graphql_query · Telique MCP: Risk & Policy

WHAT IT DOES

What graphql_query does on Telique MCP

AI agents invoke graphql_query to trigger actions in Telique 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 graphql_query needs a policy

The tool runs arbitrary GraphQL queries supplied by the caller against two distinct backend APIs (LSMS and LERG). While GraphQL is often read-oriented, arbitrary query execution can include mutations, and the open-ended nature of the tool means an AI agent could construct queries with unintended scope or side effects.

From the tool's definition "Execute GraphQL queries against LSMS or LERG" — the tool explicitly executes arbitrary GraphQL queries against backend APIs

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 Telique MCP, so you can run agents against it safely.

FAQ

Questions about graphql_query

What does the graphql_query tool do? +

Execute GraphQL queries against LSMS or LERG. These are DISTINCT APIs with different schemas — do not mix their syntax. LSMS (service=. It is categorised as a Execute tool in the Telique 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 graphql_query? +

Register the Telique 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 Telique MCP. 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 Telique MCP server (ringer/telique-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.