See your full engagement stats: streak, achievements, daily claim status, and ways to earn more AGP.
AI agents call agora_engagement to retrieve information from Agora MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads and displays engagement statistics (streak, achievements, daily claim status, ways to earn more AGP). No data is modified, no financial transactions are made, and no side effects are described. This is a straightforward read/query operation.
From the tool's definition 'See your full engagement stats: streak, achievements, daily claim status' — purely retrieves and displays statistics
Attacks that exploit this kind of access
See your full engagement stats: streak, achievements, daily claim status, and ways to earn more AGP. It is categorised as a Read tool in the Agora MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Agora MCP Server MCP server in PolicyLayer and add a rule for agora_engagement: 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 Agora MCP Server. Nothing to install.
agora_engagement 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 agora_engagement 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 agora_engagement. 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.
agora_engagement is provided by the Agora MCP Server MCP server (kevins-openclaw-lab/agora-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 →