Run a read-only SELECT/WITH SQL query against the configured ODBC database. Results are row-limited by default. Use all_rows=true to return all matching rows.
AI agents invoke run_readonly_query to trigger actions in OpenLink MCP Server for ODBC. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Although constrained to SELECT/WITH (read-only), the tool actively executes SQL against an ODBC-connected database, making it an Execute action. The read-only constraint reduces severity, but misuse could still expose sensitive data across any ODBC-accessible database. Severity is medium due to potential for broad data exfiltration across schemas.
From the tool's definition 'Run a read-only SELECT/WITH SQL query against the configured ODBC database' — executes SQL queries against an external database system
Attacks that exploit this kind of access
Run a read-only SELECT/WITH SQL query against the configured ODBC database. Results are row-limited by default. Use all_rows=true to return all matching rows. It is categorised as a Execute tool in the OpenLink MCP Server for ODBC MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenLink MCP Server for ODBC MCP server in PolicyLayer and add a rule for run_readonly_query: 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 OpenLink MCP Server for ODBC. Nothing to install.
run_readonly_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_readonly_query 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 run_readonly_query. 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.
run_readonly_query is provided by the OpenLink MCP Server for ODBC MCP server (pvsmark/pvs-odbc-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 →