Supabase
MCP server for interacting with the Supabase platform
作者提供的说明(英文原文)
SQL Server monitoring and diagnostics for AI agents using Extended Events. No ODBC drivers required.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"sql-sentinel": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/tkmawarire/sql-sentinel-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add sql-sentinel -- docker run -i --rm ghcr.io/tkmawarire/sql-sentinel-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"sql-sentinel": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/tkmawarire/sql-sentinel-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"sql-sentinel": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/tkmawarire/sql-sentinel-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 tkmawarire 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(2.3.1)于8个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 .NET, Docker。
同一分类中有:Supabase, MongoDB MCP Server, Elasticsearch MCP Server
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP server for interacting with the Supabase platform
MongoDB Model Context Protocol Server
MCP server for interacting with Elasticsearch
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A production-ready MCP (Model Context Protocol) server for SQL Server monitoring, diagnostics, and database operations. Built with .NET 9 and Microsoft.Data.SqlClient for native SQL Server connectivity — no ODBC drivers required.
sys.dm_os_wait_stats directly, categorized by type (CPU, I/O, Lock, Memory, etc.)sp_reset_connection, SET statements, trace queries) GRANT ALTER ANY EVENT SESSION TO [your_login];
GRANT VIEW SERVER STATE TO [your_login];
- For blocked process detection:
EXEC sp_configure 'show advanced options', 1;
RECONFIGURE; EXEC sp_configure 'blocked process threshold', 5; RECONFIGURE;
No .NET SDK required. Works on any system with Docker installed.
docker pull ghcr.io/tkmawarire/sql-sentinel-mcp:latest
claude_desktop_config.json){
"mcpServers": { "sql-sentinel": { "command": "docker", "args": ["run", "-i", "--rm", "--network", "host", "-e", "SQL_SENTINEL_CONNECTION_STRING=Server=localhost;Database=master;User Id=sa;Password=YourPassword;TrustServerCertificate=true", "ghcr.io/tkmawarire/sql-sentinel-mcp:latest"] } } }
claude mcp add sql-sentinel \
-e SQL_SENTINEL_CONNECTION_STRING="Server=localhost;Database=master;User Id=sa;Password=YourPassword;TrustServerCertificate=true" \ -- docker run -i --rm --network host \ -e SQL_SENTINEL_CONNECTION_STRING \ ghcr.io/tkmawarire/sql-sentinel-mcp:latest
Network access: The
-iflag is required for stdio transport. Use--network hostso the container can reach SQL Server on your host machine. For remote SQL Server, omit--network hostand use the accessible hostname in your connection string.
Connection string: Set
SQL_SENTINEL_CONNECTION_STRINGvia-e. All tools read the connection string from this environment variable.
Requires .NET 9 SDK or later.
dotnet tool install -g SQLSentinel.Mcp
{
"mcpServers": { "sql-sentinel": { "command": "sql-sentinel-mcp", "env": { "SQL_SENTINEL_CONNECTION_STRING": "Server=localhost;Database=master;User Id=sa;Password=YourPassword;TrustServerCertificate=true" } } } }
git clone https://github.com/tkmawarire/sql-sentinel.git
cd sql-sentinel dotnet build
Run directly:
dotnet run --project SqlServer.Profiler.Mcp/
Or publish a self-contained single binary:
# Windows
dotnet publish SqlServer.Profiler.Mcp/ -c Release -r win-x64 --self-contained
dotnet publish SqlServer.Profiler.Mcp/ -c Release -r linux-x64 --self-contained
dotnet publish SqlServer.Profiler.Mcp/ -c Release -r osx-arm64 --self-contained
dotnet publish SqlServer.Profiler.Mcp/ -c Release -r osx-x64 --self-contained
Output will be in bin/Release/net9.0/{runtime}/publish/
All tools read the connection string from the SQL_SENTINEL_CONNECTION_STRING environment variable. Set it once before starting the server:
export SQL_SENTINEL_CONNECTION_STRING="Server=localhost;Database=master;User Id=sa;Password=YourPassword;TrustServerCertificate=false;Encrypt=true"
SQL Authentication:
Server=localhost;Database=master;User Id=sa;Password=YourPassword;TrustServerCertificate=false;Encrypt=true
Windows Authentication:
Server=localhost;Database=master;Integrated Security=true;TrustServerCertificate=false;Encrypt=true
Note: Only use
TrustServerCertificate=truein development environments with self-signed certificates.
For production, always use
TrustServerCertificate=falsewith a valid SSL certificate.
