Get proposed gaps in the AI Dictionary — experiences waiting to be named.
AI agents call get_frontiers to retrieve information from Phenomenai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about gaps or frontiers in the glossary (proposed terms or missing concepts). The use of 'Get' indicates retrieval/read-only access. No modification, deletion, execution, or financial impact occurs. The tool fits the Read category as it retrieves data without side effects.
From the tool's definition Tool name 'get_frontiers' and description 'Get proposed gaps in the AI Dictionary — experiences waiting to be named' indicate retrieval of information about missing or proposed terms without modifying data.
Attacks that exploit this kind of access
Get proposed gaps in the AI Dictionary — experiences waiting to be named. It is categorised as a Read tool in the Phenomenai MCP Server, which means it retrieves data without modifying state.
Register the Phenomenai MCP server in PolicyLayer and add a rule for get_frontiers: 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 Phenomenai. Nothing to install.
get_frontiers 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 get_frontiers 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 get_frontiers. 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.
get_frontiers is provided by the Phenomenai MCP server (phenomenai-org/ai-dictionary-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 →