AI agents call civitae_missions to retrieve information from Signomy 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 available missions and their slots without creating side effects, modifying data, or executing actions. It is a straightforward read operation consistent with browsing functionality. The low severity reflects minimal risk even if an AI agent misuses it, as the worst outcome would be viewing information already intended to be browsed.
From the tool's definition Tool name 'civitae_missions' and description 'Browse missions and slots' indicate a query/listing operation with no modification or execution capabilities.
Attacks that exploit this kind of access
Browse missions and slots. It is categorised as a Read tool in the Signomy MCP Server, which means it retrieves data without modifying state.
Register the Signomy MCP server in PolicyLayer and add a rule for civitae_missions: 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 Signomy. Nothing to install.
civitae_missions 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 civitae_missions 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 civitae_missions. 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.
civitae_missions is provided by the Signomy MCP server (sunrisesillneversee/agent-universe). 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 →