SQL Sentinel MCP Server

Analyze the sequence and timing of queries for a specific operation. Perfect for understanding what queries run during a specific user action, API call, or business operation. Shows queries in execution order with cumulative timing and gaps between queries. Use correlationId to track queries containing a specific identifier (e.g., order ID, request ID), or sessionId to follow a specific database connection (SPID).

Check if the current SQL Server login has the required permissions for profiling. Required permissions for SQL Sentinel: - ALTER ANY EVENT SESSION: Create, modify, and drop Extended Events sessions - VIEW SERVER STATE: Read from ring buffer targets and DMVs Returns the current permission status and provides GRANT statements if permissions are missing.

Create a new SQL Server profiling session using Extended Events. This creates a server-side event session that captures SQL queries, stored procedure calls, and other database events with minimal overhead (~1-2%). The session is created but NOT started. Use sqlsentinel_start_session to begin capture.

Creates a new table in the SQL Server database. Expects a valid CREATE TABLE SQL statement.

Returns detailed schema information for a table including columns, indexes, constraints, and foreign keys.

Drop a profiling session and discard all captured events. WARNING: This permanently deletes all captured events. Retrieve any needed data with sqlsentinel_get_events before dropping.

Drops a table from the SQL Server database. Expects a valid DROP TABLE SQL statement.

Retrieve blocked process events captured by a profiling session. PREREQUISITE: 'blocked process threshold' must be configured on the server: EXEC sp_configure 'blocked process threshold', 5; -- triggers after 5 seconds RECONFIGURE; Sessions must include the BlockedProcess event type. Returns blocked and blocking SPID pairs with wait resources and SQL text.

Get information about databases, applications, logins, active sessions, or current blocking. Useful for understanding what's connected to the server and for identifying active blocking chains.

Retrieve deadlock events captured by a profiling session. Sessions must include the Deadlock event type (maps to sqlserver.xml_deadlock_report). Returns structured deadlock information: victim process, all involved SPIDs, wait resources, lock modes, and SQL text per process.

Retrieve captured events from a profiling session with filtering. Returns query events with timing, resource usage, and metadata. Supports filtering by time, database, application, duration, and text content. When deduplicate=true (default), identical queries are grouped with execution counts.

Get aggregate statistics from captured events. Provides summary metrics grouped by query fingerprint, database, application, or login. Useful for identifying slow queries, high-frequency queries, or resource-intensive operations.

Query sys.dm_os_wait_stats to show what SQL Server is waiting on. This does NOT require a profiling session - it queries the server directly. Shows cumulative wait statistics since the last SQL Server restart or manual reset. Useful for identifying systemic bottlenecks. Waits are categorized as: CPU, I/O, Lock, Memory, Network, Latch, Preemptive, Other. Common benign waits (SLEEP_*, BROKER_*, background tasks) are excluded.

Grant the required profiling permissions to a specified SQL Server login. IMPORTANT: The connection used must have elevated privileges (sysadmin role or CONTROL SERVER permission). Grants: - ALTER ANY EVENT SESSION: Create, modify, and drop Extended Events sessions - VIEW SERVER STATE: Read from ring buffer targets and DMVs

Single diagnostic command that produces a comprehensive server health report. Pulls together: - Top 5 slowest queries (requires an active profiling session) - Recent deadlocks (if session includes Deadlock event type) - Recent blocking events (if session includes BlockedProcess event type) - Top 10 wait statistics from sys.dm_os_wait_stats - Currently active blocking chains from sys.dm_exec_requests - AI-ready insights with severity and recommendations For sessionName: pass an active or stopped session to include query/event analysis. Pass empty string to skip query analysis and only return live DMV data.

Inserts data into a table. Expects a valid INSERT SQL statement.

List all profiling sessions created by this MCP server. Shows session name, state (RUNNING/STOPPED), and buffer usage.

Lists all user tables in the SQL Server database. Returns schema-qualified table names (e.g., 'dbo.Users').

Get full details of a specific past capture by its ID. Returns the complete capture summary including top queries by duration, insights, diagnostic findings, and context from that profiling session. Use capture IDs from sqlsentinel_memory_list.

List past profiling captures stored in memory. Returns summaries of previous profiling sessions that were automatically saved when you retrieved events, stats, or ran health checks. Use this to discover what data is available from past operations without re-running them. Memory persists across server restarts and conversation compaction. Filter by server name, session name, tag, or time range.

Delete memory data for a specific server, or clean up expired memories. Use 'expired' as serverName to only clean up expired captures. Use a specific server name to remove all captures and query history for that server.

Get the performance history of a specific query fingerprint across all captures. Shows how a query's performance has changed over time: execution counts, average/max duration, reads, and CPU usage across multiple profiling sessions. Use this to detect performance regressions or improvements. Get query fingerprints from get_events, get_stats, or memory_search_queries.

Search through remembered queries across all past captures. Find queries by SQL text content, database, minimum execution count, or minimum average duration. Returns query fingerprints with their cumulative statistics and performance history. Results are sorted by total duration (heaviest queries first).

Show memory system statistics: total captures, query count, disk usage, date range. Useful for understanding what historical data is available and managing storage.

Add tags or a note to a past capture for easier retrieval later. Tags help categorize captures (e.g., 'before_deploy', 'regression_test', 'production_issue'). Notes provide free-form context about what the capture was for. Tagged captures have extended retention (90 days vs 30 days default).

Create AND start a profiling session in one step. Convenience tool for rapid debugging. Creates a session with specified filters and immediately begins capture.

Executes a SELECT query against the SQL Server database and returns the results.

Start capturing events for an existing profiling session. The session must have been created first with sqlsentinel_create_session.

Stop capturing events for a profiling session. Events captured so far are retained. Use sqlsentinel_drop_session to completely remove the session.

Capture events in real-time for a specified duration. Starts a live stream on the profiling session and collects all events that occur during the capture window. Use this to observe which queries execute during a specific operation — start the stream, perform the operation, then review the captured events. The stream automatically stops after durationSeconds elapses. Events are returned sorted by timestamp with full query details.

Updates data in a table. Expects a valid UPDATE SQL statement.