Low Risk

get_curator_dashboard

Operational dashboard for MetaVault curators. Aggregates vault health, position status, depositor flows, fee revenue estimates, and actionable alerts into a single view. Designed for curators managing live MetaVaults who need a quick operational overview. Returns: - Vault health: TVL, live APY wi...

Part of the Spectra server.

get_curator_dashboard is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE SPECTRA →

Free to start. No card required.

AI agents call get_curator_dashboard to retrieve information from Spectra 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_curator_dashboard 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.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_curator_dashboard": {}
  }
}

See the full Spectra policy for all 25 tools.

Get this rule live on your own Spectra server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY SPECTRA →

View all 25 tools →

These attack patterns abuse exactly the kind of access get_curator_dashboard gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so get_curator_dashboard only ever does what you allow.

SECURE SPECTRA →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the get_curator_dashboard tool do? +

Operational dashboard for MetaVault curators. Aggregates vault health, position status, depositor flows, fee revenue estimates, and actionable alerts into a single view. Designed for curators managing live MetaVaults who need a quick operational overview. Returns: - Vault health: TVL, live APY with composition (base vs incentives), share price - Position status: each active PT position with maturity countdown, APY, and size. Positions approaching maturity are flagged (!!!=14d, !!=30d) - Depositor flows: epoch-by-epoch net inflows/outflows with trend analysis - Fee revenue: estimated annual curator fee revenue (at current rates — both TVL and APY are variable, so this is a snapshot projection, not a guarantee) - Bridge activity: cross-chain CCTP transfer summary - Action items: auto-generated alerts for expiring positions, outflow trends, pending bridges, high incentive dependency, and missing positions Pool allocations show each position as a % of total vault TVL (e.g., "37.1% | $236K"), sorted by size. Idle liquidity (undeployed capital) is shown separately. When the API doesn't provide LP balance data for a position, it shows "?%". Cross-chain positions: MetaVault positions may live on a different chain than the MetaVault itself (e.g., Base MetaVault → Avalanche pools via CCTP bridge). Pool addresses in positions are on the position's chain, not the MetaVault's home chain. Epoch flows: Derived from asset snapshots and rate changes. Yield accrual is estimated from share rate deltas — actual yield may differ. Use share price trend to corroborate. Requires chain + metavault_address. Use get_metavaults to discover addresses. Use model_metavault_strategy for leverage modeling after reviewing the dashboard. Use get_pool_activity on specific pool addresses for trading pattern analysis. Use get_address_activity on the curator's EOA for cross-pool curator activity.. It is categorised as a Read tool in the Spectra MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_curator_dashboard? +

Register the Spectra MCP server in PolicyLayer and add a rule for get_curator_dashboard: 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 Spectra. Nothing to install.

What risk level is get_curator_dashboard? +

get_curator_dashboard is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_curator_dashboard? +

Yes. Add a rate_limit block to the get_curator_dashboard 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 get_curator_dashboard completely? +

Set action: deny in the PolicyLayer policy for get_curator_dashboard. 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 get_curator_dashboard? +

get_curator_dashboard is provided by the Spectra MCP server (spectra-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Spectra tool call.

Deterministic rules across all 25 Spectra tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.