AI agents call cfsa_search_standards to retrieve information from GBMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search or query standards metadata without modifying data. Although the description is empty, the naming convention ('search'), the server's stated purpose (querying), and the pattern of sibling tools ('get', 'search') all indicate this is a retrieval operation with no side effects. The minimal blast radius from misuse (returning metadata) and non-destructive nature justify low severity.
From the tool's definition Tool name is 'cfsa_search_standards' which follows the search/query pattern. It is a sibling of tools like 'cfsa_get_standard', 'doc88_search_documents', and 'foodmate_get_law' that are clearly Read operations.
Attacks that exploit this kind of access
cfsa_search_standards. It is categorised as a Read tool in the GBMCP MCP Server, which means it retrieves data without modifying state.
Register the GB MCP server in PolicyLayer and add a rule for cfsa_search_standards: 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 GBMCP. Nothing to install.
cfsa_search_standards 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 cfsa_search_standards 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 cfsa_search_standards. 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.
cfsa_search_standards is provided by the GB MCP server (loydgik/gbmcp). 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 →