run_graphql · Gadget MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_graphql does on Gadget MCP Server

AI agents invoke run_graphql to trigger actions in Gadget MCP Server. 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_graphql needs a policy

Although the server is described as read-only and the tool is intended for read-only queries, it executes arbitrary GraphQL provided by the caller. GraphQL queries can include mutations if the server doesn't strictly enforce read-only at the protocol level, and 'arbitrary' execution of user-supplied query strings is an Execute-category action.

From the tool's definition 'Run an arbitrary read-only GraphQL query' — executes arbitrary GraphQL queries supplied as arguments

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_graphql Rate-limited

run_graphql 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_graphql": {
      "limits": [
        {
          "counter": "run_graphql_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 Gadget MCP Server, so you can run agents against it safely.

FAQ

Questions about run_graphql

What does the run_graphql tool do? +

Run an arbitrary read-only GraphQL query against the Gadget app. Use this for complex queries with nested relations or custom filtering that query_records can. It is categorised as a Execute tool in the Gadget MCP Server 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_graphql? +

Register the Gadget MCP Server MCP server in PolicyLayer and add a rule for run_graphql: 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 Gadget MCP Server. Nothing to install.

What risk level is run_graphql? +

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

Can I rate-limit run_graphql? +

Yes. Add a rate_limit block to the run_graphql 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_graphql completely? +

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

run_graphql is provided by the Gadget MCP Server MCP server (stronger-ecommerce/gadget-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.