📊 三低策略 — 双低+剩余规模小，适合追求弹性的投资者
AI agents call cb_triple_low to retrieve information from Cb Strategy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing financial data about convertible bonds without modifying, executing external operations, deleting, or moving money. It produces investment strategy insights based on publicly available market data. The blast radius of misuse is minimal—incorrect analysis would inform poor investment decisions but wouldn't cause system damage, data loss, or unintended execution.
From the tool's definition Tool provides analysis and filtering of Chinese convertible bonds using a '三低策略' (triple-low strategy). The description indicates it performs data retrieval and ranking based on financial metrics (dual-low criteria plus small remaining issuance scale).
Attacks that exploit this kind of access
📊 三低策略 — 双低+剩余规模小，适合追求弹性的投资者. It is categorised as a Read tool in the Cb Strategy MCP Server, which means it retrieves data without modifying state.
Register the Cb Strategy MCP server in PolicyLayer and add a rule for cb_triple_low: 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 Cb Strategy. Nothing to install.
cb_triple_low 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 cb_triple_low 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.
Set action: deny in the PolicyLayer policy for cb_triple_low. 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.
cb_triple_low is provided by the Cb Strategy MCP server (lozzi1910/cb-strategy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →