Get the GraphQL schema for a Limitless subgraph via introspection.
AI agents call get_subgraph_schema to retrieve information from Limitless MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and returns GraphQL schema information through introspection. Introspection is a read-only GraphQL operation that retrieves metadata about the schema structure itself. It does not modify, delete, execute code, or trigger external operations.
From the tool's definition Tool name is 'get_subgraph_schema' and description states it 'Get the GraphQL schema for a Limitless subgraph via introspection.' This retrieves schema metadata via introspection, a read-only operation with no side effects.
Attacks that exploit this kind of access
Get the GraphQL schema for a Limitless subgraph via introspection. It is categorised as a Read tool in the Limitless MCP MCP Server, which means it retrieves data without modifying state.
Register the Limitless MCP server in PolicyLayer and add a rule for get_subgraph_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 Limitless MCP. Nothing to install.
get_subgraph_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 get_subgraph_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 get_subgraph_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.
get_subgraph_schema is provided by the Limitless MCP server (paulieb14/limitless-subgraphs). 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 →