🔍 下修博弈分析 — 寻找可能触发回售/下修的转债博弈机会
AI agents call cb_revision_analysis 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 analyzes Chinese convertible bonds to identify potential opportunities based on revision/redemption triggers. It retrieves and analyzes financial data without modifying any state, executing code, or committing financial transactions. The action is read-only querying and ranking of bond data to support investment research and decision-making.
From the tool's definition Tool name 'cb_revision_analysis' and description '寻找可能触发回售/下修的转债博弈机会' (find convertible bond arbitrage opportunities that may trigger redemption/revision) indicate analysis and search functionality.
Attacks that exploit this kind of access
🔍 下修博弈分析 — 寻找可能触发回售/下修的转债博弈机会. 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_revision_analysis: 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_revision_analysis 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_revision_analysis 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_revision_analysis. 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_revision_analysis 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 →