Return an 'is anything on fire' snapshot across every registered market for a protocol + chain. For Compound V3, returns per-market pause flags, utilization, totalSupply, totalBorrow. For Aave V3, returns per-reserve isActive/isFrozen/isPaused, utilization, totalSupplied, totalBorrowed. Each entr...
AI agents call get_market_incident_status to retrieve information from VaultPilot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
chain | string | — | EVM chain (used by compound-v3 / aave-v3 only; ignored otherwise). |
wallet | string | — | Wallet address — used by `solana-protocols` (SPL exposure scope) and `tron` (TRC-20 USDT counterparty blacklist scope, issue #249). Solana base58 (43-44 chars) |
protocol | string | Yes | What to scan. EVM lending: compound-v3 flags per-Comet pause + utilization, aave-v3 flags per-reserve isPaused/isFrozen/!isActive + utilization. Base-layer chai |
Parameters from the server's own tool schema.
Even though get_market_incident_status only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Return an 'is anything on fire' snapshot across every registered market for a protocol + chain. For Compound V3, returns per-market pause flags, utilization, totalSupply, totalBorrow. For Aave V3, returns per-reserve isActive/isFrozen/isPaused, utilization, totalSupplied, totalBorrowed. Each entry has a flagged bit: Compound flags on any pause or utilization ≥ 95% (borrowers trapped); Aave flags on paused/frozen/inactive or utilization ≥ 95%. Top-level incident: true if any market/reserve is flagged. Use when you suspect a governance pause, a utilization cliff, or multi-market contagion from a shared-collateral exploit — collapses what would otherwise take one get_compound_market_info call per market. It is categorised as a Read tool in the VaultPilot MCP MCP Server, which means it retrieves data without modifying state.
get_market_incident_status accepts 3 parameters: chain, wallet, protocol. Required: protocol. The full parameter table on this page comes from the server's own tool schema.
Register the VaultPilot MCP server in PolicyLayer and add a rule for get_market_incident_status: 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 VaultPilot MCP. Nothing to install.
get_market_incident_status 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_market_incident_status 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_market_incident_status. 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_market_incident_status is provided by the VaultPilot MCP server (vaultpilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.