Skip to main content
Glama
alaturqua

MCP Trino Server

by alaturqua

show_create_view

Retrieve the CREATE VIEW statement for a specific Trino view by providing catalog, schema, and view name parameters.

Instructions

Show the CREATE VIEW statement for a specific view

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
catalogYescatalog name
schema_nameYesschema name
viewYesThe name of the view

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The core implementation of show_create_view that executes the SQL query against Trino. It validates catalog/schema, constructs the SHOW CREATE VIEW query, executes it, and extracts the result.
    def show_create_view(
        self,
        catalog: str,
        schema: str,
        view: str,
    ) -> str:
        """Show the CREATE VIEW statement for a view.
    
        Args:
            catalog (str): The catalog name. If None, uses configured default.
            schema (str): The schema name. If None, uses configured default.
            view (str): The name of the view.
    
        Returns:
            str: The CREATE VIEW statement for the specified view.
    
        Raises:
            CatalogSchemaError: If either catalog or schema is not specified and not configured.
        """
        catalog = catalog or self.config.catalog
        schema = schema or self.config.schema
        if not catalog or not schema:
            raise CatalogSchemaError
        query = f"SHOW CREATE VIEW {catalog}.{schema}.{view}"
        result = json.loads(self.execute_query(query))
        return result[0]["Create View"] if result else ""
  • src/server.py:109-125 (registration)
    MCP tool registration using @mcp.tool() decorator. Wraps the client.show_create_view() call and defines the tool interface with Pydantic Field descriptions for parameters.
    @mcp.tool(description="Show the CREATE VIEW statement for a specific view")
    def show_create_view(
        catalog: str = Field(description="catalog name "),
        schema_name: str = Field(description="schema name "),
        view: str = Field(description="The name of the view"),
    ) -> str:
        """Show the CREATE VIEW statement for a view.
    
        Args:
            catalog: catalog name
            schema_name:  schema name
            view: The name of the view
    
        Returns:
            str: The CREATE VIEW statement
        """
        return client.show_create_view(catalog, schema_name, view)
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. While 'Show' implies a read-only operation, the description omits error handling (what happens if the view doesn't exist), permission requirements, or whether the returned DDL is formatted or raw. For a metadata retrieval tool with no safety annotations, this is insufficient behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence of nine words with zero redundancy. Every word serves the purpose of defining the tool's action and target, making it appropriately concise for the complexity level.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple input schema (3 flat string parameters) and presence of an output schema to define return values, the description is minimally adequate. However, the absence of annotations (safety hints) and lack of usage guidance leave gaps that prevent a higher score for a database metadata tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the schema already fully documents all three parameters (catalog, schema_name, view). The description mentions 'for a specific view' which loosely references the view parameter, but adds no semantic detail beyond the schema regarding parameter formats or relationships (e.g., that catalog and schema_name provide namespace context). Baseline 3 is appropriate when schema coverage is comprehensive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Show') with a clear resource ('CREATE VIEW statement') and scope ('for a specific view'). It effectively distinguishes from sibling tool 'show_create_table' by explicitly targeting 'VIEW' objects rather than tables.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'describe_table' or 'show_create_table'. It fails to mention prerequisites (e.g., view must exist) or when an 'execute_query' alternative might be preferable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/alaturqua/mcp-trino-python'

If you have feedback or need assistance with the MCP directory API, please join our Discord server