AI agents call rpc_capabilities to retrieve information from Rpcclient without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool inspects (reads) the available API capabilities for a session without performing any actions, modifications, or side effects. It is purely a discovery/query operation to understand what is available.
From the tool's definition Inspect client/subsystem API surface for a session
Attacks that exploit this kind of access
Inspect client/subsystem API surface for a session. It is categorised as a Read tool in the Rpcclient MCP Server, which means it retrieves data without modifying state.
Register the Rpcclient MCP server in PolicyLayer and add a rule for rpc_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 Rpcclient. Nothing to install.
rpc_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 rpc_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 rpc_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.
rpc_capabilities is provided by the Rpcclient MCP server (appknox/rpcclient-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 →