Rollback a stored procedure to a previous version. Can specify version number or use latest backup.
AI agents use rollback_sp to create or update resources in MSSQL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MSSQL MCP Server environment.
Rolling back a stored procedure overwrites the current version with a previous one, which is a reversible write operation (the current version is replaced but prior versions presumably exist). However, the blast radius is high because overwriting a stored procedure in production could affect all callers and disrupt database operations.
From the tool's definition Rollback a stored procedure to a previous version. Can specify version number or use latest backup.
Attacks that exploit this kind of access
Rollback a stored procedure to a previous version. Can specify version number or use latest backup. It is categorised as a Write tool in the MSSQL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MSSQL MCP Server MCP server in PolicyLayer and add a rule for rollback_sp: 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.
rollback_sp is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rollback_sp 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 rollback_sp. 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.
rollback_sp 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 →