Aggregated risk signals for a single RWA token, optimized for AI-agent decision-making. Composes TVL drift (24h/7d/30d), mint-burn activity, whale-flow anomalies, attestation status, and compliance flags into one structured response with explicit anomaly classifications and human-readable flags. ...
AI agents call get_token_risk_signals to retrieve information from RWA Pipe MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates pre-computed risk analytics for RWA tokens without modifying state or executing external operations. It is fundamentally a Read operation.
From the tool's definition Tool name and description indicate data retrieval: 'Aggregated risk signals for a single RWA token' with composition of TVL drift, mint-burn activity, whale-flow anomalies, attestation status, and compliance flags.
Attacks that exploit this kind of access
Aggregated risk signals for a single RWA token, optimized for AI-agent decision-making. Composes TVL drift (24h/7d/30d), mint-burn activity, whale-flow anomalies, attestation status, and compliance flags into one structured response with explicit anomaly classifications and human-readable flags. Use this when an agent needs to evaluate. It is categorised as a Read tool in the RWA Pipe MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RWA Pipe MCP Server MCP server in PolicyLayer and add a rule for get_token_risk_signals: 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 RWA Pipe MCP Server. Nothing to install.
get_token_risk_signals 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_token_risk_signals 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_token_risk_signals. 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_token_risk_signals is provided by the RWA Pipe MCP Server MCP server (rwapipe/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 →