call_procedure · Database MCP: Risk & Policy

WHAT IT DOES

What call_procedure does on DatabaseMCP

AI agents invoke call_procedure to trigger actions in DatabaseMCP. 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.

WHY IT NEEDS A POLICY

Why call_procedure needs a policy

Although the server claims to 'enforce security restrictions to prevent data modification,' the call_procedure tool itself executes arbitrary stored procedures whose actual behavior depends on their arguments and internal logic.

From the tool's definition Tool name 'call_procedure' and description 'Execute a stored procedure by providing necessary arguments' indicate runtime execution of arbitrary stored procedures.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_procedure Rate-limited

call_procedure 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "call_procedure": {
      "limits": [
        {
          "counter": "call_procedure_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches DatabaseMCP, so you can run agents against it safely.

FAQ

Questions about call_procedure

What does the call_procedure tool do? +

Execute a stored procedure by providing necessary arguments. It is categorised as a Execute tool in the DatabaseMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on call_procedure? +

Register the Database MCP server in PolicyLayer and add a rule for call_procedure: 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 DatabaseMCP. Nothing to install.

What risk level is call_procedure? +

call_procedure is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit call_procedure? +

Yes. Add a rate_limit block to the call_procedure 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.

How do I block call_procedure completely? +

Set action: deny in the PolicyLayer policy for call_procedure. 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.

What MCP server provides call_procedure? +

call_procedure is provided by the Database MCP server (leovegasys/databasemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.