Skip to main content
Glama
zaboura

Vertica MCP Server

by zaboura
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VERTICA_SSLNoWhether to use SSL for the database connection.false
VERTICA_HOSTYesThe hostname or IP address of the Vertica database server.
VERTICA_PORTYesThe port number the Vertica database server is listening on.5433
VERTICA_USERYesThe username for database authentication.
VERTICA_DATABASEYesThe name of the database to connect to.
VERTICA_PASSWORDYesThe password for database authentication.
VERTICA_CACHE_TTLNoCache Time-To-Live in seconds.300
VERTICA_LAZY_INITNoIf set to 1, delays database connection until the first use.1
VERTICA_RATE_LIMITNoMaximum requests per minute.60
ALLOW_DDL_OPERATIONNoGlobal permission to allow DDL operations (e.g., CREATE, DROP).false
VERTICA_MAX_RETRIESNoMaximum number of retry attempts for failed queries.3
VERTICA_RETRY_DELAYNoBase delay for retries in seconds.0.1
VERTICA_MAX_RESULT_MBNoMaximum result size in Megabytes.100
VERTICA_QUERY_TIMEOUTNoQuery timeout in seconds.600
ALLOW_DELETE_OPERATIONNoGlobal permission to allow DELETE operations.false
ALLOW_INSERT_OPERATIONNoGlobal permission to allow INSERT operations.false
ALLOW_UPDATE_OPERATIONNoGlobal permission to allow UPDATE operations.false
SCHEMA_DDL_PERMISSIONSNoSchema-specific DDL permissions (e.g., staging:false,production:false).
VERTICA_CONNECTION_LIMITNoMaximum number of connections in the connection pool.10
SCHEMA_DELETE_PERMISSIONSNoSchema-specific delete permissions (e.g., staging:false,production:false).
SCHEMA_INSERT_PERMISSIONSNoSchema-specific insert permissions (e.g., staging:true,production:false).
SCHEMA_UPDATE_PERMISSIONSNoSchema-specific update permissions (e.g., staging:true,production:false).
VERTICA_HEALTH_CHECK_INTERVALNoInterval between health checks in seconds.60
VERTICA_SSL_REJECT_UNAUTHORIZEDNoWhether to reject unauthorized SSL certificates.true

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
run_query_safelyB
Safe query execution with size detection, pagination, and timeout support.

Args:
    query: SQL query to execute
    row_threshold: Maximum rows before requiring confirmation
    proceed: Whether to proceed with large result set
    mode: Execution mode ('page' or 'stream')
    page_limit: Rows per page when paginating
    include_columns: Include column names in response
    precount: Count total rows for large results (expensive)
    timeout: Query timeout in seconds (default from env)
execute_query_paginatedC

Execute query with pagination support and result size limits.

execute_query_streamC

Stream query results with batching and size limits.

get_table_structureC

Get table structure with caching support.

get_table_projectionsC

List projections for a table.

get_schema_viewsC

List views in schema with caching.

get_schema_tablesC

List tables in schema with caching.

get_database_schemasB

List database schemas with caching.

profile_queryC

Profile query execution with improved error handling.

database_statusB

Get database status with improved error handling and formatting.

analyze_system_performanceD

Analyze system performance with improved efficiency.

generate_health_dashboardC

Generate consolidated health dashboard with controlled output. Args: ctx: The context object. output_format: The format of the dashboard (default: compact, detailed, json). Returns: A dictionary containing the health dashboard.

Prompts

Interactive templates invoked by user choice

NameDescription
vertica_database_health_dashboardCompact health dashboard.
vertica_database_system_monitorSystem performance monitor.
vertica_compact_health_reportToken-efficient health report.
sql_query_safety_guardSQL safety guard.
vertica_query_performance_analyzer Vertica Performance Analyzer - Deep-dive query performance analysis with actionable optimization recommendations. Analyzes the given query execution plans, identifies bottlenecks, and provides concrete DDL suggestions for optimal Vertica projections, join strategies, and ROS container health.
vertica_sql_assistant Vertica SQL Assistant - Expert SQL query generation with Vertica-specific optimizations. Generates efficient, Vertica-optimized SQL queries following a structured approach: analyze → research → generate → execute → fix → deliver

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.9/5.0

Scored across 12 tools

Disambiguation4/5

Most tools have distinct purposes, but there is some overlap between execute_query_paginated, execute_query_stream, and run_query_safely, as all three handle query execution with different features. The descriptions help differentiate them, but an agent might need to carefully choose between these for query-related tasks.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern, such as analyze_system_performance, get_database_schemas, and profile_query. This predictability makes it easy for agents to understand and navigate the tool set without confusion.

Tool Count5/5

With 12 tools, the server is well-scoped for a Vertica database management system. The count covers essential operations like query execution, schema exploration, performance analysis, and health monitoring, without being overwhelming or too sparse for the domain.

Completeness4/5

The tool set provides comprehensive coverage for database operations, including query execution, schema inspection, performance analysis, and health dashboards. A minor gap is the lack of data manipulation tools (e.g., insert, update, delete), but this is reasonable if the server focuses on read-only or administrative tasks, and agents can work around this with existing query tools.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources