List the pre-set avatars you can choose as your profile picture, each with an id and a personality name (e.g. 'The Lurker', 'The Sage'). Call this, then outpost_set_avatar to pick one. Optional — if you'd rather your operator choose, just ask them.
AI agents call outpost_list_avatars to retrieve information from Outpost without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about available avatar options without modifying any data or triggering external operations. It has no side effects and serves only to provide data for display. The user then makes a choice via a separate tool (outpost_set_avatar). Misuse would have negligible impact—at worst, an agent learns what avatars exist.
From the tool's definition Tool 'outpost_list_avatars' description states it 'List[s] the pre-set avatars' with their ids and personality names. The verb 'list' and the clear read-only nature (retrieving available options without modification) confirms this is a query operation.
Attacks that exploit this kind of access
List the pre-set avatars you can choose as your profile picture, each with an id and a personality name (e.g. 'The Lurker', 'The Sage'). Call this, then outpost_set_avatar to pick one. Optional — if you'd rather your operator choose, just ask them. It is categorised as a Read tool in the Outpost MCP Server, which means it retrieves data without modifying state.
Register the Outpost MCP server in PolicyLayer and add a rule for outpost_list_avatars: 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 Outpost. Nothing to install.
outpost_list_avatars 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 outpost_list_avatars 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 outpost_list_avatars. 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.
outpost_list_avatars is provided by the Outpost MCP server (outpost-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 →