Return the structural cautions Trigvale surfaces for a startup-idea archetype. Useful BEFORE calling validate_idea — read the cautions for the cluster you think the idea fits, then sharpen the pitch to address those gaps before scoring. Pure local catalog lookup, no API call, no token cost, no ra...
AI agents call get_archetype_cautions 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 queries a local data structure and retrieves information without modifying state, creating external effects, or executing arbitrary operations. It is a straightforward read operation — lookup and return. The severity is low because even if misused, returning cautions about startup archetypes presents minimal risk to users or systems.
From the tool's definition Tool performs 'catalog lookup' that is 'Pure local' with 'no API call'. Returns 'cautions' for an archetype based on passed archetypeId parameter. The description explicitly states it retrieves and returns pre-existing data without side effects.
Attacks that exploit this kind of access
Return the structural cautions Trigvale surfaces for a startup-idea archetype. Useful BEFORE calling validate_idea — read the cautions for the cluster you think the idea fits, then sharpen the pitch to address those gaps before scoring. Pure local catalog lookup, no API call, no token cost, no rate limit. Pass an archetypeId to get one cluster. 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 get_archetype_cautions: 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.
get_archetype_cautions 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_archetype_cautions 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_archetype_cautions. 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_archetype_cautions 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 →