AI agents invoke runtime_graphql to trigger actions in Zion. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | |
appExId | string | null | — | |
variables | object | — | |
projectExId | string | — | |
appVersionExId | string | null | — |
Parameters from the server's own tool schema.
This tool executes arbitrary GraphQL operations (queries, mutations, subscriptions) against a production backend with administrative privileges. While GraphQL can perform reads (Read), writes (Write), or deletions (Destructive) depending on the operation sent, the tool itself is fundamentally an execution interface that runs whatever operation an agent specifies.
From the tool's definition Tool description states it will "Run a raw GraphQL operation against the deployed project's runtime backend" with "admin" privileges.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Run a raw GraphQL operation against the deployed project's runtime backend (the auto-generated data/actionflow/AI/TPA API), as admin. It is categorised as a Execute tool in the Zion MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
runtime_graphql accepts 5 parameters: query, appExId, variables, projectExId, appVersionExId. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Zion MCP server in PolicyLayer and add a rule for runtime_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 Zion. Nothing to install.
runtime_graphql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the runtime_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.
Set action: deny in the PolicyLayer policy for runtime_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.
runtime_graphql is provided by the Zion MCP server (zion-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
runtime_graphql is one line of Zion's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →