Rebuild an index on a table (requires FULL mode)
AI agents invoke sqlserver_rebuild_index to trigger actions in Multi-Database 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.
Rebuilding an index is a significant database operation that rewrites index structures, which can be resource-intensive and affect table availability (locking). It is not a simple read or write, but rather an execution of a maintenance command that has operational side effects.
From the tool's definition 'Rebuild an index on a table' - this is a maintenance operation that reorganizes/rewrites index structures
Attacks that exploit this kind of access
Rebuild an index on a table (requires FULL mode). It is categorised as a Execute tool in the Multi-Database MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Multi-Database MCP Server MCP server in PolicyLayer and add a rule for sqlserver_rebuild_index: 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 Multi-Database MCP Server. Nothing to install.
sqlserver_rebuild_index 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 sqlserver_rebuild_index 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 sqlserver_rebuild_index. 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.
sqlserver_rebuild_index is provided by the Multi-Database MCP Server MCP server (nam088/mcp-server). 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 →