Get all tokens with active ZARQ warnings. Returns the full list of 205 monitored tokens with their risk level (SAFE/WATCH/WARNING/CRITICAL), trust score, structural weakness count, and NDD score. Filter to see only tokens with active warnings or structural collapse alerts. Example: get_risk_signa...
Part of the Zarq MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_risk_signals to retrieve information from Zarq without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_risk_signals only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_risk_signals:
rules:
- action: allowSee the full Zarq policy for all 11 tools.
Agents calling read-class tools like get_risk_signals have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Get all tokens with active ZARQ warnings. Returns the full list of 205 monitored tokens with their risk level (SAFE/WATCH/WARNING/CRITICAL), trust score, structural weakness count, and NDD score. Filter to see only tokens with active warnings or structural collapse alerts. Example: get_risk_signals() or get_risk_signals(level='CRITICAL'). It is categorised as a Read tool in the Zarq MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_risk_signals. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Zarq MCP server.
get_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_risk_signals rule in your Intercept 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 Intercept policy for get_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_risk_signals is provided by the Zarq MCP server (agentidx/zarq-risk). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept