Execute a SQL query and return results in Markdown table format.
AI agents invoke podbc_execute_query_md to trigger actions in Mcp Sqlalchemy. 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.
This tool executes SQL queries with side effects determined by user input. While the output format (Markdown) is benign, the core function is query execution—a classic Execute category tool. Severity is high because a malicious agent could run INSERT, UPDATE, or DROP commands (though Destructive would require confirmation that DELETE/DROP are explicitly permitted).
From the tool's definition Tool name contains 'execute_query' and description states 'Execute a SQL query'. The tool runs arbitrary SQL commands against a database via SQLAlchemy/pyodbc, whose effects depend entirely on the query argument provided.
Documented attack patterns abuse exactly the kind of access podbc_execute_query_md gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Sqlalchemy, and nothing reaches the server without passing your rules. This is the rule we recommend for podbc_execute_query_md:
{
"version": "1",
"default": "deny",
"tools": {
"podbc_execute_query_md": {
"limits": [
{
"counter": "podbc_execute_query_md_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}podbc_execute_query_md stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a SQL query and return results in Markdown table format. It is categorised as a Execute tool in the Mcp Sqlalchemy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Sqlalchemy MCP server in PolicyLayer and add a rule for podbc_execute_query_md: 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 Sqlalchemy. Nothing to install.
podbc_execute_query_md 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 podbc_execute_query_md 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 podbc_execute_query_md. 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.
podbc_execute_query_md is provided by the Mcp Sqlalchemy MCP server (openlinksoftware/mcp-sqlalchemy-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Sqlalchemy, 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.
14 Mcp Sqlalchemy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.