PostgreSQL MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_MODEL | No | Model to use | gpt-5.2-mini |
| CACHE_ENABLED | No | Enable schema caching | true |
| DATABASE_HOST | No | PostgreSQL host | localhost |
| DATABASE_NAME | Yes | Database name (required) | |
| DATABASE_PORT | No | PostgreSQL port | 5432 |
| DATABASE_USER | Yes | Database user (required) | |
| CACHE_MAX_SIZE | No | Max number of cached schemas | 100 |
| OPENAI_API_KEY | Yes | OpenAI API key (required) | |
| OPENAI_TIMEOUT | No | API timeout in seconds | 30 |
| CACHE_SCHEMA_TTL | No | Schema cache TTL in seconds | 3600 |
| DATABASE_PASSWORD | Yes | Database password (required) | |
| OPENAI_MAX_TOKENS | No | Max tokens per request | 32000 |
| SECURITY_MAX_ROWS | No | Max rows per query | 10000 |
| OPENAI_TEMPERATURE | No | Model temperature | 0.0 |
| DATABASE_MAX_POOL_SIZE | No | Maximum connections in pool | 20 |
| DATABASE_MIN_POOL_SIZE | No | Minimum connections in pool | 5 |
| RESILIENCE_MAX_RETRIES | No | Max retry attempts | 3 |
| RESILIENCE_RETRY_DELAY | No | Initial retry delay in seconds | 1.0 |
| OBSERVABILITY_LOG_LEVEL | No | Log level | INFO |
| DATABASE_COMMAND_TIMEOUT | No | Query timeout in seconds | 30 |
| OBSERVABILITY_LOG_FORMAT | No | Log format (json/text) | json |
| RESILIENCE_BACKOFF_FACTOR | No | Exponential backoff factor | 2.0 |
| OBSERVABILITY_METRICS_PORT | No | Metrics HTTP port | 9090 |
| SECURITY_BLOCKED_FUNCTIONS | No | Comma-separated blocked functions (optional) | |
| SECURITY_MAX_EXECUTION_TIME | No | Query execution timeout in seconds | 30 |
| OBSERVABILITY_METRICS_ENABLED | No | Enable Prometheus metrics | true |
| SECURITY_ALLOW_WRITE_OPERATIONS | No | Allow INSERT/UPDATE/DELETE | false |
| RESILIENCE_CIRCUIT_BREAKER_TIMEOUT | No | Circuit breaker timeout in seconds | 60 |
| RESILIENCE_CIRCUIT_BREAKER_THRESHOLD | No | Failures before circuit breaker opens | 5 |
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": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {
"tasks": {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
}
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| addA | Add two numbers |
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 1 tool
Only one tool exists, so no ambiguity between tools.
With a single tool, naming consistency is inherently maintained.
A single trivial arithmetic tool is extremely thin for a PostgreSQL MCP server, fitting the description of an extreme mismatch.
The server's name suggests database-related functionality, but the only tool adds two numbers, leaving the entire database surface missing.