Skip to main content
Glama
MCP PostgreSQL Operations

MCP PostgreSQL Operations

by call518

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
POSTGRES_DBNoDefault database name for connectionstestdb
POSTGRES_HOSTNoPostgreSQL server hostname or IP address127.0.0.1
POSTGRES_PORTNoPostgreSQL server port number5432
POSTGRES_USERNoPostgreSQL connection username (needs read permissions)postgres
POSTGRES_PASSWORDYesPostgreSQL user password (supports special characters)

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

MCP-PostgreSQL-Ops inspects one PostgreSQL server (12-18) for operations and monitoring: server and database information, schema structure, query performance, locks, VACUUM/autovacuum and bloat, index and I/O statistics, WAL, replication, and capacity.

Scope and permissions

  • Every tool runs predefined read-only SQL against the configured server (POSTGRES_HOST/PORT/USER). Use the tools for facts; never guess, simulate, or invent results.

  • Tools that accept database_name query that database; without it they use the configured default database (POSTGRES_DB). Visibility depends on the connected role's privileges; when results look incomplete, say that the role may lack access (for example pg_read_all_stats) instead of concluding nothing exists.

  • There is no tool or switch that changes the database. Do not claim to have run VACUUM, killed a session, changed a setting, or created/dropped an index. You may suggest SQL for the user to review and run themselves; label it as not executed.

Reporting results

  • Report what the tool returned. Quote errors as-is. Never present an error, an empty result, or a version/extension notice as a healthy or successful outcome.

  • Tools that depend on pg_stat_statements or pg_stat_monitor fail when the extension is missing; report that and point to installing it. pg_stat_monitor is optional and unavailable on managed services such as RDS/Aurora.

  • Tools for newer versions (for example get_wal_summarizer_status on PG 17+, get_async_io_status on PG 18+) return a notice on older servers. Report the notice; do not substitute other data.

Asking before acting

  • Before suggesting destructive SQL (pg_terminate_backend, DROP, VACUUM FULL, REINDEX, ALTER SYSTEM), state its impact (locks, downtime, restart needs) and let the user decide.

  • get_table_schema_info, get_database_schema_info, and get_table_relationships need a specific database. If the user did not name one, ask, or offer to list databases with get_database_list; do not guess a database name.

Meaning of numbers

  • Most pg_stat_* values are cumulative since the last statistics reset or server start, not per-interval rates. Say so when presenting counts or totals; do not treat them as current load.

  • Active sessions, locks, running VACUUM operations, and async I/O are point-in-time snapshots.

  • Bloat figures are estimates from dead-tuple statistics, not measured on-disk free space.

  • Keep units as returned (ms, bytes, pretty sizes). Do not compare cache hit ratios across databases without noting their activity volumes.

  • A missing column on an older PostgreSQL version is "not available on this version", not zero.

Large results

  • Many tools accept limit (default 20; most clamp to 1-100, some lower). Start with the default, narrow with schema_name, table_name, table_pattern, or database_name, and raise limit only when the user needs more rows.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_lock_monitoringA

[Tool Purpose]: Monitor current locks and potential deadlocks in PostgreSQL

[Exact Functionality]:

  • List all current locks held and waited for by sessions

  • Show blocked and blocking sessions, lock types, and wait status

  • Help diagnose lock contention and deadlock risk

  • Filter results by granted status, state, mode, lock type, or username

[Required Use Cases]:

  • When user requests "lock monitoring", "deadlock check", "blocked sessions", etc.

  • When diagnosing performance issues due to locking

  • When checking for blocked or waiting queries

  • When filtering specific types of locks or users

[Strictly Prohibited Use Cases]:

  • Requests for killing sessions or force-unlocking

  • Requests for lock configuration changes

  • Requests for historical lock data (only current state is shown)

get_wal_statusA

[Tool Purpose]: Monitor WAL (Write Ahead Log) status and statistics

[Exact Functionality]:

  • Show current WAL location and LSN information

  • Display WAL file generation rate and size statistics

  • Monitor WAL archiving status and lag

  • Provide WAL-related configuration and activity metrics

[Required Use Cases]:

  • When user requests "WAL status", "WAL monitoring", "log shipping status", etc.

  • When diagnosing replication lag or WAL archiving issues

  • When monitoring database write activity and WAL generation

[Strictly Prohibited Use Cases]:

  • Requests for WAL configuration changes

  • Requests for manual WAL switching or archiving

  • Requests for WAL file manipulation or cleanup

Returns: WAL status information including current LSN, WAL files, archiving status, and statistics

get_replication_statusA

[Tool Purpose]: Monitor PostgreSQL replication status and statistics

[Exact Functionality]:

  • Show current replication connections and their status

  • Display replication lag information for standbys

  • Monitor WAL sender and receiver processes

  • Provide replication slot information and statistics

[Required Use Cases]:

  • When user requests "replication status", "standby lag", "replication monitoring", etc.

  • When diagnosing replication issues or performance problems

  • When checking replication slot usage and lag

[Strictly Prohibited Use Cases]:

  • Requests for replication configuration changes

  • Requests for replication slot creation or deletion

  • Requests for failover or switchover operations

Returns: Replication status including connections, lag information, slots, and statistics

get_server_infoA

[Tool Purpose]: Check basic information and connection status of PostgreSQL server

[Exact Functionality]:

  • Retrieve PostgreSQL server version information

  • Display connection settings (with password masking)

  • Verify server accessibility

  • Check installation status of extensions (pg_stat_statements, pg_stat_monitor)

[Required Use Cases]:

  • When user requests "server info", "PostgreSQL status", "connection check", etc.

  • When basic database server information is needed

  • When preliminary check is needed before using monitoring tools

[Strictly Prohibited Use Cases]:

  • Requests for specific data or table information

  • Requests for performance statistics or monitoring data

  • Requests for configuration changes or administrative tasks

Returns: Comprehensive information including server version, connection info, and extension status

get_current_database_infoA

[Tool Purpose]: Get information about the current database connection

[Exact Functionality]:

  • Show the name of the currently connected database

  • Display database-specific information like encoding, locale, and size

  • Provide connection context for clarity in multi-database environments

[Required Use Cases]:

  • When user asks "what database am I connected to?", "current database", etc.

  • When clarifying database context for analysis operations

  • When troubleshooting connection issues or confirming target database

[Strictly Prohibited Use Cases]:

  • Requests for database structure changes or creation/deletion

  • Requests for user authentication or permission changes

  • Requests for configuration modifications

get_database_listA

[Tool Purpose]: Retrieve list of all databases and their basic information on PostgreSQL server

[Exact Functionality]:

  • Retrieve list of all databases on the server

  • Display owner, encoding, and size information for each database

  • Include database connection limit information

[Required Use Cases]:

  • When user requests "database list", "DB list", "database info", etc.

  • When need to check what databases exist on the server

  • When database size or owner information is needed

[Strictly Prohibited Use Cases]:

  • Requests for tables or schemas inside specific databases

  • Requests for database creation or deletion

  • Requests related to user permissions or security

Returns: Table-format information including database name, owner, encoding, size, and connection limit

get_table_listA

[Tool Purpose]: Retrieve list of all tables and their information from specified database (or current DB)

[Exact Functionality]:

  • Retrieve list of all tables in specified database

  • Display schema, owner, and size information for each table

  • Distinguish table types (regular tables, views, etc.)

[Required Use Cases]:

  • When user requests "table list", "table listing", "schema info", etc.

  • When need to understand structure of specific database

  • When table size or owner information is needed

[Strictly Prohibited Use Cases]:

  • Requests for data inside tables

  • Requests for table structure changes or creation/deletion

  • Requests for detailed column information of specific tables

get_user_listA

[Tool Purpose]: Retrieve list of all user accounts and permission information on PostgreSQL server

[Exact Functionality]:

  • Retrieve list of all database user accounts

  • Display permission information for each user (superuser, database creation rights, etc.)

  • Include account creation date and expiration date information

[Required Use Cases]:

  • When user requests "user list", "account info", "permission check", etc.

  • When user permission management or security inspection is needed

  • When account status overview is needed

[Strictly Prohibited Use Cases]:

  • Requests for user password information

  • Requests for user creation, deletion, or permission changes

  • Requests for specific user sessions or activity history

Returns: Table-format information including username, superuser status, permissions, and account status

get_table_schema_infoA

[Tool Purpose]: Retrieve detailed schema information for specific table or all tables in a database

[Exact Functionality]:

  • Retrieve detailed column information including data types, constraints, defaults

  • Display primary keys, foreign keys, indexes, and other table constraints

  • Show table-level metadata such as size, row count estimates

[Required Use Cases]:

  • When user requests "table schema", "column info", "table structure", etc.

  • When detailed table design information is needed for development

  • When analyzing database structure and relationships

[Strictly Prohibited Use Cases]:

  • Requests for actual data inside tables

  • Requests for table structure changes or DDL operations

  • Requests for performance statistics (use other tools for that)

get_database_schema_infoA

[Tool Purpose]: Retrieve detailed information about database schemas (namespaces) and their contents

[Exact Functionality]:

  • Show all schemas in a database with their owners and permissions

  • Display schema-level statistics including table count and total size

  • List all objects (tables, views, functions) within specific schema

  • Show schema access privileges and usage patterns

[Required Use Cases]:

  • When user requests "database schema info", "schema overview", "namespace structure", etc.

  • When analyzing database organization and schema-level permissions

  • When exploring multi-schema database architecture

[Strictly Prohibited Use Cases]:

  • Requests for actual data inside tables

  • Requests for schema structure changes or DDL operations

  • Requests for individual table details (use get_table_schema_info for that)

get_table_relationshipsA

[Tool Purpose]: Analyze table relationships including foreign keys, dependencies, and inheritance

[Exact Functionality]:

  • Show foreign key relationships (inbound and outbound)

  • Display view dependencies and table references

  • Analyze inheritance and partition relationships

  • Identify orphaned tables and relationship patterns

[Required Use Cases]:

  • When user requests "table relationships", "foreign keys", "dependencies", etc.

  • When analyzing database schema design and data model

  • When planning data migration or schema changes

[Strictly Prohibited Use Cases]:

  • Requests for actual data inside tables

  • Requests for relationship modifications or DDL operations

  • Requests for performance statistics (use other tools for that)

get_active_connectionsA

[Tool Purpose]: Retrieve all active connections and session information on current PostgreSQL server

[Exact Functionality]:

  • Retrieve list of all currently active connected sessions

  • Display user, database, and client address for each connection

  • Include session status and currently executing query information

[Required Use Cases]:

  • When user requests "active connections", "current sessions", "connection status", etc.

  • When server load or performance problem diagnosis is needed

  • When checking connection status of specific users or applications

[Strictly Prohibited Use Cases]:

  • Requests for forceful connection termination or session management

  • Requests for detailed query history of specific sessions

  • Requests for connection security or authentication-related changes

Returns: Information including PID, username, database name, client address, status, and current query

get_pg_stat_statements_top_queriesA

[Tool Purpose]: Analyze top queries that consumed the most time using pg_stat_statements extension

[Exact Functionality]:

  • Retrieve top query list based on total execution time

  • Display call count, average execution time, and cache hit rate for each query

  • Support identification of queries requiring performance optimization

[Required Use Cases]:

  • When user requests "slow queries", "performance analysis", "top queries", etc.

  • When database performance optimization is needed

  • When query performance monitoring or tuning is required

[Strictly Prohibited Use Cases]:

  • When pg_stat_statements extension is not installed

  • Requests for query execution or data modification

  • Requests for statistics data reset or configuration changes

get_pg_stat_monitor_recent_queriesA

[Tool Purpose]: Analyze recently executed queries and detailed monitoring information using pg_stat_monitor extension

[Exact Functionality]:

  • Retrieve detailed performance information of recently executed queries

  • Display client IP and time bucket information by execution period

  • Provide more detailed monitoring data than pg_stat_statements

[Required Use Cases]:

  • When user requests "recent queries", "detailed monitoring", "pg_stat_monitor", etc.

  • When real-time query performance monitoring is needed

  • When client-specific or time-based query analysis is required

[Strictly Prohibited Use Cases]:

  • When pg_stat_monitor extension is not installed

  • Requests for query execution or data modification

  • Requests for monitoring configuration changes or data reset

get_database_size_infoA

[Tool Purpose]: Analyze size information and storage usage status of all databases in PostgreSQL server

[Exact Functionality]:

  • Retrieve disk usage for each database

  • Analyze overall server storage usage status

  • Provide database list sorted by size

[Required Use Cases]:

  • When user requests "database size", "disk usage", "storage space", etc.

  • When capacity management or cleanup is needed

  • When resource usage status by database needs to be identified

[Strictly Prohibited Use Cases]:

  • Requests for data deletion or cleanup operations

  • Requests for storage configuration changes

  • Requests related to backup or restore

Returns: Table-format information with database names and size information sorted by size

get_table_size_infoA

[Tool Purpose]: Analyze size information and index usage of all tables in specified schema

[Exact Functionality]:

  • Retrieve size information of all tables within schema

  • Analyze index size and total size per table

  • Provide table list sorted by size

[Required Use Cases]:

  • When user requests "table size", "schema capacity", "index usage", etc.

  • When storage analysis of specific schema is needed

  • When resource usage status per table needs to be identified

[Strictly Prohibited Use Cases]:

  • Requests for table data deletion or cleanup operations

  • Requests for index creation or deletion

  • Requests for table structure changes

get_postgresql_configA

[Tool Purpose]: Retrieve and analyze PostgreSQL server configuration parameter values

[Exact Functionality]:

  • Retrieve all PostgreSQL configuration parameters (when config_name is not specified)

  • Retrieve current value and description of specific configuration parameter

  • Filter configurations by text pattern (when filter_text is specified)

  • Display whether configuration can be changed and if restart is required

[Required Use Cases]:

  • When user requests "PostgreSQL config", "config", "parameters", etc.

  • When checking specific configuration values is needed

  • When searching for configurations containing specific text

  • When configuration status identification is needed for performance tuning

[Strictly Prohibited Use Cases]:

  • Requests for configuration value changes or modifications

  • Requests for PostgreSQL restart or reload

  • Requests for system-level configuration changes

get_index_usage_statsA

[Tool Purpose]: Analyze usage rate and performance statistics of all indexes in database

[Exact Functionality]:

  • Analyze usage frequency and efficiency of all indexes

  • Identify unused indexes

  • Provide scan count and tuple return statistics per index

[Required Use Cases]:

  • When user requests "index usage rate", "index performance", "unnecessary indexes", etc.

  • When database performance optimization is needed

  • When index cleanup or reorganization is required

[Strictly Prohibited Use Cases]:

  • Requests for index creation or deletion

  • Requests for index reorganization or REINDEX execution

  • Requests for statistics reset

get_vacuum_analyze_statsA

[Tool Purpose]: Analyze VACUUM and ANALYZE execution history and statistics per table

[Exact Functionality]:

  • Retrieve last VACUUM/ANALYZE execution time for each table

  • Provide Auto VACUUM/ANALYZE execution count statistics

  • Analyze table activity with tuple insert/update/delete statistics

[Required Use Cases]:

  • When user requests "VACUUM status", "ANALYZE history", "table statistics", etc.

