postgres-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URI | Yes | PostgreSQL connection URI | |
| OPENAI_API_KEY | No | OpenAI API key for experimental index tuning by LLM |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_schemasA | List all schemas in the database |
| list_objectsC | List objects in a schema |
| get_object_detailsB | Show detailed information about a database object |
| explain_queryA | Explains the execution plan for a SQL query, showing how the database will execute it and provides detailed cost estimates. |
| analyze_workload_indexesB | Analyze frequently executed queries in the database and recommend optimal indexes |
| analyze_query_indexesA | Analyze a list of (up to 10) SQL queries and recommend optimal indexes |
| analyze_db_healthA | Analyzes database health. Here are the available health checks:
|
| get_top_queriesA | Reports the slowest or most resource-intensive queries using data from the 'pg_stat_statements' extension. |
| execute_sqlB | Execute any SQL query |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: listing schemas, executing SQL, listing objects, getting details, explaining queries, analyzing indexes (with two variants), health checks, and top queries. No overlap or ambiguity.
All tool names follow a consistent verb_noun snake_case pattern (e.g., list_schemas, execute_sql, analyze_db_health). No mixing of styles or irregular verbs.
9 tools is an appropriate size for a database management and analysis server. It covers key operations without being overwhelming or too sparse.
The set covers schema inspection, SQL execution, object details, query analysis, index recommendations, health checks, and performance queries. Minor gaps like missing direct table size tools are acceptable given the analysis focus.