4.2}/skills/teradata-sql-analytics/SKILL.md

@@ -29,6 +29,11 @@ Apply these principles throughout the session:
 **1. Don't assume. Surface uncertainty and tradeoffs.**
 If you know a native function exists but haven't loaded its syntax topic, say so — don't write syntax from training knowledge. When multiple approaches fit (exact vs. approximate vector search, ARIMA vs. Holt-Winters, TD_XGBoost vs. TD_GLM), state the tradeoff and let the user decide. If the schema or task is ambiguous, ask before writing SQL.
 
+**Topic triggers — load these immediately when the task involves:**
+- Apache Iceberg, Delta Lake, Open Table Format, OTF tables, DATALAKE objects, three-tier notation (`datalake.db.table`) → read [syntax/open-table-format.md](syntax/open-table-format.md)
+- S3, Azure Blob, GCS, object store, READ_NOS, WRITE_NOS, CREATE FOREIGN TABLE, NOS foreign tables → read [syntax/object-store.md](syntax/object-store.md)
+- `describe_table` does not work for OTF or foreign tables — use `HELP TABLE` passed through `execute_query` instead
+
 **2. Minimum SQL that solves the problem. Nothing speculative.**
 Don't add columns, CTEs, or transformations that weren't requested. At Teradata scale, unnecessary work has real cost. Load only the syntax topics needed for the current task.
 

{tdsql_mcp-1.4.1 → tdsql_mcp-1.4.2}/src/tdsql_mcp/server.py

@@ -31,6 +31,10 @@ mcp = FastMCP(
         "AI_* functions, etc.) from training knowledge — training data for these functions is frequently "
         "incomplete or incorrect. Always call get_syntax_help to load authoritative syntax before writing "
         "any native function call. "
+        "CRITICAL: For Apache Iceberg or Delta Lake (Open Table Format) tables: always call "
+        "get_syntax_help(topic='open-table-format') before writing any DDL, DML, or query. "
+        "CRITICAL: For Native Object Store access (READ_NOS, WRITE_NOS, foreign tables pointing to "
+        "S3, Azure, or GCS): always call get_syntax_help(topic='object-store') before writing any SQL. "
         "Before writing any SQL: "
         "(1) call get_syntax_help(topic='sql-basics') for Teradata SQL fundamentals — reserved word quoting, "
         "DDL syntax, operator differences from standard SQL, "
@@ -40,6 +44,8 @@ mcp = FastMCP(
         "(4) load the relevant topic(s) for exact syntax. "
         "Use explain_query to validate syntax before executing. "
         "Use describe_table and list_tables to explore the schema. "
+        "IMPORTANT: describe_table does not work for OTF (Iceberg/Delta Lake) tables or NOS foreign tables "
+        "— use HELP TABLE passed through execute_query instead. "
         "Results are returned as JSON."
     ),
 )
@@ -301,6 +307,16 @@ def get_syntax_help(topic: str = "index") -> str:
     and required options are complex and training data is frequently wrong. This tool returns
     the authoritative syntax. When in doubt about exact syntax, load the topic first.
 
+    Topic quick-reference for common scenarios:
+      - Apache Iceberg tables, Delta Lake tables, Open Table Format (OTF), DATALAKE objects,
+        three-tier notation (datalake.db.table), time travel → topic='open-table-format'
+      - S3, Azure Blob, GCS, READ_NOS, WRITE_NOS, CREATE FOREIGN TABLE, NOS,
+        object store, foreign table → topic='object-store'
+      - ML, XGBoost, random forest, clustering, regression → topic='ml-functions'
+      - Embeddings, vector search, semantic search, RAG → topic='vector-search' or 'embeddings'
+      - Time series, forecasting, ARIMA → topic='uaf-concepts' then 'uaf-forecasting'
+      - LLM text analytics, sentiment, PII → topic='ai-text-analytics'
+
     Recommended call order:
       1. get_syntax_help(topic='guidelines') — see the canonical mapping of common SQL
          patterns to native Teradata functions (start here if unsure what exists)