Skip to main content
Glama
yalinz-cloud

PostgreSQL MCP Server

by yalinz-cloud

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_MODELNoOpenAI model to usegpt-5.2-mini
CACHE_ENABLEDNoEnable schema cachingtrue
DATABASE_HOSTNoPostgreSQL hostlocalhost
DATABASE_NAMEYesDatabase name
DATABASE_PORTNoPostgreSQL port5432
DATABASE_USERYesDatabase user
CACHE_MAX_SIZENoMaximum number of cached schemas100
OPENAI_API_KEYYesOpenAI API key
OPENAI_TIMEOUTNoAPI timeout in seconds30
CACHE_SCHEMA_TTLNoSchema cache TTL in seconds3600
DATABASE_PASSWORDYesDatabase password
OPENAI_MAX_TOKENSNoMaximum tokens per request32000
SECURITY_MAX_ROWSNoMaximum rows per query10000
OPENAI_TEMPERATURENoModel temperature0.0
ADDITIONAL_DATABASESNoJSON array of additional database configurations
DATABASE_MAX_POOL_SIZENoMaximum connection pool size20
DATABASE_MIN_POOL_SIZENoMinimum connection pool size5
RESILIENCE_MAX_RETRIESNoMaximum retry count3
RESILIENCE_RETRY_DELAYNoInitial retry delay in seconds1.0
SECURITY_ALLOW_EXPLAINNoAllow EXPLAIN statementsfalse
OBSERVABILITY_LOG_LEVELNoLog levelINFO
RESILIENCE_RETRY_JITTERNoRetry delay jitter ratio (0-1)0.1
SECURITY_BLOCKED_TABLESNoComma-separated list of blocked tables
DATABASE_COMMAND_TIMEOUTNoQuery timeout in seconds30
OBSERVABILITY_LOG_FORMATNoLog format (json/text)json
SECURITY_BLOCKED_COLUMNSNoComma-separated list of blocked columns
RESILIENCE_BACKOFF_FACTORNoExponential backoff factor2.0
OBSERVABILITY_METRICS_PORTNoMetrics HTTP port9090
SECURITY_BLOCKED_FUNCTIONSNoComma-separated list of blocked PostgreSQL functions
SECURITY_MAX_EXECUTION_TIMENoQuery execution timeout in seconds30
OBSERVABILITY_METRICS_ENABLEDNoEnable Prometheus metricstrue
SECURITY_ALLOW_WRITE_OPERATIONSNoAllow INSERT/UPDATE/DELETE operationsfalse
RESILIENCE_LLM_CONCURRENCY_LIMITNoMaximum concurrent LLM calls5
RESILIENCE_CIRCUIT_BREAKER_TIMEOUTNoCircuit breaker timeout in seconds60
RESILIENCE_QUERY_CONCURRENCY_LIMITNoMaximum concurrent queries10
RESILIENCE_RATE_LIMIT_WAIT_TIMEOUTNoRate limit wait timeout in seconds10
RESILIENCE_CIRCUIT_BREAKER_THRESHOLDNoFailure count before circuit breaker trips5

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": 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

NameDescription
addA

Add two numbers

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.2/5.0

Scored across 1 tool

Disambiguation1/5

Only one tool exists, so there is no possibility of confusion between tools. However, the tool's purpose (adding two numbers) is completely unrelated to the server's stated domain of PostgreSQL, making the set conceptually incoherent.

Naming Consistency1/5

With a single tool named 'add', there is no pattern to evaluate. The name is also extremely generic and does not reflect the PostgreSQL domain.

Tool Count1/5

A single trivial arithmetic tool is an extreme mismatch for a PostgreSQL MCP server, which would be expected to expose database operations like querying, schema management, or connection handling.

Completeness1/5

The tool surface is severely incomplete for the stated purpose. A PostgreSQL server with only 'add' provides no database-related functionality and would fail any real agent task involving PostgreSQL.

Maintenance

ActivityMaintained
ResponsivenessNo issues