Executes a read-only GraphQL query against the Hasura endpoint...
AI agents invoke run_graphql_query to trigger actions in Advanced Hasura GraphQL 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.
Although labeled 'read-only', this tool executes arbitrary GraphQL queries determined by user input. GraphQL queries can perform complex operations including multiple nested resolvers, field authorization bypass scenarios, and resource-intensive aggregations that could overwhelm the endpoint.
From the tool's definition Executes a read-only GraphQL query against the Hasura endpoint
Attacks that exploit this kind of access
Executes a read-only GraphQL query against the Hasura endpoint. It is categorised as a Execute tool in the Advanced Hasura GraphQL MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Advanced Hasura GraphQL MCP Server MCP server in PolicyLayer and add a rule for run_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 Advanced Hasura GraphQL MCP Server. Nothing to install.
run_graphql_query 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 run_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.
Set action: deny in the PolicyLayer policy for run_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.
run_graphql_query is provided by the Advanced Hasura GraphQL MCP Server MCP server (vikasversetest-debug/hasura_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →