AI agents call validate.cusip to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs deterministic validation of an existing identifier against a security master database. It retrieves validation results and returns a boolean + metadata with no side effects, no data modification, and no financial movement. The parent server context (pay-per-call on blockchain) is irrelevant to this tool's function—the tool itself only reads and validates. Classification as Read is appropriate.
From the tool's definition Tool description states 'Validate a CUSIP... Returns valid + check digit. Deterministic security-master validation.' This is a validation/lookup operation with no modification, creation, deletion, or financial transaction capabilities.
Attacks that exploit this kind of access
Validate a CUSIP (9-character US/Canada securities identifier) with its mod-10 weighted check digit. Returns valid + check digit. Deterministic security-master validation. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for validate.cusip: 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 Mcp. Nothing to install.
validate.cusip 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 validate.cusip 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 validate.cusip. 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.
validate.cusip is provided by the MCP server (@2sio/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 →