Azure SQL:
Server=yourserver.database.windows.net;Database=yourdb;User Id=user;Password=password;Encrypt=true
| Tool | Description |
|---|---|
sqlsentinel_create_session | Create an Extended Events session with filters (not started) |
sqlsentinel_start_session | Start capturing events for an existing session |
sqlsentinel_stop_session | Stop capturing; events are retained |
sqlsentinel_drop_session | Drop session and discard all events |
sqlsentinel_list_sessions | List all MCP-created sessions with state and buffer usage |
sqlsentinel_quick_capture | Create and start a session in one step |
| Tool | Description |
|---|---|
sqlsentinel_get_events | Retrieve captured events with filtering, sorting, and deduplication |
sqlsentinel_get_stats | Aggregate statistics grouped by fingerprint, database, app, or login |
sqlsentinel_analyze_sequence | Analyze query execution sequence with timing and gaps |
sqlsentinel_get_connection_info | List databases, applications, logins, sessions, and blocking info |
sqlsentinel_stream_events | Real-time event capture for a specified duration (1–300s) |
| Tool | Description |
|---|---|
sqlsentinel_get_deadlocks | Retrieve deadlock events with victim, processes, locks, and SQL text |
sqlsentinel_get_blocking | Retrieve blocked process events with wait resources and SQL text |
sqlsentinel_get_wait_stats | Query sys.dm_os_wait_stats categorized by type (no session required) |
sqlsentinel_health_check | Comprehensive report: slow queries, deadlocks, blocking, wait stats, insights |
| Tool | Description |
|---|---|
sqlsentinel_check_permissions | Check current login permissions and blocked process threshold config |
sqlsentinel_grant_permissions | Grant required permissions to a login (requires sysadmin) |
| Tool | Description |
|---|---|
sqlsentinel_list_tables | List all user tables in the database (schema-qualified) |
sqlsentinel_describe_table | Detailed table schema: columns, indexes, constraints, foreign keys |
sqlsentinel_create_table | Create a new table via CREATE TABLE statement |
sqlsentinel_insert_data | Insert data via INSERT statement |
sqlsentinel_read_data | Execute SELECT queries and return results |
sqlsentinel_update_data | Update data via UPDATE statement |
sqlsentinel_drop_table | Drop a table via DROP TABLE statement |
Agent: sqlsentinel_quick_capture(
sessionName: "debug_api", applications: "MyWebApp", minDurationMs: 100 )
// User triggers the slow operation
Agent: sqlsentinel_get_events( sessionName: "debug_api", sortBy: "DurationDesc", limit: 20 )
Agent: sqlsentinel_drop_session(sessionName: "debug_api")
Agent: sqlsentinel_quick_capture(
sessionName: "n_plus_one_check", databases: "OrdersDB" )
// User loads a page
Agent: sqlsentinel_get_stats( sessionName: "n_plus_one_check", groupBy: "QueryFingerprint" )
// Look for queries with high execution counts
Agent: sqlsentinel_analyze_sequence(
sessionName: "my_session", correlationId: "order-12345", responseFormat: "Markdown" )
Agent: sqlsentinel_quick_capture(
sessionName: "deadlock_monitor", eventTypes: "Deadlock" )
// Wait for deadlocks to occur
Agent: sqlsentinel_get_deadlocks( sessionName: "deadlock_monitor", responseFormat: "Markdown" )
Agent: sqlsentinel_quick_capture(
sessionName: "blocking_check", eventTypes: "BlockedProcess" )
// Requires: sp_configure 'blocked process threshold', 5
Agent: sqlsentinel_get_blocking( sessionName: "blocking_check", responseFormat: "Markdown" )
Agent: sqlsentinel_health_check(
sessionName: "my_session", slowQueryThresholdMs: 1000, responseFormat: "Markdown" )
Agent: sqlsentinel_list_tables()
Agent: sqlsentinel_describe_table( name: "dbo.Products" )
Agent: sqlsentinel_read_data( sql: "SELECT TOP 10 * FROM dbo.Products ORDER BY CreatedDate DESC" )
Agent: sqlsentinel_get_wait_stats(
topN: 20, responseFormat: "Markdown" )
Queries are normalized to group similar ones:
-- These become one fingerprint:
SELECT * FROM Users WHERE id = 123 SELECT * FROM Users WHERE id = 456
-- Fingerprint: abc123:SELECT * FROM Users WHERE id = ? -- Execution count: 2
Default excluded patterns (when excludeNoise=true):
sp_reset_connection — Connection pool resetSET TRANSACTION ISOLATION LEVEL — Session setupSET NOCOUNT, SET ANSI_* — Client configurationsp_trace_*, fn_trace_* — Trace system queriesSqlBatchCompleted, RpcCompleted, SqlStatementCompleted, SpStatementCompleted, Attention, ErrorReported, Deadlock, BlockedProcess, LoginEvent, SchemaChange, Recompile, AutoStats
sql-profiler-mcp/
├── .github/ │ └── workflows/ │ ├── docker.yml # Build & push multi-arch Docker images │ └── publish-mcp-registry.yml # Publish NuGet + MCP registry ├── .mcp/ │ └── server.json # MCP manifest (NuGet + OCI packages) ├── SqlServer.Profiler.Mcp/ # Main MCP server (stdio transport) │ ├── SqlServer.Profiler.Mcp.csproj │ ├── Program.cs # Entry point, DI setup, MCP config │ ├── Models/ │ │ ├── ProfilerModels.cs # Records, enums, data models │ │ └── DbOperationResult.cs # Result model for CRUD operations │ ├── Services/ │ │ ├── ProfilerService.cs # Core Extended Events logic │ │ ├── QueryFingerprintService.cs # SQL normalization & fingerprinting │ │ ├── WaitStatsService.cs # DMV-based wait stats analysis │ │ ├── SessionConfigStore.cs # In-memory session config storage │ │ └── EventStreamingService.cs # Real-time event streaming │ ├── Utilities/ │ │ └── SqlInputValidator.cs # SQL input validation & escaping │ └── Tools/ │ ├── SessionManagementTools.cs # Session lifecycle tools (6) │ ├── EventRetrievalTools.cs
只显示了开头部分;其余内容请在仓库中阅读