Test a draft stored procedure with specified parameters. Execute the draft version safely before deploying.
AI agents invoke test_sp_draft to trigger actions in MSSQL MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a stored procedure draft against a real database. Although described as 'safe' and pre-deployment, it still runs code (a stored procedure) that could have side effects depending on the SP's contents. Execution of arbitrary stored procedures warrants a high severity classification.
From the tool's definition 'Test a draft stored procedure with specified parameters. Execute the draft version safely before deploying.'
Attacks that exploit this kind of access
Test a draft stored procedure with specified parameters. Execute the draft version safely before deploying. It is categorised as a Execute tool in the MSSQL MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MSSQL MCP Server MCP server in PolicyLayer and add a rule for test_sp_draft: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MSSQL MCP Server. Nothing to install.
test_sp_draft is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the test_sp_draft rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for test_sp_draft. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
test_sp_draft is provided by the MSSQL MCP Server MCP server (jpcanter/sql-server-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →