Search within object definitions (procedure/function/view source code)
AI agents call search_definitions to retrieve information from SQL Server MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing metadata (source code definitions) without creating, modifying, executing, or deleting any data. It is a passive search/inspection operation consistent with database introspection. The read-only nature of the server and the absence of any action verbs beyond 'search' confirm it belongs in the Read category.
From the tool's definition Tool description states 'Search within object definitions' and server is explicitly described as 'read-only MCP server for SQL Server database introspection'.
Attacks that exploit this kind of access
Search within object definitions (procedure/function/view source code). It is categorised as a Read tool in the SQL Server MCP MCP Server, which means it retrieves data without modifying state.
Register the SQL Server MCP server in PolicyLayer and add a rule for search_definitions: 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 SQL Server MCP. Nothing to install.
search_definitions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_definitions 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 search_definitions. 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.
search_definitions is provided by the SQL Server MCP server (millelog/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 →