Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"mssql": {
"cwd": "C:/path/to/mcp-mssql-server",
"env": {
"MSSQL_CONNECTION_STRING": "sqlserver://user:password@host:1433?database=mydb&encrypt=disable"
},
"args": [
"run",
"."
],
"command": "go"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
A read-only MCP (Model Context Protocol) server that connects AI agents like Claude Code to Microsoft SQL Server databases — including SSIS ETL package analysis. Single Go binary, zero dependencies, defense-in-depth security.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y '@anthropic-ai/claude-code' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution
Claude Code used the git worktree `commondir` file when determining folder trust but did not validate its contents. By crafting a repository with a `commondir` file pointing to a path the victim had previously trusted, an attacker could bypass the trust dialog and immediately execute malicious hooks defined in `.claude/settings.json`. Exploiting this required the victim to clone a malicious repository and run Claude Code within it, and for the attacker to know or guess a path the victim had alre
Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace
Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the symlink and wrote to the target location outside the workspace without prompting the user for confirmation. This allowed a sandbox escape where neither the sandboxed command nor the unsandboxed app could independently write outside the workspace, but their combination
Claude Code: Insecure System-Wide Configuration Loading Enables Local Privilege Escalation on Windows
On Windows, Claude Code loaded system-wide default configuration from `C:\ProgramData\ClaudeCode\managed-settings.json` without validating directory ownership or access permissions. Because the `ProgramData` directory is writable by non-administrative users by default and the `ClaudeCode` subdirectory was not pre-created or access-restricted, a low-privileged local user could create this directory and place a malicious configuration file that would be automatically loaded for any user launching
Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File
Claude Code resolved the permission mode from settings files, including the repo-controlled `.claude/settings.json`, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set `permissions.defaultMode` to `bypassPermissions` in its committed `.claude/settings.json`, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easie
Claude Code has Sandbox Escape via Persistent Configuration Injection in settings.json
Claude Code's bubblewrap sandboxing mechanism failed to properly protect the .claude/settings.json configuration file when it did not exist at startup. While the parent directory was mounted as writable and .claude/settings.local.json was explicitly protected with read-only constraints, settings.json was not protected if it was missing. This allowed malicious code running inside the sandbox to create this file and inject persistent hooks (such as SessionStart commands) that would execute with ho
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in data
Query and manage PostgreSQL databases directly from AI assistants
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Manage Supabase projects — databases, auth, storage, and edge functions
Real-time financial market data: stocks, forex, crypto, commodities, and economic indicators
MCP Security Weekly
Get CVE alerts and security updates for Mcp Mssql Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A read-only MCP (Model Context Protocol) server that connects AI agents like Claude Code to Microsoft SQL Server databases — including SSIS ETL package analysis. Single Go binary, zero dependencies, defense-in-depth security.
Claude AI (cloud) <-- HTTPS --> Claude Code (local) <-- stdio --> mcp-mssql (local) <-- TCP 1433 --> SQL Server
|
+-- File I/O --> .dtsx packages (SSIS)
SQL Server is never exposed to the internet. All database traffic stays local. SSIS tools parse .dtsx files directly from a configured path.
SELECT and WITH (CTE) queries allowedINSERT, UPDATE, DELETE, DROP, ALTER, CREATE, TRUNCATE, EXEC, EXECUTE, XP_CMDSHELL, OPENROWSET, BULK INSERT, MERGE, and semicolons are blocked using word-boundary regex matchinglist_tables and describe_tablepassword, salary, credit_card) are automatically stripped from query resultsTOP N injected into queries missing a row limit (default: 100, configurable)[AUDIT] tag (status, row count, query text); every table access logged with [ACCESS] tag.mcp-mssql-config.json per projectdescribe_table uses @p1 parameters to prevent SQL injection.exe with your team, no Go installation required.dtsx files for control flow, data flow, table references, and column mappings| Tool | Description | Parameters |
|---|---|---|
query_database | Execute a SELECT query. Auto-limited, validated, column-masked. | sql (required) |
list_tables | List all queryable tables. Blocked tables excluded. | none |
describe_table | Get column names, data types, nullability. Parameterized. | table_name (required) |
exec_sp | Execute a read-only stored procedure. SP definition inspected first. | procedure (required), params |
benchmark_query | Compare query performance (time + row count, no data returned). | query1 (required), query2 |
Parse .dtsx files from the configured project_ssis_path.
| Tool | Description | Parameters |
|---|---|---|
ssis_list_packages | List all .dtsx packages in the configured path. | none |
ssis_control_flow | Extract task sequence, types, and embedded SQL from a package. | package_name (required) |
ssis_data_flow | Extract data flow components, table names, SQL queries, column mappings. | package_name (required) |
ssis_impact_check | Scan ALL packages for references to a table or column. Use before schema changes. | table_name (required), column_name |
ssis_table_refs | List all tables a single package reads from or writes to. | package_name (required) |
ssis_schema_validate | Cross-reference a package against the live DB schema. Reports missing tables/columns. | package_name (required) |
Query the SSISDB catalog for deployed packages and execution history.
| Tool | Description | Parameters |