AgentKey is a security and authorization layer for AI agents. It sits between AI agents and the systems they touch, enforcing fail-closed permissions, preventing unauthorized actions with single-use execution tokens, managing human approvals, and generating cryptographically signed, offline-verifiable audit evidence. It is built for AI agents and MCP workflows.

How does AgentKey prevent unauthorized AI agent actions?

In enforce mode, every tool call routed through AgentKey is checked against defined permissions before it runs, and an approved action can be bound to a single-use execution attempt that expires after use. An action that is not explicitly allowed is denied by default. In the default observe mode the same checks run and are recorded, with would-block markers, without blocking. Protection applies to calls routed through the SDK or the MCP bridge.

What is fail-closed permission for AI agents?

Fail-closed permission means that if AgentKey cannot verify an action is allowed, the action is blocked by default. This is the opposite of fail-open systems where unclear permissions allow actions through. Fail-closed is the safer approach for AI agents that may attempt unexpected or harmful actions.

How does AgentKey protect against prompt injection?

AgentKey scans untrusted content before it reaches the model and validates every tool call routed through it against an explicit permission policy. In enforce mode, a call blocked by policy or by a quarantined input scan does not run; in the default observe mode the same call is recorded with a would-block marker instead of being blocked. This covers tool calls routed through the AgentKey SDK or MCP bridge; it does not intercept calls made outside the integration.

What is MCP security in AgentKey?

MCP security in AgentKey refers to protecting Model Context Protocol servers and the AI agents that connect to them. AgentKey adds a security layer that controls what MCP tools an agent can call, validates inputs, requires human approval for sensitive operations, and records every action as verifiable evidence.

What are cryptographically signed audit logs?

AgentKey generates audit evidence that is cryptographically signed, meaning it cannot be tampered with after creation. Each audit record includes a digital signature that proves its authenticity. This evidence can be verified offline, without access to AgentKey's servers, making it suitable for compliance, incident response, and legal proceedings.

Does AgentKey support human-in-the-loop approval?

Yes. AgentKey supports human-in-the-loop approval workflows where sensitive actions require manual sign-off before execution. You can define which actions need human approval, and AgentKey will pause the agent, notify the approver, and only execute the action after explicit approval.

How much does AgentKey cost?

AgentKey offers a free tier for getting started. Paid plans scale based on agent usage and the number of protected actions. Visit the pricing page for current plan details and feature comparisons.

Which AI platforms does AgentKey work with?

AgentKey is agent-agnostic. Any agent whose tool calls can be wrapped with the JavaScript or Python SDK, or whose MCP client can be pointed at the AgentKey MCP bridge, works with it. The agent's framework or model does not matter: AgentKey sits on the tool-call path, not inside the model.

Can AgentKey audit evidence be used for compliance?

Yes. AgentKey's audit evidence is cryptographically signed, offline-verifiable, and can help meet audit evidence requirements. Every action routed through AgentKey is recorded with timestamps, agent identity, tool called, and outcome. The evidence is tamper-evident rather than tamper-proof: verification detects any alteration to the stored record, but it does not prove the signing keys were never compromised, and it does not cover actions taken outside AgentKey.

AgentKey

AgentKey · Security

AI Agent Tool Security

AI agent tool security is the practice of vetting, scoring, and controlling the external tools, MCP servers, APIs, and plugins an AI agent connects to, so that untrusted or revoked tools cannot execute on the agent's behalf.

By AgentKey · Last updated 2026-10-08

Tools are the supply chain

An agent is only as trustworthy as the tools it calls. A tool can be malicious, compromised, or simply changed. Treating tools as a supply chain means knowing which ones the agent connects to, scoring their risk, and being able to block a tool the moment it is revoked.

The tool lifecycle

Register: add a tool to the trust registry when the agent first connects to it.
Score: assign a risk score based on what the tool can do and who publishes it.
Approve or flag: mark a tool approved, flagged, quarantined, or revoked.
Enforce: a revoked tool is blocked outright; a flagged tool escalates risk.
Override: set a score manually when you have context the registry does not.

Unregistered surface area

An unregistered tool is a blind spot. Surfacing the tools an agent reaches that you have not vetted lets you see, and then close, the part of the attack surface you did not know about.

Where AgentKey fits

AgentKey keeps a tool trust registry. register_tool records and scores a tool; a flagged or quarantined tool escalates risk during authorization, and a revoked tool is blocked regardless of permission.

Frequently asked questions

What is AI agent tool security?

Vetting, scoring, and controlling the tools an agent connects to. It treats tools as a supply chain: register, score, approve or flag, and block a tool when it is revoked.

What happens when a tool is revoked?

Calls to it are blocked outright, regardless of the permission. A flagged or quarantined tool escalates the risk level instead of blocking immediately.