AI agents call classify_archetype to retrieve information from Trigvale without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data by categorizing a startup idea against a predefined set of archetypes. It produces informational output (mapping) with no ability to modify data, execute external operations, delete records, or affect financial systems. The operation is read-only analysis, making it the safest category.
From the tool's definition Tool description indicates it 'Map[s] an idea' to archetypes, which is a classification/lookup operation. No description suggests data creation, modification, deletion, code execution, or financial impact.
Attacks that exploit this kind of access
Map an idea to 1–3 of Trigvale. It is categorised as a Read tool in the Trigvale MCP Server, which means it retrieves data without modifying state.
Register the Trigvale MCP server in PolicyLayer and add a rule for classify_archetype: 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 Trigvale. Nothing to install.
classify_archetype 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 classify_archetype 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 classify_archetype. 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.
classify_archetype is provided by the Trigvale MCP server (sydacos-development/trigvale-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 →