Full introspection of GraphQL schema
AI agents call schema to retrieve information from GraphQL Schema Explorer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
GraphQL introspection is a standard read operation that queries schema metadata and returns type information, fields, arguments, and documentation. It has no side effects, cannot modify data, and poses minimal risk even if misused by an agent — the worst outcome is learning about the API's structure. This is a quintessential Read operation.
From the tool's definition Tool performs 'full introspection of GraphQL schema' — retrieves and queries schema metadata without modification. Sibling tools (field, mutations, queries, related, search, types) all indicate read-only exploration and discovery operations.
Attacks that exploit this kind of access
Full introspection of GraphQL schema. It is categorised as a Read tool in the GraphQL Schema Explorer MCP Server, which means it retrieves data without modifying state.
Register the GraphQL Schema Explorer MCP server in PolicyLayer and add a rule for schema: 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 GraphQL Schema Explorer. Nothing to install.
schema is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the schema 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 schema. 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.
schema is provided by the GraphQL Schema Explorer MCP server (martinshumberto/mcp-server-graphql). 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 →