  • When database maintenance status overview is needed

  • When performance issues or statistics update status verification is required

[Strictly Prohibited Use Cases]:

  • Requests for VACUUM or ANALYZE execution

  • Requests for Auto VACUUM configuration changes

  • Requests for forced statistics update

get_table_bloat_analysisA

[Tool Purpose]: Analyze table bloat based on dead tuple statistics and size information

[Exact Functionality]:

  • Calculate bloat ratio based on dead tuples vs total tuples

  • Estimate bloat size in bytes and human-readable format

  • Show last VACUUM/AUTOVACUUM timestamps for maintenance tracking

  • Identify tables requiring VACUUM maintenance

  • Filter tables by name pattern using SQL LIKE or ILIKE matching

  • Sort results by bloat severity (dead tuple ratio and count)

[Required Use Cases]:

  • When user requests "table bloat", "bloat analysis", "dead tuples", etc.

  • When identifying tables that need VACUUM maintenance

  • When investigating database storage efficiency and space usage

  • When troubleshooting performance issues related to table bloat

  • When analyzing specific table groups (e.g., tables with "user", "log", "temp" in names)

[Strictly Prohibited Use Cases]:

  • Requests for automatic VACUUM execution

  • Requests for bloat removal or cleanup operations

  • Requests for table restructuring or data modification

get_database_bloat_overviewA

[Tool Purpose]: Provide database-wide bloat overview and summary statistics

[Exact Functionality]:

  • Summarize bloat statistics across all schemas

  • Identify schemas and tables with highest bloat ratios

  • Calculate total estimated bloat size per schema

  • Show aggregate dead tuple counts and maintenance status

[Required Use Cases]:

  • When user requests "database bloat overview", "bloat summary", etc.

  • When getting high-level view of database storage efficiency

  • When planning database maintenance activities

  • When investigating overall database performance issues

[Strictly Prohibited Use Cases]:

  • Requests for automatic maintenance operations

  • Requests for bloat cleanup or removal

  • Requests for schema or database restructuring

get_autovacuum_statusA

[Tool Purpose]: Analyze autovacuum configuration and current maintenance status for tables

[Exact Functionality]:

  • Analyze autovacuum trigger conditions based on dead tuple thresholds

  • Calculate current dead tuple ratios vs autovacuum trigger points

  • Show autovacuum configuration settings per table

  • Identify tables requiring immediate autovacuum attention

  • Estimate next autovacuum execution likelihood

[Required Use Cases]:

  • When user requests "autovacuum status", "autovacuum configuration", "vacuum trigger analysis", etc.

  • When planning autovacuum optimization and tuning

  • When troubleshooting autovacuum performance issues

  • When identifying tables with autovacuum problems

[Strictly Prohibited Use Cases]:

  • Requests for autovacuum configuration changes

  • Requests for manual VACUUM execution

  • Requests for autovacuum process restart or control

get_autovacuum_activityA

[Tool Purpose]: Monitor recent autovacuum and autoanalyze activity patterns and execution history

[Exact Functionality]:

  • Track recent autovacuum and autoanalyze execution patterns

  • Analyze autovacuum frequency and timing intervals

  • Show tables with most/least autovacuum activity

  • Calculate average time between autovacuum executions

  • Identify tables with irregular autovacuum patterns

[Required Use Cases]:

  • When user requests "autovacuum activity", "autovacuum history", "vacuum patterns", etc.

  • When monitoring autovacuum performance and effectiveness

  • When troubleshooting autovacuum scheduling issues

  • When analyzing autovacuum workload distribution

[Strictly Prohibited Use Cases]:

  • Requests for autovacuum process control or restart

  • Requests for autovacuum configuration modifications

  • Requests for manual vacuum scheduling

get_running_vacuum_operationsA

[Tool Purpose]: Monitor currently running VACUUM and ANALYZE operations in real-time

[Exact Functionality]:

  • Show all currently active VACUUM, ANALYZE, and REINDEX operations

  • Display operation progress, elapsed time, and process details

  • Identify blocking or long-running maintenance operations

  • Provide process IDs for operation tracking

[Required Use Cases]:

  • When user requests "running VACUUM", "active maintenance", "current VACUUM status", etc.

