Get a single capability with its component and asset bindings.
AI agents call get_capability to retrieve information from Mipiti MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries capability data along with its associated bindings (components and assets). It performs a read-only lookup operation with no side effects on the system state. No data is created, modified, or deleted. The blast radius of misuse is minimal—an agent could retrieve sensitive capability information, but cannot alter threat models, controls, or evidence.
From the tool's definition Tool name is 'get_capability' and description states 'Get a single capability' — a retrieval operation with no modification, creation, or deletion.
Attacks that exploit this kind of access
Get a single capability with its component and asset bindings. It is categorised as a Read tool in the Mipiti MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mipiti MCP Server MCP server in PolicyLayer and add a rule for get_capability: 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 Mipiti MCP Server. Nothing to install.
get_capability 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 get_capability 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 get_capability. 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.
get_capability is provided by the Mipiti MCP Server MCP server (mipiti/mipiti-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 →