graphql_query · Ghe Mcp Gateway MCP: Risk & Policy

WHAT IT DOES

What graphql_query does on Ghe Mcp Gateway

AI agents invoke graphql_query to trigger actions in Ghe Mcp Gateway. 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 graphql_query needs a policy

Although GraphQL queries are often read-only, GraphQL also supports mutations that can create, modify, or delete data. The tool permits 'arbitrary' GraphQL, meaning an AI agent could craft mutations to alter repositories, permissions, webhooks, or other sensitive GitHub Enterprise resources. The most severe applicable category is Execute, since arbitrary code/query execution is possible.

From the tool's definition "Run an arbitrary GraphQL query against GitHub's v4 API" — the word 'arbitrary' and 'run' indicate execution of user-supplied GraphQL, which can include mutations (write/destructive operations) beyond simple reads

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

graphql_query Rate-limited

graphql_query 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": {
    "graphql_query": {
      "limits": [
        {
          "counter": "graphql_query_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 Ghe Mcp Gateway, so you can run agents against it safely.

FAQ

Questions about graphql_query

What does the graphql_query tool do? +

Run an arbitrary GraphQL query against GitHub's v4 API. It is categorised as a Execute tool in the Ghe Mcp Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on graphql_query? +

Register the Ghe Mcp Gateway MCP server in PolicyLayer and add a rule for graphql_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 Ghe Mcp Gateway. Nothing to install.

What risk level is graphql_query? +

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

Can I rate-limit graphql_query? +

Yes. Add a rate_limit block to the graphql_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.

How do I block graphql_query completely? +

Set action: deny in the PolicyLayer policy for graphql_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.

What MCP server provides graphql_query? +

graphql_query is provided by the Ghe Mcp Gateway MCP server (mholzinger/ghe-mcp-gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.