Search for FFS flags by keyword. Returns matching flags with their IDs and types.
AI agents call ffs_search_flag to retrieve information from FFS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries flag metadata (IDs, types) based on keyword input. It does not modify, create, delete, or execute any operations—it only returns information. This is a classic Read operation with minimal blast radius if misused.
From the tool's definition Tool name 'ffs_search_flag' and description 'Search for FFS flags by keyword. Returns matching flags with their IDs and types.' indicate a search/query operation with no side effects.
Attacks that exploit this kind of access
Search for FFS flags by keyword. Returns matching flags with their IDs and types. It is categorised as a Read tool in the FFS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FFS MCP Server MCP server in PolicyLayer and add a rule for ffs_search_flag: 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 FFS MCP Server. Nothing to install.
ffs_search_flag 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 ffs_search_flag 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 ffs_search_flag. 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.
ffs_search_flag is provided by the FFS MCP Server MCP server (zhipingyang/ffs-mcp-server). 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 →