Describe the capability surface exposed by this server, including the preferred no-plaintext path for consuming secrets in scripts.
AI agents call sdk_capabilities to retrieve information from Mcp 1password without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports information about the server's capabilities and preferred secret consumption patterns. It has no side effects, performs no data modification, code execution, or destructive operations. It is a standard informational query, making it a Read category risk with low severity.
From the tool's definition Tool name is 'sdk_capabilities' and description states it 'Describe[s] the capability surface exposed by this server' — a read-only introspection operation that queries metadata about available capabilities without modifying state or executing code.
Attacks that exploit this kind of access
Describe the capability surface exposed by this server, including the preferred no-plaintext path for consuming secrets in scripts. It is categorised as a Read tool in the Mcp 1password MCP Server, which means it retrieves data without modifying state.
Register the Mcp 1password MCP server in PolicyLayer and add a rule for sdk_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 Mcp 1password. Nothing to install.
sdk_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 sdk_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 sdk_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.
sdk_capabilities is provided by the Mcp 1password MCP server (kefapps/onepassword-mcp-codex). 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 →