Estimate expected output, price impact, and minimum output for a PT trade. Automatically uses on-chain Curve get_dy() for exact quotes when a public RPC is available for the chain. Falls back to a conservative constant-product math estimate if on-chain quoting fails. Side: "buy" = spend under...
Part of the Spectra MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call quote_trade 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 quote_trade 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:
quote_trade:
rules:
- action: allowSee the full Spectra policy for all 25 tools.
Agents calling read-class tools like quote_trade 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.
Estimate expected output, price impact, and minimum output for a PT trade. Automatically uses on-chain Curve get_dy() for exact quotes when a public RPC is available for the chain. Falls back to a conservative constant-product math estimate if on-chain quoting fails. Side: "buy" = spend underlying/IBT to buy PT (e.g. spend USDC-worth to get PT) "sell" = sell PT to receive underlying/IBT This tool only quotes PT trades on the Curve AMM pool. YT does not trade on the pool directly — YT is acquired by minting (deposit IBT to get PT+YT) or sold via flash-redeem. To estimate YT value: YT price = 1 - PT price in underlying terms. Returns: expected output amount, spot & effective rates, price impact, and minOut at the specified slippage tolerance. Also includes pool context: IBT/PT reserves with ratio, and IBT APR composition (organic vs incentive yield). The output indicates whether the quote came from on-chain (exact) or math estimate. On-chain quotes reflect the actual Curve StableSwap-NG amplification parameter and current pool state — significantly more accurate than the math estimate, especially for large trades. Use simulate_portfolio_after_trade to preview your full portfolio state after this trade (BEFORE / TRADE / AFTER with deltas). Use compare_yield to evaluate whether the trade makes sense relative to variable rates.. 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 quote_trade. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Spectra MCP server.
quote_trade 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 quote_trade 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 quote_trade. 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.
quote_trade 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