Scan all Spectra chains for YT (Yield Token) arbitrage opportunities. Compares the IBT's actual current variable APR against the rate implied by the YT's market price. When these diverge significantly, an arbitrage opportunity may exist: - Positive spread (IBT APR > YT implied rate): IBT earn...
Single-target operation
Part of the Spectra MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call scan_yt_arbitrage 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 scan_yt_arbitrage 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:
scan_yt_arbitrage:
rules:
- action: allow See the full Spectra policy for all 25 tools.
Agents calling read-class tools like scan_yt_arbitrage 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.
Scan all Spectra chains for YT (Yield Token) arbitrage opportunities. Compares the IBT's actual current variable APR against the rate implied by the YT's market price. When these diverge significantly, an arbitrage opportunity may exist: - Positive spread (IBT APR > YT implied rate): IBT earns more than the YT price implies - Negative spread (IBT APR < YT implied rate): IBT earns less than the YT price implies Returns opportunities sorted by absolute spread, with capital-aware entry sizing, break-even analysis, and IBT APR composition (organic base yield vs external incentive programs — critical for assessing whether the spread is driven by sustainable yield). Execution mechanics: - Buying YT: The Spectra Router can flash-mint (flash-borrow IBT → mint PT+YT → sell PT on pool → user covers shortfall → user receives YT). This appears as SELL_PT in pool activity. Alternatively, minting IBT → PT+YT and selling PT separately. - Selling YT: The Router flash-redeems (borrow IBT → buy PT from pool → burn PT+YT → repay → profit). This appears as BUY_PT in pool activity. The Curve pool does NOT trade YT directly. - Break-even assumes the spread persists. Real variable rates fluctuate — spreads can close quickly. The break-even period is the minimum time needed, not a guarantee. Use compare_yield for a detailed fixed-vs-variable breakdown on a specific pool. Use get_pool_activity to monitor recent trading patterns in the target pool.. 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 scan_yt_arbitrage. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Spectra MCP server.
scan_yt_arbitrage 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 scan_yt_arbitrage 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 scan_yt_arbitrage. 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.
scan_yt_arbitrage 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