π εδ½ηη₯ β 转θ‘ζΊ’δ»·η+δ»·ζ Όεδ½ζεΊοΌιε稳ε₯εζθ΅θ
AI agents call cb_dual_low to retrieve information from Cb Strategy without modifying anything β typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and ranks convertible bond data according to specific financial metrics. It is a data retrieval and analysis function that produces filtered/sorted views of existing information without creating, modifying, deleting, or executing any irreversible or external operations.
From the tool's definition Tool performs filtering and sorting of convertible bonds based on dual-low criteria (conversion premium ratio + price). The description indicates 'dual-low ranking/sorting' (εδ½ζεΊ) with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
π εδ½ηη₯ β 转θ‘ζΊ’δ»·η+δ»·ζ Όεδ½ζεΊοΌιε稳ε₯εζθ΅θ . 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_dual_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_dual_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_dual_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_dual_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_dual_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 →