Use this when the user asks about a wallet's AAVE position — 'What is my health factor?', 'What have I supplied to AAVE?', 'How much have I borrowed?', 'Am I at risk of liquidation?', 'Show me my collateral and debt on Arbitrum'. Returns all supplied assets (with aToken balances), all borrowed as...
Part of the Graph Aave MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_aave_user_position to retrieve information from Graph Aave without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_aave_user_position only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_aave_user_position:
rules:
- action: allowSee the full Graph Aave policy for all 32 tools.
Agents calling read-class tools like get_aave_user_position have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Use this when the user asks about a wallet's AAVE position — 'What is my health factor?', 'What have I supplied to AAVE?', 'How much have I borrowed?', 'Am I at risk of liquidation?', 'Show me my collateral and debt on Arbitrum'. Returns all supplied assets (with aToken balances), all borrowed assets (variable + stable debt), collateral flags, and e-mode category. Health Factor ≈ sum(collateral_i * price_i * liqThreshold_i) / sum(debt_i * price_i). HF < 1.0 = liquidatable. Amounts in native token units — divide by 10^decimals.. It is categorised as a Read tool in the Graph Aave MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_aave_user_position. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Graph Aave MCP server.
get_aave_user_position 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_aave_user_position rule in your Intercept 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 Intercept policy for get_aave_user_position. 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_aave_user_position is provided by the Graph Aave MCP server (graph-aave-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept