AI agents call get-table-details to retrieve information from Neosql without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation that retrieves schema metadata. It has no side effects, does not modify data, execute code, or perform destructive operations. The blast radius of misuse is minimal—an AI agent could at worst learn the database structure but cannot alter it.
From the tool's definition Tool name 'get-table-details' and description states it retrieves 'detailed information about...tables including columns, indexes, primary keys, and foreign keys' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Get detailed information about one or more tables including columns, indexes, primary keys, and foreign keys. It is categorised as a Read tool in the Neosql MCP Server, which means it retrieves data without modifying state.
Register the Neosql MCP server in PolicyLayer and add a rule for get-table-details: 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 Neosql. Nothing to install.
get-table-details 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-table-details 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-table-details. 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-table-details is provided by the Neosql MCP server (unvus/neosql-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 →