find_column_references

Find all references to a column name across the database — which tables/views define it and which stored procedures, views, functions, and triggers use it in their SQL body. Useful for impact analysis and data lineage.

Server Sql Database sql-database-mcp-server
Category Read
Risk class Low
Parameters 43 required

What find_column_references does on Sql Database

AI agents call find_column_references to retrieve information from Sql Database without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
server string Yes Server hostname (e.g. server1.database.windows.net)
database string Yes Database name
table_name string Optional: restrict the search to references of this column from a specific table
column_name string Yes The column name to search for across all database objects

Parameters from the server's own tool schema.

Why find_column_references needs a policy

This tool retrieves and queries metadata about column usage patterns without creating, modifying, deleting, or executing any data-altering operations. It is a pure read operation that inspects schema relationships. The low severity reflects minimal blast radius — even if an agent misuses it, the worst outcome is discovering unwanted schema information, not data loss or system compromise.

From the tool's definition Tool description states it 'Find[s] all references to a column name across the database' and explicitly notes its purpose as 'impact analysis and data lineage.' The verbs are introspective queries ('which tables/views define it', 'which stored procedures use…

Questions about find_column_references

What does the find_column_references tool do? +

Find all references to a column name across the database — which tables/views define it and which stored procedures, views, functions, and triggers use it in their SQL body. Useful for impact analysis and data lineage. It is categorised as a Read tool in the Sql Database MCP Server, which means it retrieves data without modifying state.

What parameters does find_column_references accept? +

find_column_references accepts 4 parameters: server, database, table_name, column_name. Required: server, database, column_name. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on find_column_references? +

Register the Sql Database MCP server in PolicyLayer and add a rule for find_column_references: 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 Database. Nothing to install.

What risk level is find_column_references? +

find_column_references is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit find_column_references? +

Yes. Add a rate_limit block to the find_column_references 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.

How do I block find_column_references completely? +

Set action: deny in the PolicyLayer policy for find_column_references. 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.

What MCP server provides find_column_references? +

find_column_references is provided by the Sql Database MCP server (sql-database-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.