MySQL MCP

Get overall InnoDB Cluster status (requires mysql_innodb_cluster_metadata schema).

Analyze cluster state and provide switchover recommendations. Note: This tool does NOT execute a switchover.

Get a visual representation of the cluster topology.

Convert column values to a different character set or collation.

Concatenate multiple columns with an optional separator.

Update a row only if its _version matches expectedVersion. Prevents lost updates in multi-agent environments.

Analyze all constraints for issues: missing NOT NULL, missing primary keys.

Generate mysqldump command for backing up database.

Create an index on a table. Supports BTREE, HASH, FULLTEXT, and SPATIAL index types.

Create a new database/schema with specified charset and collation.

Create a new table with specified columns, engine, and charset.

Create a new trigger.

Create or replace a view with specified algorithm and check option.

Comprehensive database health assessment workflow

Get the full foreign key dependency graph with cascade paths, row counts, circular dependency detection, and severity assessment. Agent-optimized structured output.

Get detailed information about a table's structure including columns, types, and constraints.

Scores tables by bloat/fragmentation risk using information_schema DATA_FREE vs DATA_LENGTH metrics. Returns per-table risk scores (0-100) with recommendations.

Detects unusual connection patterns by analyzing concentration by user, host, and state. Flags when a single user monopolizes the pool or idle connections accumulate.

Detects queries deviating from their historical execution time norms using MAX/AVG variance analysis. Requires performance_schema.

Disable optimistic concurrency control (OCC) on a table. Drops the _version column and its trigger.

Add documents to a collection.

Get collection statistics.

Create a new JSON document collection.

Create an index on document fields.

Drop a document collection.

Query documents in a collection.

List JSON document collections in a schema.

Update documents in a collection.

Remove documents from a collection.

Drop a partition from a partitioned table. Warning: This deletes all data in the partition!

Drop a database/schema. WARNING: This permanently deletes all data.

Drop (delete) a table from the database.

Drop a trigger.

Drop a view.

Enable optimistic concurrency control (OCC) on a table. Adds a _version column and an auto-increment trigger.

Modify an existing scheduled event schedule, body, or status.

Create a scheduled event (one-time or recurring) to execute SQL at specified times.

Remove a scheduled event.

List all scheduled events with status, schedule, and execution info.

Get detailed status and execution history for a specific event.

Execute TypeScript/JavaScript code in a sandboxed environment with access to all MySQL tools via the mysql.* API. Available API groups: - mysql.core: readQuery, writeQuery, listTables, describeTable, createTable, createIndex (8 methods) - mysql.transactions: begin, commit, rollback, savepoint, execute (7 methods) - mysql.json: extract, set, insert, remove, contains, keys, merge, diff, stats (17 methods) - mysql.text: regexpMatch, likeSearch, soundex, substring, concat, collationConvert (6 methods) - mysql.fulltext: fulltextSearch, fulltextCreate, fulltextBoolean, fulltextExpand (5 methods) - …

Get query execution plan using EXPLAIN.

Get query execution plan with actual timing using EXPLAIN ANALYZE (MySQL 8.0+). Only TREE format is supported.

Export table data as SQL INSERT statements or CSV format.

Flush tables to ensure data is written to disk.

Generate a query with FORCE INDEX hint.

Perform FULLTEXT search in BOOLEAN MODE with operators (+, -, *, etc.).

Create a FULLTEXT index on specified columns for fast text search.

Drop a FULLTEXT index from a table.

Perform FULLTEXT search WITH QUERY EXPANSION for finding related terms.

Perform FULLTEXT search with relevance ranking.

Get all indexes for a table including type, columns, and cardinality.

Get Group Replication flow control statistics and throttling info.

List all Group Replication members with detailed state information.

Identify the current primary member in a single-primary GR cluster.

Get comprehensive Group Replication status including mode and member state.

Get Group Replication transaction statistics and pending transactions.

Get Global Transaction ID (GTID) status for replication.

Import data into a table from an array of row objects.

Analyze table and suggest potentially missing indexes based on query patterns. Run an index audit for redundant/duplicate indexes, missing foreign key indexes, and unindexed large tables.

Analyze and optimize database indexes

Get index usage statistics from performance_schema.

Get detailed InnoDB engine status. Defaults to parsed summary output. Use raw=true for full text.

Append a value to a JSON array at the specified path.

