AI agents call nodus_verify_signal to retrieve information from Nodusai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns historical grounding sources without modifying any state. It performs information retrieval to support verification of past Oracle signals. No data is created, modified, deleted, or executed. The action is purely informational and read-only, making it the lowest severity category.
From the tool's definition Tool name 'nodus_verify_signal' with description 'Retrieve grounding sources for a past signal to verify the Oracle' indicates a retrieval operation.
Attacks that exploit this kind of access
Retrieve grounding sources for a past signal to verify the Oracle. It is categorised as a Read tool in the Nodusai MCP Server, which means it retrieves data without modifying state.
Register the Nodusai MCP server in PolicyLayer and add a rule for nodus_verify_signal: 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 Nodusai. Nothing to install.
nodus_verify_signal 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 nodus_verify_signal 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 nodus_verify_signal. 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.
nodus_verify_signal is provided by the Nodusai MCP server (nodusai-your-prediction-broker/nodusai-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 →