fix: improve some tools' parameters

chat_history.json

@@ -1 +1 @@
-[{"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "# Result\nThe tables in the database are:\n*   dim\\_agreement\n*   dim\\_customer\n*   dim\\_product\n*   dim\\_product\\_order\\_item\n\n# Explanation\nThe `list_tables` tool was called to retrieve a list of all available tables in the database schema. The result shows the names of these tables.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "what was my previous request ?", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "# Result\nlist all tables\n# Explanation\nThe user's previous request was to list all the tables in the database. This was determined by reviewing the previous turn in the conversation history.\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "count tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\n4\n# Explanation\nThe user requested the number of tables. The previous response listed the tables, and counting them gives the answer.\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "what was my last message ?", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\ncount tables\n# Explanation\nThe user's last message was \"count tables\". This was determined by reviewing the previous turn in the conversation history.\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "what was my very first message in this conversation?", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\nlist all tables\n# Explanation\nThe user's very first message in this conversation was \"list all tables\". This was determined by reviewing the conversation history.\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "total number of sales in 2024", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\nThe tables in the database are:\n*   dim\\_agreement\n*   dim\\_customer\n*   dim\\_product\n*   dim\\_product\\_order\\_item\n\n# Explanation\nThe `list_tables` tool was called to retrieve a list of all available tables in the database schema. The result shows the names of these tables.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\nThe tables in the database are:\n*   dim_agreement\n*   dim_customer\n*   dim_product\n*   dim_product_order_item\n\n# Explanation\nThe `list_tables` tool was called to retrieve a list of all available tables in the database schema. The result shows the names of these tables.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "hi there. show me the largest table name", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "I am sorry, I cannot directly determine the \"largest table name\" based on the available tools. I can list the tables and show their schemas, but I do not have a tool to determine table sizes. I would need a tool to get table sizes to fulfill this request. However, I can list the tables for you.\n\n```markdown\n# Result\nThe tables in the database are:\n*   dim\\_agreement\n*   dim\\_customer\n*   dim\\_product\n*   dim\\_product\\_order\\_item\n\n# Explanation\nThe `list_tables` tool was called to retrieve a list of all available tables in the database schema. The result shows the names of these tables.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "you are free to execute any sql query and get the size of each table and return me the count of largest one", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "I am sorry, I cannot directly determine the \"largest table\" based on the available tools. I can list the tables and show their schemas, but I do not have a tool to determine table sizes. I would need a tool to get table sizes to fulfill this request. I can list the tables for you, but I cannot provide the count of the largest one.", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}]
+[{"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "# Result\nThe tables in the database are:\n*   dim\\_agreement\n*   dim\\_customer\n*   dim\\_product\n*   dim\\_product\\_order\\_item\n\n# Explanation\nThe `list_tables` tool was called to retrieve a list of all available tables in the database schema. The result shows the names of these tables.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "what was my previous request ?", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "# Result\nlist all tables\n# Explanation\nThe user's previous request was to list all the tables in the database. This was determined by reviewing the previous turn in the conversation history.\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "count tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\n4\n# Explanation\nThe user requested the number of tables. The previous response listed the tables, and counting them gives the answer.\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "what was my last message ?", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\ncount tables\n# Explanation\nThe user's last message was \"count tables\". This was determined by reviewing the previous turn in the conversation history.\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "what was my very first message in this conversation?", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\nlist all tables\n# Explanation\nThe user's very first message in this conversation was \"list all tables\". This was determined by reviewing the conversation history.\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "total number of sales in 2024", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\nThe tables in the database are:\n*   dim\\_agreement\n*   dim\\_customer\n*   dim\\_product\n*   dim\\_product\\_order\\_item\n\n# Explanation\nThe `list_tables` tool was called to retrieve a list of all available tables in the database schema. The result shows the names of these tables.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "list all tables", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "```markdown\n# Result\nThe tables in the database are:\n*   dim_agreement\n*   dim_customer\n*   dim_product\n*   dim_product_order_item\n\n# Explanation\nThe `list_tables` tool was called to retrieve a list of all available tables in the database schema. The result shows the names of these tables.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "hi there. show me the largest table name", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "I am sorry, I cannot directly determine the \"largest table name\" based on the available tools. I can list the tables and show their schemas, but I do not have a tool to determine table sizes. I would need a tool to get table sizes to fulfill this request. However, I can list the tables for you.\n\n```markdown\n# Result\nThe tables in the database are:\n*   dim\\_agreement\n*   dim\\_customer\n*   dim\\_product\n*   dim\\_product\\_order\\_item\n\n# Explanation\nThe `list_tables` tool was called to retrieve a list of all available tables in the database schema. The result shows the names of these tables.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "you are free to execute any sql query and get the size of each table and return me the count of largest one", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "I am sorry, I cannot directly determine the \"largest table\" based on the available tools. I can list the tables and show their schemas, but I do not have a tool to determine table sizes. I would need a tool to get table sizes to fulfill this request. I can list the tables for you, but I cannot provide the count of the largest one.", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "can you find the foreign keys and relationships ?", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "I am unable to retrieve the foreign keys using the `get_foreign_keys` tool. It seems there's an issue with the tool's execution. However, based on the table schemas provided, I can infer the relationships.\n\n# Result\n\n*   **dim\\_agreement**:  Related to `dim_customer` via `customer_id`.\n*   **dim\\_customer**:  Likely related to `dim_product`, `dim_product_order_item`, and potentially other tables through their respective `customer_id` columns.\n*   **dim\\_product**: Related to `dim_customer` via `customer_id`, `dim_agreement` via `agreement_id`, and likely other tables through foreign key relationships.\n*   **dim\\_product\\_order\\_item**: Related to `dim_customer` via `customer_id`, `dim_agreement` via `agreement_id`, and likely related to a product order table via a `product_order_id`.\n\n# Explanation\n\nThe `get_foreign_keys` tool did not return the foreign key relationships. Therefore, I am relying on the schema descriptions to determine the relationships between the tables. The tables are connected through foreign keys, as described in the table descriptions.\n\n# Query\n\nN/A", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}, {"type": "human", "data": {"content": "get all the foreign keys and summarize them", "additional_kwargs": {}, "response_metadata": {}, "type": "human", "name": null, "id": null, "example": false}}, {"type": "ai", "data": {"content": "I am sorry, I cannot directly retrieve and summarize all foreign keys using the available tools. The `get_foreign_keys` tool did not work in a previous turn. However, I can describe the relationships between the tables based on the schema descriptions.\n\n# Result\n\n*   **dim\\_agreement**: Related to `dim_customer` via `customer_id`.\n*   **dim\\_customer**: Likely related to `dim_product` and `dim_product_order_item` through their respective `customer_id` columns.\n*   **dim\\_product**: Related to `dim_customer` via `customer_id`, `dim_agreement` via `agreement_id`, and likely other tables through foreign key relationships.\n*   **dim\\_product\\_order\\_item**: Related to `dim_customer` via `customer_id`, `dim_agreement` via `agreement_id`, and likely related to a product order table via a `product_order_id`.\n\n# Explanation\n\nThe `get_foreign_keys` tool did not return the foreign key relationships. Therefore, I am relying on the schema descriptions to determine the relationships between the tables. The tables are connected through foreign keys, as described in the table descriptions.\n\n# Query\n```sql\nN/A\n```", "additional_kwargs": {}, "response_metadata": {}, "type": "ai", "name": null, "id": null, "example": false, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": null}}]

