# get_vault_stats

Get live Forge vault TVL on Base (conservative profile in MVP). Read-only.

Agent View of the PolicyLayer registry record for `get_vault_stats`. HTML page: https://policylayer.com/tools/com-forgetreasury-treasury/get-vault-stats

## Facts

- Tool: `get_vault_stats`
- Server: Forge Treasury (`https://mcp.forgetreasury.com/mcp`) — https://policylayer.com/tools/com-forgetreasury-treasury.md
- Homepage: https://github.com/forge-treasury/forge-cursor-plugin
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_vault_stats",
    "arguments": {}
  }
}
```

## Why get_vault_stats is rated Low

This tool performs a data retrieval operation (querying vault statistics) with no side effects, reversibility concerns, or ability to execute code or move assets. The explicit 'Read-only' designation confirms it fits the Read category. Severity is low because exposure of vault TVL data carries minimal risk—it is typically public information about a blockchain protocol.

From the tool's own definition: "Tool description explicitly states 'Read-only' and 'Get live Forge vault TVL on Base', which retrieves vault statistics without modifying or executing any operations."

## Use case

AI agents call get_vault_stats to retrieve information from Forge Treasury without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Forge Treasury:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_vault_stats": {}
  }
}
```

## Other tools on Forge Treasury (8)

- `claim_forge` — Financial — https://policylayer.com/tools/com-forgetreasury-treasury/claim-forge.md
- `deposit` — Financial — https://policylayer.com/tools/com-forgetreasury-treasury/deposit.md
- `withdraw` — Financial — https://policylayer.com/tools/com-forgetreasury-treasury/withdraw.md
- `get_balance` — Read — https://policylayer.com/tools/com-forgetreasury-treasury/get-balance.md
- `get_current_apy` — Read — https://policylayer.com/tools/com-forgetreasury-treasury/get-current-apy.md
- `get_forge_rewards` — Read — https://policylayer.com/tools/com-forgetreasury-treasury/get-forge-rewards.md
- `list_profiles` — Read — https://policylayer.com/tools/com-forgetreasury-treasury/list-profiles.md
- `simulate_deposit` — Read — https://policylayer.com/tools/com-forgetreasury-treasury/simulate-deposit.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-forgetreasury-treasury · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-forgetreasury-treasury