Get all foreign keys for a table
AI agents call get_foreign_keys to retrieve information from Mcp Database without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves foreign key constraints from a database table's schema. It is a read-only operation that returns metadata about table relationships. There are no side effects, no data modification, no code execution, and no destructive operations. It falls squarely within the Read category (search, list, get, fetch).
From the tool's definition Tool name 'get_foreign_keys' and description 'Get all foreign keys for a table' indicate a retrieval operation that queries database schema metadata without modifying or executing code.
Attacks that exploit this kind of access
Get all foreign keys for a table. It is categorised as a Read tool in the Mcp Database MCP Server, which means it retrieves data without modifying state.
Register the Mcp Database MCP server in PolicyLayer and add a rule for get_foreign_keys: 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 Mcp Database. Nothing to install.
get_foreign_keys 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 get_foreign_keys 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 get_foreign_keys. 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.
get_foreign_keys is provided by the Mcp Database MCP server (nam088/mcp-database-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 →