postgre_mcp_server.py

@@ -352,11 +352,12 @@ def get_foreign_keys(table_name: str) -> str:
     JOIN information_schema.constraint_column_usage ccu
         ON rc.unique_constraint_name = ccu.constraint_name
     WHERE tc.constraint_type = 'FOREIGN KEY'
-        AND tc.table_schema = %s
-        AND tc.table_name = %s
+        AND tc.table_schema = {schema}
+        AND tc.table_name = {table_name}
     ORDER BY tc.constraint_name, kcu.ordinal_position
     """
-    return execute_query(sql)
+
+    return execute_query(sql, (schema, table_name))
 
 
 @mcp.tool(description="Fetches and formats the schema details for all tables in the configured database schema.")
@@ -428,15 +429,20 @@ async def generate_select_query(table_name: str) -> list[PromptMessage]:
 
 @mcp.prompt(description="Generates a prompt message to assist in writing analytical queries for a given table.")
 async def generate_analytical_query(table_name: str) -> list[PromptMessage]:
-    """Generate analytical queries for a table"""
+    """ Generate analytical queries for a table
+    Args:
+        table_name: The name of the table to generate analytical queries for
+    """
+    load_dotenv()
+    schema = os.getenv("DB_SCHEMA")
     try:
         async with db_lifespan(mcp) as db_ctx:
             pool = db_ctx.pool
             async with pool.acquire() as conn:
-                columns = await conn.fetch("""
+                columns = await conn.fetch(f"""
                     SELECT column_name, data_type
                     FROM information_schema.columns 
-                    WHERE table_schema = $1 AND table_name = $2
+                    WHERE table_schema = {schema} AND table_name = {table_name}
                     ORDER BY ordinal_position
                 """, db_ctx.schema, table_name)
 
@@ -477,7 +483,7 @@ def find_relationships(table_name: str, schema: str = 'public') -> str:
     """
     try:
         # First get explicit foreign key relationships
-        fk_sql = """
+        fk_sql = f"""
         SELECT 
             kcu.column_name,
             ccu.table_name as foreign_table,
@@ -492,18 +498,18 @@ def find_relationships(table_name: str, schema: str = 'public') -> str:
             ON ccu.constraint_name = tc.constraint_name
             AND ccu.table_schema = tc.table_schema
         WHERE tc.constraint_type = 'FOREIGN KEY'
-            AND tc.table_schema = %s
-            AND tc.table_name = %s
+            AND tc.table_schema = {schema}
+            AND tc.table_name = {table_name}
         """
 
         # Then look for implied relationships based on common patterns
-        implied_sql = """
+        implied_sql = f"""
         WITH source_columns AS (
             -- Get all ID-like columns from our table
             SELECT column_name, data_type
             FROM information_schema.columns
-            WHERE table_schema = %s 
-            AND table_name = %s
+            WHERE table_schema = {schema}
+            AND table_name = {table_name}
             AND (
                 column_name LIKE '%%id' 
                 OR column_name LIKE '%%_id'
@@ -538,8 +544,8 @@ def find_relationships(table_name: str, schema: str = 'public') -> str:
                 ON c.table_schema = t.table_schema 
                 AND c.table_name = t.table_name
                 AND (c.column_name = 'id' OR c.column_name = sc.column_name)
-            WHERE t.table_schema = %s
-                AND t.table_name != %s  -- Exclude self-references
+            WHERE t.table_schema = {schema}
+                AND t.table_name != {table_name}  -- Exclude self-references
         )
         SELECT 
             source_column as column_name,