  • When troubleshooting slow or stuck VACUUM operations

  • When monitoring maintenance operation progress

  • When identifying maintenance operations that may be affecting performance

[Strictly Prohibited Use Cases]:

  • Requests for terminating or controlling VACUUM processes

  • Requests for starting new VACUUM operations

  • Requests for changing VACUUM parameters or configuration

get_vacuum_effectiveness_analysisA

[Tool Purpose]: Analyze VACUUM effectiveness and maintenance patterns using existing statistics

[Exact Functionality]:

  • Compare manual VACUUM vs autovacuum effectiveness patterns

  • Analyze VACUUM frequency vs table activity (DML operations)

  • Identify tables with suboptimal VACUUM patterns

  • Calculate maintenance efficiency ratios without performance impact

  • Show VACUUM coverage analysis across all tables

[Required Use Cases]:

  • When user requests "VACUUM effectiveness", "maintenance efficiency", "VACUUM analysis", etc.

  • When planning manual VACUUM schedules or autovacuum tuning

  • When identifying tables with poor maintenance patterns

  • When analyzing overall database maintenance health

[Strictly Prohibited Use Cases]:

  • Requests for VACUUM execution or scheduling

  • Requests for autovacuum configuration changes

  • Requests for maintenance operation control

get_database_statsA

[Tool Purpose]: Get comprehensive database-wide statistics and performance metrics

[Exact Functionality]:

  • Show database-wide transaction statistics (commits, rollbacks)

  • Display block I/O statistics (disk reads vs buffer hits)

  • Provide tuple operation statistics (returned, fetched, inserted, updated, deleted)

  • Show temporary file usage and deadlock counts

  • Include checksum failure information and I/O timing data

[Required Use Cases]:

  • When user requests "database statistics", "database performance", "transaction stats", etc.

  • When analyzing overall database performance and activity

  • When investigating I/O performance or buffer cache efficiency

  • When checking for deadlocks or temporary file usage

[Strictly Prohibited Use Cases]:

  • Requests for statistics reset or modification

  • Requests for database configuration changes

  • Requests for performance tuning actions

Returns: Comprehensive database statistics including transactions, I/O, tuples, and performance metrics

get_bgwriter_statsA

[Tool Purpose]: Analyze background writer and checkpoint performance statistics with version compatibility

[Exact Functionality]:

  • Show checkpoint execution statistics (timed vs requested)

  • Display checkpoint timing information (write and sync times)

  • Provide buffer writing statistics by different processes

  • Analyze background writer performance and efficiency

  • Automatically adapts to PostgreSQL version (17+ uses separate checkpointer view)

[Required Use Cases]:

  • When user requests "checkpoint stats", "bgwriter performance", "buffer stats", etc.

  • When analyzing I/O performance and checkpoint impact

  • When investigating background writer efficiency

  • When troubleshooting checkpoint-related performance issues

[Strictly Prohibited Use Cases]:

  • Requests for checkpoint execution or configuration changes

  • Requests for background writer parameter modifications

  • Requests for statistics reset

Returns: Background writer and checkpoint performance statistics with version-appropriate data

get_io_statsA

[Tool Purpose]: Analyze comprehensive I/O statistics across all database operations with version compatibility

[Exact Functionality]:

  • PostgreSQL 16+: Shows detailed I/O statistics from pg_stat_io (reads, writes, hits, timing)

  • PostgreSQL 12-15: Falls back to pg_statio_* views with basic I/O information

  • Provides buffer cache efficiency analysis and I/O timing when available

  • Identifies I/O patterns and performance bottlenecks

[Required Use Cases]:

  • When user requests "I/O stats", "I/O performance", "buffer cache analysis", etc.

  • When analyzing storage performance and buffer efficiency

  • When identifying I/O bottlenecks across different backend types

  • When comparing I/O patterns between relation types

[Strictly Prohibited Use Cases]:

  • Requests for I/O configuration changes or buffer tuning

  • Requests for storage or filesystem modifications

  • Requests for I/O statistics reset

get_table_io_statsA

[Tool Purpose]: Analyze I/O performance statistics for tables (disk reads vs buffer cache hits)

[Exact Functionality]:

  • Show heap, index, and TOAST table I/O statistics

  • Calculate buffer hit ratios for performance analysis

  • Identify tables with poor buffer cache performance

  • Provide detailed I/O breakdown by table component

[Required Use Cases]:

  • When user requests "table I/O stats", "buffer performance", "disk vs cache", etc.

  • When analyzing table-level I/O performance

  • When identifying tables causing excessive disk I/O

  • When optimizing buffer cache efficiency

[Strictly Prohibited Use Cases]:

  • Requests for I/O optimization actions

  • Requests for buffer cache configuration changes

  • Requests for statistics reset

get_index_io_statsA

[Tool Purpose]: Analyze I/O performance statistics for indexes (disk reads vs buffer cache hits)

[Exact Functionality]:

  • Show index-level I/O statistics and buffer hit ratios

  • Identify indexes with poor buffer cache performance

  • Provide detailed I/O performance metrics per index

  • Help optimize index and buffer cache usage

[Required Use Cases]:

  • When user requests "index I/O stats", "index buffer performance", etc.

  • When analyzing index-level I/O performance

  • When identifying indexes causing excessive disk I/O

  • When optimizing index buffer cache efficiency

[Strictly Prohibited Use Cases]:

  • Requests for index optimization actions

  • Requests for buffer cache configuration changes

  • Requests for statistics reset

get_all_tables_statsA

[Tool Purpose]: Get comprehensive statistics for all tables (including system tables if requested)

[Exact Functionality]:

  • Show detailed access statistics for all tables in database

  • Include sequential scans, index scans, and tuple operations

  • Provide live/dead tuple estimates and maintenance history

  • Option to include system catalog tables

[Required Use Cases]:

  • When user requests "all tables stats", "complete table statistics", etc.

  • When analyzing overall table usage patterns

  • When investigating table maintenance needs across the database

  • When getting comprehensive database activity overview

[Strictly Prohibited Use Cases]:

  • Requests for table maintenance operations (VACUUM, ANALYZE)

  • Requests for statistics reset or modification

  • Requests for table optimization actions

get_user_functions_statsA

[Tool Purpose]: Analyze performance statistics for user-defined functions

[Exact Functionality]:

  • Show execution count and timing statistics for user functions

  • Calculate average execution time per function call

  • Identify performance bottlenecks in user-defined functions

  • Provide total and self execution time breakdown

[Required Use Cases]:

  • When user requests "function stats", "function performance", etc.

  • When analyzing user-defined function performance

  • When identifying slow or frequently called functions

  • When optimizing application function usage

[Strictly Prohibited Use Cases]:

  • Requests for function modification or optimization

  • Requests for statistics reset

  • Requests for function execution or testing

get_database_conflicts_statsA

[Tool Purpose]: Analyze query conflicts in standby/replica database environments

[Exact Functionality]:

  • Show conflict statistics for standby servers (only relevant on replicas)

  • Display conflicts by type (tablespace, lock, snapshot, bufferpin, deadlock)

  • Help diagnose replication-related performance issues

  • Provide conflict resolution statistics

[Required Use Cases]:

  • When user requests "replication conflicts", "standby conflicts", etc.