Find rows where JSON column contains a specified value.

Compare two JSON documents and identify differences.

Extract values from JSON columns using JSON path expressions.

Simple JSON value extraction by row ID.

Suggest functional indexes for frequently accessed JSON paths.

Insert values into JSON columns only if the path does not exist.

Get the keys of a JSON object at the specified path.

Merge two JSON documents using JSON_MERGE_PATCH or JSON_MERGE_PRESERVE.

Normalize JSON column structure by extracting all unique keys across documents.

Remove values from JSON columns at specified paths.

Replace values in JSON columns only if the path exists.

Search for a string value in JSON columns and return matching paths.

Set or update values in JSON columns at specified paths.

Analyze statistics for a JSON column including depth, size, and key frequency.

Simple JSON value update by row ID.

Validate if a string is valid JSON.

Kill a running query or connection.

Find rows using LIKE pattern matching with % and _ wildcards.

List all constraints (primary key, foreign key, unique, check) for a table.

List all user-defined functions with return types and metadata.

List all databases/schemas with metadata including charset and collation.

List all stored procedures with parameters and metadata.

List all tables and views in the database with metadata.

List all triggers with event timing, action, and definition.

List all views with their definitions, security type, and check option.

Get binary log position from master/source server.

Guide for modifying the codebase (schemas, proxies) to prevent and heal LLM hallucinations.

Generate migration scripts for schema changes

Execute migration SQL and record it atomically. Note: MySQL DDL statements cannot be rolled back, they commit the current transaction. Auto-provisions the tracking table on first use. Use mysql_migration_record instead if you only need to log an already-applied migration.

Query migration history with optional filtering by status and source system. Returns paginated results ordered by applied_at descending.

Initialize or verify the schema version tracking table (_mcp_schema_versions). Idempotent — safe to call repeatedly. Returns current tracking state.

Record a migration in the schema version tracking table with status 'recorded' (metadata only, SQL not executed). Use mysql_migration_apply instead to execute SQL and record with status 'applied'. Auto-provisions the tracking table on first use. Computes SHA-256 hash for idempotency detection.

Analyze proposed DDL statements for risks: data loss, lock contention, constraint violations, and breaking changes. Pre-flight check before executing migrations.

Roll back a specific migration by ID or version. Executes the stored rollback_sql and updates status to 'rolled_back'. Use dryRun: true to preview the rollback SQL without executing.

Get current migration tracking status: latest version, counts by status, and list of source systems. Returns initialized: false if tracking table does not exist.

Optimize tables to reclaim unused space and defragment data.

Get detailed optimizer trace for a query.

Get partition information for a table.

Analyze and optimize slow queries

Get connection pool statistics.

Help build SQL queries for common operations

Analyze a query and suggest optimizations.

Get top query statistics from performance_schema. NOTE: This returns overall server query stats. Do NOT pass a specific query or sql string.

Quickly run a SQL query - shortcut for mysql_read_query or mysql_write_query

Quickly explore database schema - lists tables or describes a specific table

Execute a read-only SQL query (SELECT). Uses prepared statements for safety.

Find rows where column matches a regular expression pattern.

Reorganize partitions by splitting or merging them.

Repair corrupted tables (MyISAM only).

Calculate replication lag in seconds.

Show replication slave/replica status. Use summary=true for key metrics only.

Generate command for restoring from mysqldump backup.

Assign a role to a user.

Create a new role.

Drop a role.

Grant privileges to a role.

List privileges granted to a role.

List all roles defined in MySQL.

Revoke a role from a user, or privileges from a role.

Get InnoDB Cluster metadata cache status including refresh statistics and last refresh host.

Get MySQL Router connection pool status including idle and stashed server connections.

List IP addresses that have been blocked for a route due to too many failed connection attempts.

List active connections on a route including source/destination addresses, bytes transferred, and connection times.

List backend MySQL server destinations for a route. Shows address and port of each destination server.

Check if a route is alive and functioning. Returns isAlive boolean indicating route health.

Get operational status of a specific route including active connections, total connections, and blocked hosts count.

List all configured routes in MySQL Router. Returns route names that can be used with other router tools.

Get MySQL Router process status including version, hostname, and uptime. Requires Router REST API access.

Get the global Event Scheduler status and event statistics.

Help design table schemas

Get a complete schema snapshot in a single agent-optimized JSON structure. Includes tables, columns, constraints, indexes, views, routines, and triggers.

Query the MySQL audit log (requires Enterprise Audit or compatible plugin).

Get Transparent Data Encryption (TDE) and keyring status.

List MySQL Enterprise Firewall allowlist rules.

Get MySQL Enterprise Firewall plugin status.

Apply data masking to sensitive values (implementation for Community Edition).

Validate password strength using MySQL validate_password component. Note: Requires validate_password component to be installed.

Identify tables and columns that may contain sensitive data.

Get SSL/TLS connection and certificate status.

Get comprehensive privilege report for users.

Get or update runtime configuration values for the server. Currently supports updating the log level.

Get comprehensive server health information.

Complete MySQL InnoDB Cluster and Group Replication setup guide

Complete MySQL Document Store and X DevAPI setup guide

Complete MySQL Event Scheduler setup and configuration guide

Complete ProxySQL setup and configuration guide

MySQL replication setup and configuration guide

Complete MySQL Router setup and configuration guide

MySQL Shell setup and usage guide

Complete MySQL Spatial/GIS setup and usage guide

Show all running processes and queries.

Show server status variables.

Show server configuration variables.

Get detailed replication slave/replica status.

Get slow queries from performance_schema (if available).

Find rows with phonetically similar values using SOUNDEX.

Create a buffer (expanded area) around a geometry.

Find rows where the geometry is contained within a specified polygon.

Add a geometry/spatial column to an existing table.

Create a SPATIAL index on a geometry column for faster queries.

Find rows within a certain distance from a point (Cartesian distance).

Calculate distance on a sphere (for geographic coordinates). Returns distance in meters.

Convert geometry between WKT and GeoJSON formats.

Calculate the intersection of two geometries.

Create a POINT geometry from longitude/latitude coordinates.

Create a POLYGON geometry from coordinates.

Transform a geometry from one spatial reference system to another.

Find rows where the geometry is within a specified geometry.

Calculate Pearson correlation coefficient between two numeric columns.

Calculate descriptive statistics (mean, median, stddev, min, max, count) for a numeric column.

Get distinct values from a column with count. Useful for understanding cardinality and unique value distribution.

Analyze the distribution of values in a column with histogram buckets.

Get value frequency distribution (count per unique value) ordered by frequency descending. Shows the most common values first.

View or update column histogram statistics (MySQL 8.0+).

Perform one-sample t-test or z-test against a hypothesized mean. For z-test, provide populationStdDev (sigma) for accurate results. Use groupBy to test each group separately.

Access data from previous (LAG) or next (LEAD) rows in an ordered set. Useful for comparisons, deltas, and change detection. Note: table, column, and orderBy are required.

Calculate moving average (AVG OVER sliding window) for a numeric column. Specify windowSize for the number of preceding rows to include.

Divide ordered rows into N equal buckets (e.g., quartiles with buckets=4). Returns bucket assignment per row.

Detect statistical outliers in a numeric column using IQR (interquartile range) or Z-score method. IQR is robust against non-normal distributions.

Calculate percentile values for a numeric column.

Assign rank within an ordered result set. Supports rank (gaps), dense_rank (no gaps), and percent_rank (0-1). Use partitionBy to rank within groups. Note: table and orderBy are required.

Perform simple linear regression analysis (y = mx + b) between two columns.

Assign sequential row numbers within an ordered result set. Use partitionBy to restart numbering per group.

Calculate cumulative running total (SUM OVER) for a numeric column. Use partitionBy to reset total per group. Note: table, column, and orderBy are required.

Get a random sample of rows from a table.

Get summary statistics (count, avg, min, max, stddev) for multiple numeric columns. Defaults to all numeric columns if none specified.

Aggregate and analyze time series data with specified intervals.

Get the top N rows ranked by a column. Auto-excludes long-content columns (text, json, blob) from output unless selectColumns is specified.

Extract substrings from column values.

Get connection and activity summary by host from sys schema.

Get current InnoDB lock contention information from sys schema.

Get I/O usage summary by file, table, or global from sys schema.

Get memory usage summary by allocation type from sys schema.

Complete MySQL sys schema usage guide for diagnostics and troubleshooting

Get aggregated statistics for a schema including tables, indexes, and auto-increment status.

Get statement execution statistics including latency and row counts from sys schema.

