Hologres MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOLOGRES_HOST | Yes | The host address of the Hologres instance. | |
| HOLOGRES_PORT | Yes | The port number for the Hologres instance. | |
| HOLOGRES_USER | Yes | The access ID or username for the Hologres database. | |
| HOLOGRES_DATABASE | Yes | The name of the Hologres database. | |
| HOLOGRES_PASSWORD | Yes | The access key or password for the Hologres database. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execute_hg_select_sqlC | Execute SELECT SQL to query data from Hologres database. |
| execute_hg_select_sql_with_serverlessA | Use Serverless Computing resources to execute SELECT SQL to query data in Hologres database. When the error like "Total memory used by all existing queries exceeded memory limitation" occurs during execute_hg_select_sql execution, you can re-execute the SQL with the tool execute_hg_select_sql_with_serverless. |
| execute_hg_dml_sqlC | Execute (INSERT, UPDATE, DELETE) SQL to insert, update, and delete data in Hologres databse. |
| execute_hg_ddl_sqlA | Execute (CREATE, ALTER, DROP) SQL statements to CREATE, ALTER, or DROP tables, views, procedures, GUCs etc. in Hologres databse. |
| gather_hg_table_statisticsC | Execute the ANALYZE TABLE command to have Hologres collect table statistics, enabling QO to generate better query plans |
| get_hg_query_planC | Get query plan for a SQL query in Hologres database |
| get_hg_execution_planC | Get actual execution plan with runtime statistics for a SQL query in Hologres database |
| call_hg_procedureC | Call a stored procedure in Hologres database. |
| create_hg_maxcompute_foreign_tableB | Create a MaxCompute foreign table in Hologres database to accelerate queries on MaxCompute data. |
| list_hg_schemasA | List all schemas in the current Hologres database, excluding system schemas. |
| list_hg_tables_in_a_schemaA | List all tables in a specific schema in the current Hologres database, including their types (table, view, foreign table, partitioned table). |
| show_hg_table_ddlC | Show DDL script for a table, view, or foreign table in Hologres database. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| All Schemas in Hologres database | Hologres is a PostgreSQL-compatible OLAP product. List all schemas in Hologres database |
TDQS
Scored across 12 tools
Most tools have distinct purposes, such as executing different SQL types or listing schemas/tables, but there is some overlap between get_hg_execution_plan and get_hg_query_plan, which could cause confusion as both relate to query plans. The descriptions clarify the difference (runtime statistics vs. query plan), but the similarity in naming and function might lead to misselection in some contexts.
All tool names follow a consistent verb_noun pattern with the prefix 'hg_' for Hologres, such as execute_hg_ddl_sql and list_hg_schemas. The naming is uniform across all tools, using snake_case throughout, which makes the set predictable and easy to understand.
With 12 tools, the server is well-scoped for a database management system, covering key operations like SQL execution, procedure calls, table management, and query analysis. Each tool serves a specific function without redundancy, making the count appropriate for the domain.
The toolset provides comprehensive coverage for Hologres database operations, including CRUD-like SQL execution, schema/table listing, and performance analysis. A minor gap is the lack of tools for user or permission management, but core workflows for data querying and administration are well-covered, allowing agents to handle most tasks effectively.