Get SentinelX capabilities (/capabilities), including allowed commands,
AI agents call sentinel_capabilities to retrieve information from SentinelX Core MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs an informational GET request to retrieve capability/configuration metadata. It has no side effects, does not execute commands, and does not modify data. The highest risk is information disclosure about system capabilities, which is typical of read-category tools and poses minimal risk to users or systems.
From the tool's definition Tool name 'sentinel_capabilities' and description 'Get SentinelX capabilities (/capabilities)' indicate a read-only query operation that retrieves information about allowed commands without modifying state.
Attacks that exploit this kind of access
Get SentinelX capabilities (/capabilities), including allowed commands,. It is categorised as a Read tool in the SentinelX Core MCP MCP Server, which means it retrieves data without modifying state.
Register the SentinelX Core MCP server in PolicyLayer and add a rule for sentinel_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 SentinelX Core MCP. Nothing to install.
sentinel_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 sentinel_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 sentinel_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.
sentinel_capabilities is provided by the SentinelX Core MCP server (pensados/sentinelx-core-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 →