query_subgraph · Graph Lending MCP: Risk & Policy

WHAT IT DOES

What query_subgraph does on Graph Lending

AI agents invoke query_subgraph to trigger actions in Graph Lending. 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.

WHY IT NEEDS A POLICY

Why query_subgraph needs a policy

This tool executes arbitrary raw GraphQL queries against external subgraph endpoints. While GraphQL over The Graph is typically read-only (queries, not mutations), the 'raw' and 'arbitrary' nature means an AI agent could craft exploratory or complex queries that fan out across 40+ protocols, potentially exfiltrating sensitive account/position data at scale.

From the tool's definition Execute a raw GraphQL query against any registered lending subgraph. Use for custom filters, uncommon fields, or exploratory queries.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_subgraph Rate-limited

query_subgraph stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_subgraph": {
      "limits": [
        {
          "counter": "query_subgraph_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Graph Lending, so you can run agents against it safely.

FAQ

Questions about query_subgraph

What does the query_subgraph tool do? +

Execute a raw GraphQL query against any registered lending subgraph. Use for custom filters, uncommon fields, or exploratory queries. All subgraphs use the Messari standardized lending schema with entities: lendingProtocols, markets, accounts, positions, deposits, borrows, repays, withdraws, liquidates, flashloans, financialsDailySnapshots, marketDailySnapshots, usageMetricsDailySnapshots. It is categorised as a Execute tool in the Graph Lending MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_subgraph? +

Register the Graph Lending 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 Graph Lending. Nothing to install.

What risk level is query_subgraph? +

query_subgraph is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_subgraph? +

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.

How do I block query_subgraph completely? +

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.

What MCP server provides query_subgraph? +

query_subgraph is provided by the Graph Lending MCP server (paulieb14/graph-lending-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.