  • When analyzing replica server performance issues

  • When troubleshooting replication lag or conflicts

  • When monitoring standby server health

[Strictly Prohibited Use Cases]:

  • Requests for conflict resolution actions

  • Requests for replication configuration changes

  • Requests for statistics reset

get_wait_eventsA

[Tool Purpose]: List available wait event types and their descriptions (PostgreSQL 17+)

[Exact Functionality]:

  • Show all wait event types with human-readable descriptions from pg_wait_events catalog

  • Correlate with current active sessions waiting on events

  • Filter by specific wait event type

  • Falls back to basic pg_stat_activity wait info on PG < 17

[Required Use Cases]:

  • When user requests "wait events", "wait event descriptions", "what are sessions waiting on"

  • When diagnosing session waits and understanding wait event meanings

  • When analyzing wait patterns across the database

[Strictly Prohibited Use Cases]:

  • Requests for session termination or wait resolution

  • Requests for configuration changes

get_wal_summarizer_statusA

[Tool Purpose]: Monitor WAL summarizer status for incremental backup support (PostgreSQL 17+)

[Exact Functionality]:

  • Show WAL summarizer process state and progress

  • Display available WAL summaries for incremental backups

  • Report summarize_wal configuration status

  • Falls back to version notice on PG < 17

[Required Use Cases]:

  • When user requests "WAL summarizer", "incremental backup status", "WAL summary"

  • When checking incremental backup readiness

  • When monitoring WAL summarization progress

[Strictly Prohibited Use Cases]:

  • Requests for WAL summarizer configuration changes

  • Requests for backup execution

get_async_io_statusA

[Tool Purpose]: Monitor asynchronous I/O subsystem status (PostgreSQL 18+)

[Exact Functionality]:

  • Show active async I/O operations from pg_aios view

  • Display I/O method configuration and concurrency settings

  • Report async I/O file handle usage

  • Falls back to I/O configuration info on PG < 18

[Required Use Cases]:

  • When user requests "async I/O status", "AIO monitoring", "I/O subsystem"

  • When investigating I/O performance and concurrency

  • When checking async I/O configuration

[Strictly Prohibited Use Cases]:

  • Requests for I/O configuration changes

  • Requests for storage modifications

get_per_backend_io_statsA

[Tool Purpose]: Analyze per-backend I/O and WAL statistics (PostgreSQL 18+)

Note: Uses pg_stat_get_backend_io() and pg_stat_get_backend_wal() which are new in PG 18.

[Exact Functionality]:

  • Show I/O statistics broken down by individual backend process

  • Display per-backend WAL generation statistics

  • Identify backends with highest I/O activity

  • Falls back to version notice on PG < 18

[Required Use Cases]:

  • When user requests "per-backend I/O", "backend I/O stats", "which backend is doing most I/O"

  • When diagnosing I/O hotspots at the process level

  • When analyzing per-connection I/O patterns

[Strictly Prohibited Use Cases]:

  • Requests for backend termination

  • Requests for I/O configuration changes

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 37 tools

Disambiguation3/5

Most tools target distinct PostgreSQL monitoring areas, but there are several overlapping clusters: table/database stats vs. table size/list/all_tables_stats, the I/O family, and the vacuum/autovacuum/bloat family. The detailed descriptions help clarify scope, but an agent may still need to compare descriptions carefully to pick the right diagnostic.

Naming Consistency5/5

All tool names follow a consistent snake_case get_* pattern, such as get_replication_status, get_table_list, and get_wait_events. There are no mixed casing styles or conflicting verb conventions.

Tool Count2/5

With 37 tools, the set is very large for a monitoring-oriented server. While many correspond to real PostgreSQL views, several could be consolidated or grouped, and the volume increases selection burden and the chance of choosing an overlapping diagnostic.

Completeness4/5

The surface covers a wide monitoring domain: replication, WAL, locks, connections, schemas, sizes, query statistics, vacuum/bloat, I/O, configuration, and wait events. Minor gaps remain, such as broader session/progress monitoring and index bloat analysis, but the read-only monitoring scope is largely complete.

Maintenance

ActivityActive
ResponsivenessNo recent community issues