run_gsql · TG_ MCP: Risk & Policy

WHAT IT DOES

What run_gsql does on TG_MCP

AI agents invoke run_gsql to trigger actions in TG_MCP. 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 run_gsql needs a policy

This tool executes arbitrary GSQL queries whose effects are determined entirely by the query argument provided by the user/agent. While GSQL queries can perform reads, writes, or even destructive operations, the tool itself is an execution primitive—the danger lies in what query gets executed. Raw query execution against a database is inherently Execute-class.

From the tool's definition Tool name 'run_gsql' and description 'Run a raw GSQL query' indicate execution of arbitrary GSQL commands against a TigerGraph database.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_gsql Rate-limited

run_gsql 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": {
    "run_gsql": {
      "limits": [
        {
          "counter": "run_gsql_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 TG_MCP, so you can run agents against it safely.

FAQ

Questions about run_gsql

What does the run_gsql tool do? +

MCP tool: Run a raw GSQL query. It is categorised as a Execute tool in the TG_MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_gsql? +

Register the TG_ MCP server in PolicyLayer and add a rule for run_gsql: 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 TG_MCP. Nothing to install.

What risk level is run_gsql? +

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

Can I rate-limit run_gsql? +

Yes. Add a rate_limit block to the run_gsql 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 run_gsql completely? +

Set action: deny in the PolicyLayer policy for run_gsql. 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 run_gsql? +

run_gsql is provided by the TG_ MCP server (muzain187/tg_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.