Read database schema information
AI agents call readSchema to retrieve information from Bun Database MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs schema inspection only—fetching metadata about database structure (tables, columns, types, constraints). It has no side effects, does not execute arbitrary queries, and does not modify data. It is a pure read operation with minimal blast radius if misused by an AI agent, as it only exposes structural information about the database.
From the tool's definition Tool name 'readSchema' and description 'Read database schema information' indicate a retrieval operation with no data modification or execution of arbitrary code.
Attacks that exploit this kind of access
Read database schema information. It is categorised as a Read tool in the Bun Database MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bun Database MCP Server MCP server in PolicyLayer and add a rule for readSchema: 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 Bun Database MCP Server. Nothing to install.
readSchema 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 readSchema 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 readSchema. 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.
readSchema is provided by the Bun Database MCP Server MCP server (ross-jill-ws/bun-db-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 →