Run a custom GraphQL query against any Predict.fun subgraph. Use this for advanced queries not covered by other tools.
AI agents invoke query_subgraph to trigger actions in Predictfun. 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.
This tool executes arbitrary GraphQL queries against the subgraphs. While GraphQL is typically read-only, 'custom' and 'any subgraph' queries introduce uncertainty about scope. The tool's primary risk is that it allows arbitrary query construction which could be used to extract sensitive data or, if mutations are supported, modify state.
From the tool's definition "Run a custom GraphQL query against any Predict.fun subgraph" — executes arbitrary user-supplied GraphQL queries
Attacks that exploit this kind of access
Run a custom GraphQL query against any Predict.fun subgraph. Use this for advanced queries not covered by other tools. It is categorised as a Execute tool in the Predictfun MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Predictfun MCP server in PolicyLayer and add a rule for query_subgraph: 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 Predictfun. Nothing to install.
query_subgraph 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 query_subgraph 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 query_subgraph. 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.
query_subgraph is provided by the Predictfun MCP server (paulieb14/predictfun-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 →