Get core capabilities (Public).
AI agents call mcp_get_capabilities to retrieve information from Atlas G Protocol without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about capabilities without modifying, executing, or deleting anything. It is a straightforward read operation that returns informational data, fitting the 'Read' category. The public nature and descriptive-only purpose result in low severity—misuse would only expose already-public information about system capabilities.
From the tool's definition Tool name 'mcp_get_capabilities' with description 'Get core capabilities (Public)' indicates a retrieval operation that queries and returns information about available capabilities.
Attacks that exploit this kind of access
Get core capabilities (Public). It is categorised as a Read tool in the Atlas G Protocol MCP Server, which means it retrieves data without modifying state.
Register the Atlas G Protocol MCP server in PolicyLayer and add a rule for mcp_get_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 Atlas G Protocol. Nothing to install.
mcp_get_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 mcp_get_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 mcp_get_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.
mcp_get_capabilities is provided by the Atlas G Protocol MCP server (michaelweed/atlas-g-protocol). 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 →