Retrieve and return a list of all schema names from the connected database.
AI agents call get_schemas to retrieve information from Mcp Odbc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries database metadata (schema names) without side effects. It does not execute arbitrary SQL, modify data, or perform destructive operations. The blast radius of misuse is minimal—an attacker gains knowledge of database structure but cannot alter, delete, or access actual data through this tool alone. This is a classic Read operation.
From the tool's definition Tool name is 'get_schemas' and description states 'Retrieve and return a list of all schema names from the connected database.' The verb 'Retrieve' and 'return' indicate read-only data retrieval with no modification, creation, or deletion of data.
Documented attack patterns abuse exactly the kind of access get_schemas gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Odbc, and nothing reaches the server without passing your rules. This is the rule we recommend for get_schemas:
{
"version": "1",
"default": "deny",
"tools": {
"get_schemas": {}
}
} get_schemas is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve and return a list of all schema names from the connected database. It is categorised as a Read tool in the Mcp Odbc MCP Server, which means it retrieves data without modifying state.
Register the Mcp Odbc MCP server in PolicyLayer and add a rule for get_schemas: 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 Odbc. Nothing to install.
get_schemas 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_schemas 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_schemas. 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_schemas is provided by the Mcp Odbc MCP server (openlinksoftware/mcp-odbc-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Odbc, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 Mcp Odbc tools catalogued and risk-classified — across an index of 43,000+ MCP servers.