Browse the NexusToken capability catalog — a live directory of
AI agents call nexus_discover_capabilities to retrieve information from NexusToken without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and discovers information about available capabilities without modifying, executing, deleting, or committing financial resources. 'Browse' and 'discover' are characteristic Read operations with no side effects. The incomplete description still clearly conveys informational retrieval.
From the tool's definition Tool name 'nexus_discover_capabilities' and description 'Browse the NexusToken capability catalog — a live directory of' indicate querying/browsing read-only access to a catalog of capabilities.
Attacks that exploit this kind of access
Browse the NexusToken capability catalog — a live directory of. It is categorised as a Read tool in the NexusToken MCP Server, which means it retrieves data without modifying state.
Register the NexusToken MCP server in PolicyLayer and add a rule for nexus_discover_capabilities: 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 NexusToken. Nothing to install.
nexus_discover_capabilities 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 nexus_discover_capabilities 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 nexus_discover_capabilities. 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.
nexus_discover_capabilities is provided by the NexusToken MCP server (bobuilds/nexustoken-sdk). 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 →