Calculate a leveraged fixed-yield strategy using Spectra PT + Morpho looping. Strategy: Deposit asset -> mint PT on Spectra -> use PT as collateral on Morpho -> borrow underlying -> deposit again -> repeat. Each loop multiplies yield exposure. Returns projected yields at different leverage leve...
Part of the Spectra MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_looping_strategy 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_looping_strategy 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_looping_strategy:
rules:
- action: allow See the full Spectra policy for all 25 tools.
Agents calling read-class tools like get_looping_strategy 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.
Calculate a leveraged fixed-yield strategy using Spectra PT + Morpho looping. Strategy: Deposit asset -> mint PT on Spectra -> use PT as collateral on Morpho -> borrow underlying -> deposit again -> repeat. Each loop multiplies yield exposure. Returns projected yields at different leverage levels (1x to max safe leverage), effective APY, and risk parameters. Automatically fetches the live Morpho borrow rate and LLTV when a matching market exists. You can still override morpho_ltv and borrow_rate manually if needed. NOTE: Looping requires a Morpho market that accepts the specific PT as collateral. Risk context: - Borrow rates are variable. A 5% spread (7% yield - 2% borrow) can turn negative if borrow rates spike above your fixed yield. Monitor rates in Morpho. - Higher leverage amplifies both returns and liquidation risk. Consider keeping 1-2 loops below maximum for safety buffer. - Entry cost (price impact) compounds across loops — each iteration faces degraded effective pool liquidity. Use get_morpho_markets to find available Morpho markets. Use scan_opportunities to discover the best looping opportunities across all chains with capital-aware sizing.. It is categorised as a Read tool in the Spectra MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_looping_strategy. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Spectra MCP server.
get_looping_strategy 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_looping_strategy 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_looping_strategy. 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_looping_strategy is provided by the Spectra MCP server (spectra-mcp-server). 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