Authensor is an open-source safety layer that sits between your AI agent and the tools it uses. It checks every action against a policy before it executes, scans content for threats like prompt injection and PII leaks, and creates a tamper-evident audit trail. It works with any AI framework including LangChain, CrewAI, OpenAI Agents SDK, Claude, and MCP servers.

What is an AI agent safety layer?

An AI agent safety layer is software that intercepts actions an AI agent wants to take and decides whether those actions should be allowed, blocked, or sent to a human for approval. Think of it as a firewall for AI behavior. Without one, agents can delete files, leak credentials, make unauthorized API calls, or send data to the wrong place.

Do I need Authensor if I already use Claude, ChatGPT, or LangChain?

Yes. These tools give your agent capabilities like file access, shell commands, API calls, and web browsing. They don't have built-in policies for what's allowed. Authensor adds that missing safety layer. It works alongside any AI tool or platform you already use.

How is Authensor different from prompt engineering or system prompts?

System prompts are instructions that the AI can be tricked into ignoring through prompt injection. Authensor enforces rules in code, outside the AI model. A policy that blocks 'rm -rf' cannot be overridden by a clever prompt. It is deterministic enforcement, not probabilistic guidance.

Yes. Authensor is MIT licensed and fully open source. You can self-host everything, including the control plane with PostgreSQL, at no cost using Docker Compose. There is an optional hosted tier for teams that want managed infrastructure.

How do I get started with Authensor?

Run 'npx create-authensor' in your terminal. It generates a working project with Authensor wired in. You can choose from five templates: TypeScript agent, Python agent, Claude Code hooks, MCP Gateway, or Docker self-hosted control plane.

What AI frameworks does Authensor work with?

Authensor works with LangChain, LangGraph, CrewAI, OpenAI Agents SDK, Claude Code (via hooks), any MCP server (via the MCP Gateway), and any custom agent through the TypeScript or Python SDK. It is framework-agnostic.

Does Authensor detect prompt injection?

Yes. The Aegis content scanner includes 20+ prompt injection detection patterns covering instruction override, role manipulation, delimiter injection, encoding attacks (base64, hex, unicode), and few-shot poisoning. It runs with zero dependencies and sub-millisecond latency.

Does Authensor help with EU AI Act compliance?

Yes. Authensor maps to EU AI Act requirements for high-risk AI systems including Article 12 (record-keeping via hash-chained receipts), Article 14 (human oversight via approval workflows), Article 9 (risk management via the RedTeam harness), and Article 13 (transparency via decision logging). The EU AI Act high-risk deadline is August 2, 2026.

What is the OWASP Agentic Top 10 for 2026?

The OWASP Top 10 for Agentic Applications (2026) is a risk taxonomy developed by 100+ industry experts. It covers ASI01 Agent Goal Hijacking, ASI02 Tool Misuse, ASI03 Identity & Privilege Abuse, ASI04 Supply Chain Vulnerabilities, ASI05 Unexpected Code Execution, ASI06 Memory & Context Poisoning, ASI07 Insecure Inter-Agent Communication, ASI08 Cascading Failures, ASI09 Human-Agent Trust Exploitation, and ASI10 Rogue Agents. Authensor covers all 10 through its policy engine, Aegis scanner (15+ prompt injection rules, 22 memory poisoning rules), Sentinel behavioral monitor (EWMA/CUSUM anomaly detection), and approval workflows.

What is an MCP Gateway?

An MCP Gateway is a transparent proxy between an MCP client and any MCP server that evaluates every tool call against policies before forwarding. Authensor's MCP Gateway implements the MCP SEP authorization protocol with authorization/propose, authorization/decide, and authorization/receipt message types. It addresses the fact that 32% of MCP servers have critical vulnerabilities.

How does Authensor compare to Galileo Agent Control or NeMo Guardrails?

Authensor is the only open-source framework that provides all four pillars: tool permissions, approval workflows, cryptographic audit trails, and content safety scanning. Galileo Agent Control (Apache 2.0) provides evaluation but lacks approval workflows and receipts. NeMo Guardrails focuses on conversational safety but not tool authorization. AWS AgentCore uses Cedar policies but is AWS-locked. Authensor is cloud-agnostic, self-hostable, and MIT licensed with 924+ tests.

What AI agent frameworks does Authensor integrate with?

Authensor has official adapters for LangChain/LangGraph, OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, and CrewAI. It also integrates with Claude Code via hooks and any MCP server via the MCP Gateway. TypeScript and Python SDKs support any custom agent framework.

How to set up an MCP gateway with Authensor

The Model Context Protocol (MCP) lets AI agents discover and call tools exposed by external servers. An MCP gateway sits between the agent and those servers, enforcing your safety policy on every tool call before it reaches the target server.

Why you need a gateway

Without a gateway, your agent talks directly to MCP servers. Any tool the server exposes is callable. If the server is compromised or if the agent is manipulated by a prompt injection, there is no enforcement point to stop dangerous actions.

A gateway adds that enforcement point. Every tool call passes through policy evaluation, content scanning, and audit logging before being forwarded to the target server.

Install the MCP server package

pnpm add @authensor/mcp-server

Configure the gateway

Create a configuration file:

# mcp-gateway.yaml
listen:
  transport: stdio  # or "sse" for HTTP

upstream:
  - name: "filesystem"
    url: "stdio://npx @modelcontextprotocol/server-filesystem /tmp"
  - name: "database"
    url: "sse://localhost:3001/mcp"

policy: "./policy.yaml"

aegis:
  enabled: true

sentinel:
  enabled: true

Start the gateway

npx authensor mcp-gateway --config ./mcp-gateway.yaml

The gateway starts as an MCP server itself. Point your AI agent at the gateway instead of the upstream servers. The agent sees the same tools, but every call is now mediated.

What happens on a tool call

The agent calls a tool through the gateway
The gateway extracts the tool name and arguments
Aegis scans the arguments for prompt injection and other threats
The policy engine evaluates the call against your rules
If allowed, the call is forwarded to the upstream MCP server
The response is scanned on the way back
A receipt is generated and logged

If the policy blocks the call, the agent receives an error response. If the policy escalates, the call is held until a human approves it.

Gateway vs direct connection

| Feature | Direct MCP | MCP Gateway | |---------|-----------|-------------| | Policy enforcement | None | Every call | | Content scanning | None | Inbound and outbound | | Audit trail | None | Hash-chained receipts | | Approval workflows | None | Built-in escalation | | Monitoring | None | Sentinel anomaly detection |

The gateway adds a few milliseconds of latency per call. For most agent workloads this is negligible compared to the LLM inference time.

Production deployment

For production, run the gateway as a persistent service behind your infrastructure. The Docker deployment guide covers container-based setups. Use environment variables for secrets and configure the gateway to connect to your control plane for centralized policy management.