Get user activity summary including statements, connections, and latency from sys schema.

Get wait event summary for performance analysis from sys schema.

Get detailed table statistics including size, rows, and engine info.

Get thread activity statistics.

Show all available MySQL tools organized by category

Get tables in safe DDL execution order. 'create' direction: dependencies first (for CREATE TABLE). 'drop' direction: dependents first (for DROP TABLE).

Begin a new transaction with optional isolation level. Returns a transaction ID for subsequent operations.

Commit a transaction, making all changes permanent.

Execute multiple SQL statements atomically. All statements succeed or all are rolled back.

Release a savepoint, removing it without rolling back.

Rollback a transaction, undoing all changes.

Rollback to a savepoint, undoing changes after that point.

Create a savepoint within a transaction for partial rollback.

List roles assigned to a user.

Store multiple vector embeddings in a single batch operation.

Create an HNSW vector index for faster KNN searches (requires MySQL 9.1+).

Delete a vector embedding by its row identifier.

Retrieve a vector embedding by its row identifier.

Combine vector similarity and fulltext search using Reciprocal Rank Fusion (RRF).

List all vector columns for a table and their dimensions.

Run ANALYZE TABLE to update vector index statistics.

Find all vectors within a maximum distance threshold.

Find the K nearest neighbors to a query vector.

Get statistics about a vector column, including dimension validation and sampling.

Store a single vector embedding in a table with a VECTOR column.

Execute a write SQL query (INSERT, UPDATE, DELETE). Uses prepared statements for safety.

Check MySQL server upgrade compatibility using util.checkForServerUpgrade(). Identifies potential issues before upgrading to a newer MySQL version.

Dump entire MySQL instance using util.dumpInstance(). Creates a compressed, parallel dump of all schemas (excluding system schemas). Ideal for full backups and migrations.

Dump selected schemas using util.dumpSchemas(). Creates a compressed, parallel dump of specified schemas. Use for partial backups.

Dump specific tables using util.dumpTables(). Creates a compressed, parallel dump of specified tables from a schema.

Export a MySQL table to a file using util.exportTable(). Supports CSV and TSV formats with WHERE clause filtering.

Import JSON documents from a file using util.importJson(). Supports NDJSON (one JSON object per line) and multi-line JSON objects (not JSON arrays). REQUIRES X Protocol (port 33060).

Parallel table import using util.importTable(). For CSV files, explicitly set fieldsTerminatedBy to ',' as the delimiter is not auto-detected. Target table must already exist.

Load a MySQL Shell dump using util.loadDump(). Restores data from a dump created by dumpInstance, dumpSchemas, or dumpTables. Supports parallel loading.

Execute a JavaScript, Python, or SQL script via MySQL Shell. Provides access to X DevAPI, AdminAPI, and all MySQL Shell features. NOTE: The script executes inside the MySQL Shell process, so file access inside the script is not restricted by allowedIoRoots. Use carefully.

Get MySQL Shell version and installation status. Useful for verifying MySQL Shell is available before running other shell tools.

Execute ProxySQL admin commands like LOAD/SAVE for users, servers, query rules, and variables. Also supports FLUSH commands.

Get connection pool statistics per backend server. Shows connections used/free, errors, queries, bytes transferred, and latency.

Get ProxySQL global variables. Filter by prefix: mysql (MySQL proxy settings), admin (admin interface settings), or all. Use like parameter for pattern matching.

Get ProxySQL memory usage metrics from stats_memory_metrics. Shows memory for SQLite, auth, query digests, and more.

Get active client sessions similar to MySQL SHOW PROCESSLIST. Shows session ID, user, database, client/server hosts, and current command.

Get query digest statistics showing top queries by execution count. Useful for identifying queries for routing, rewriting, or caching.

List query routing rules from mysql_query_rules table. Shows rule IDs, match patterns, destination hostgroups, and cache settings.

Get ProxySQL runtime configuration status including version info and admin variables. Use summary: true for condensed key variables only.

List configured backend MySQL servers from mysql_servers table. Shows hostgroup, hostname, port, status, and weights.

Get ProxySQL version, uptime, and runtime statistics. Returns global status variables from stats_mysql_global. Use summary: true for condensed key metrics.

List configured MySQL users from mysql_users table. Shows username, active status, default hostgroup, and connection limits. Passwords are redacted.