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.

Third-Party MCP Server Vetting Checklist

Connecting a third-party MCP server to your agent infrastructure is a trust decision. The server will receive your agent's requests, process them, and return results that influence your agent's behavior. A malicious or compromised server can exfiltrate data, return manipulated results, or inject instructions into your agent's context.

Source Verification

[ ] The server's source code is publicly available
[ ] The publisher has a verifiable identity (GitHub organization, company website)
[ ] The repository has meaningful commit history (not a single bulk commit)
[ ] The project has multiple contributors or a reputable maintainer
[ ] The license is compatible with your use case

Code Review

[ ] Tool descriptions do not contain prompt injection attempts
[ ] The server does not make undisclosed network calls
[ ] The server does not log or transmit tool parameters to third parties
[ ] Dependencies are minimal and from reputable sources
[ ] No obfuscated code is present
[ ] Input validation is performed on all parameters

Security Posture

[ ] The project has a security policy or disclosure process
[ ] Known vulnerabilities in dependencies are addressed promptly
[ ] The server supports authentication for tool invocations
[ ] The transport layer supports encryption
[ ] The server does not run with elevated privileges

Operational Reliability

[ ] The server handles malformed inputs gracefully (no crashes)
[ ] Error messages do not leak internal details
[ ] The server has health check capabilities
[ ] Resource consumption is bounded (no unbounded memory or CPU usage)
[ ] The server has been tested under load

Integration Testing

[ ] All exposed tools produce expected outputs for known inputs
[ ] Tool schemas are strict and well-defined
[ ] The server responds within acceptable latency bounds
[ ] Timeout behavior is correct (requests do not hang indefinitely)
[ ] Error responses conform to the MCP specification

Ongoing Monitoring

[ ] Version updates are reviewed before deployment
[ ] A process exists to check for new vulnerabilities in dependencies
[ ] Behavioral monitoring detects changes in server response patterns
[ ] A plan exists for rapid disconnection if the server is compromised

Document your vetting findings. If the server fails any critical check, do not connect it. Place an MCP gateway between the server and your agents to enforce policies on all tool invocations regardless of server trustworthiness.