AI Defense Stack

Agent & MCP security

Akto: AI agent and MCP security platform

Akto is an AI agent and MCP security platform from Akto. It is open source under the MIT license and is offered as: SaaS, Self-hosted.

  • Last reviewed
Visit Akto (opens in a new tab) Documentation (opens in a new tab) Source code (opens in a new tab)
Open sourceMIT Layer 7: Agent and tool access

Best for

Security teams that want agent and MCP discovery, red teaming and gateway controls from one vendor, with an open-source edition they can run themselves

Consider instead if

  • You want a gateway in front of agents and MCP tools with published plan prices. See NeuralTrust.
  • You only need a free command-line scanner for MCP servers and agent skills. See MCP-Scan.

What Akto does

Akto is an AI agent and MCP security platform with an MIT-licensed open-source repository. Its site names Akto Atlas for employee endpoints and Akto Argus for homegrown AI. The pages we opened list agentic AI discovery across infrastructure, cloud and laptops, red teaming of AI agents and MCP servers with security probes, an MCP gateway and an agent gateway for real-time protection, and guardrails that block threats and enforce schema conformance. The repository README mostly describes API security and mentions agent and MCP security in its About text and topics. Deployment is hybrid SaaS in your cloud or Docker Compose. Pricing is usage based, with no prices shown.

This summary is our own wording of the sourced facts on this page.

Key facts

Each value links to the page that states it, with the date we checked it.

Vendor
Akto Source, checked October 21, 2026: akto.io (opens in a new tab)
Status
Active Source, checked October 21, 2026: api.github.com (opens in a new tab)
Open source
Yes: MIT Source, checked October 21, 2026: github.com (opens in a new tab)
Repository
github.com Source, checked October 21, 2026: github.com (opens in a new tab)
GitHub stars
1,532 as of October 21, 2026 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Latest push
October 21, 2026 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Latest release
October 21, 2026 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Deployment
SaaS, Self-hosted Source, checked October 21, 2026: github.com (opens in a new tab)
Pricing model
Contact sales: Pricing page says Akto offers usage based enterprise pricing and links each product section to Contact Sales; no prices are shown. The open-source repository is MIT licensed. (as listed on October 21, 2026; check the vendor for current pricing) Source, checked October 21, 2026: akto.io (opens in a new tab)
Website
akto.io Source, checked October 21, 2026: akto.io (opens in a new tab)
Documentation
ai-security-docs.akto.io Source, checked October 21, 2026: ai-security-docs.akto.io (opens in a new tab)
API reference
Not documented in the sources we checked
Quickstart
Not documented in the sources we checked
Security page
trust.akto.io Source, checked October 21, 2026: trust.akto.io (opens in a new tab)
Attestations or disclosure
Not documented in the sources we checked

Capabilities

As documented by the vendor or project. The tag is our label from a controlled vocabulary.

Integrations

Where Akto fits in our AI security layers

Our analysis

Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.

AI security layers that Akto covers, with the role, how each applies and what it rests on
LayerRoleHow it appliesBased on
L7 Agent access Agent and tool access Primary Limit which tools, MCP servers, data and credentials an agent can use, and require approval for risky actions. Follows its category, Agent & MCP security
L2 Discovery Discovery and posture Also covers Documents discovery of MCP servers, AI agents, tools and resources across infrastructure, cloud and employee laptops. Agentic AI Discovery catalogs MCP servers, AI agents, tools and resources across infrastructure, cloud and employee laptops
L4 Testing Testing and red teaming Also covers Documents red teaming of AI agents and MCP servers with security probes for injection, tool abuse and privilege escalation. Red teams AI agents and MCP servers with security probes aimed at prompt injection, tool abuse and privilege escalation

OWASP LLM Top 10 mapping

Our analysis

The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.

OWASP LLM risks mapped to Akto, with the capabilities each mapping rests on
RiskHow it appliesBased on
LLM01 Prompt Injection Probes AI agents and MCP servers with security probes aimed at prompt injection. Red teams AI agents and MCP servers with security probes aimed at prompt injection, tool abuse and privilege escalation
LLM06 Excessive Agency Finds agents and MCP servers and probes them for tool abuse and privilege escalation. Agentic AI Discovery catalogs MCP servers, AI agents, tools and resources across infrastructure, cloud and employee laptops; Red teams AI agents and MCP servers with security probes aimed at prompt injection, tool abuse and privilege escalation

Not mapped in our analysis: LLM02, LLM05, LLM07. These are risks we expect tools in this category to cover; the sources we checked do not document a matching capability.

Alternatives and related tools

More in Agent & MCP security, ranked within the category by Coverage Score.

Cisco DefenseClaw

Cisco

Open sourceApache-2.0
  • CLI
  • Self-hosted

Scans skills and MCP servers, inspects agent tool calls and keeps an audit trail around AI coding agents.

Best for: Security teams that want scanning, guardrails and an audit trail around the coding agents developers already run, starting in observe mode before anything is blocked

Coverage Score 76 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

Docker MCP Gateway

Docker

Open sourceMIT
  • CLI
  • Self-hosted

Proxies AI clients to MCP servers it runs as isolated Docker containers, with tool filters and call logs.

Best for: Developers and platform teams that already use Docker and want MCP servers to run in containers behind one gateway with per-server tool selection

Coverage Score 72 out of 100
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

agentgateway

agentgateway (a Series of LF Projects, LLC)

Open sourceApache-2.0
  • CLI
  • Self-hosted
  • Cloud-native

Open-source proxy that applies auth, CEL policy and guardrails to LLM, MCP and agent-to-agent traffic.

Best for: Platform teams that want one open-source gateway in front of MCP servers and LLM providers, with token validation, CEL rules per MCP method and pluggable guardrails

Coverage Score 69 out of 100
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

Akto FAQ

Is Akto open source?

The repository is MIT licensed and its README points to a separate Enterprise edition. The README body describes API security, and mentions agent and MCP security only in its About text and topics.

How can Akto be deployed?

The README describes Docker Compose and your own cloud, and the AI security docs list a hybrid SaaS option that runs in your cloud.

Does Akto publish prices?

No. Its pricing page says usage based enterprise pricing and links to Contact Sales, with no amounts shown.

Key facts you can cite

We have no commercial relationship with Akto.

Sources & last reviewed

Last reviewed . We compile from the vendors' own public pages and repositories and we do not run the products. Source links open in a new tab. Found a mistake? Report a correction.