A
licenseNot graded
qualityD
maintenanceA policy-enforcing MCP gateway that intercepts all tool calls to downstream MCP servers, applying allow/deny/ask rules with human approval and audit logging for safe access to dangerous tools.
11 npm
MIT
authensor-mcp-server
Officialby AUTHENSOR
Provides a drop-in adapter to enforce safety policies, budget limits, and tool governance for agents built with the CrewAI framework.
Offers a guardrail adapter to evaluate and authorize agent actions, tool calls, and API requests within LangChain workflows before execution.
Enables governance, policy enforcement, and audit trails for complex agentic workflows and tool interactions built using LangGraph.
Integrates with the OpenAI Agents SDK to provide content safety scanning, action authorization, and session-level threat detection.
Features built-in governance and monitoring capabilities specifically designed to provide coverage against the OWASP Agentic Top 10 security vulnerabilities.
Facilitates human-in-the-loop approval workflows for high-risk agent actions through mobile Progressive Web App notifications.
Enables real-time human approval workflows for high-consequence agent actions directly via Slack notifications and interactions.
Governs agent interactions with the Stripe API, allowing for policy enforcement on charges, spending limits, and detailed audit logging of financial actions.
Provides an adapter for the Vercel AI SDK to add a comprehensive safety layer, including policy evaluation and tamper-evident action receipts.
Authensor is a security research firm in San Francisco, founded by John Daniel Kearney. It audits the instruments the AI industry measures itself with: evaluation harnesses, benchmarks, LLM judges, leaderboards and scoring pipelines.
Every defect we report is proven with a running reproduction against the genuine code at a pinned commit, and disclosed to the maintainer first. Fixed-scope audits end in an attestation with a scope, a standard version and an expiry date.
Research
The Evaluator Trust Boundary (ETB-01 to ETB-10). An evaluator has an ETB failure when its score depends on an artifact the evaluated system can influence. The page lists dated cases with upstream fixes in SWE-bench, Promptfoo, NVIDIA garak and the UK AI Security Institute's Inspect and ControlArena. Preprint: 10.5281/zenodo.21633620.
etb-scan, an offline scanner that measures ETB-01 (injected verdicts) against your own judge. Standard library only, no API keys, MIT.
pip install etb-scan
etbscan --judge mypkg:judge --trials 10The ledger: every defect filed, every fix that landed upstream, and every target read and found sound. Includes the MLflow CVE-2026-64849 credit.
Related MCP server: evav-gateway
Work with us
Evaluation-integrity audits, and a free claim check: one published number checked against the instrument that produced it, within 48 hours.
authensor.com · john@authensor.com
The retired agent-safety toolkit
This repository first held Authensor's open-source agent-safety toolkit: the policy engine, the Aegis content scanner, the Sentinel monitor, SafeClaw and the @authensor npm packages. That product line is retired and no longer maintained. Its code and documentation stay here for reference:
Quickstart · Features · Red teaming · API reference · Deployment · Development
License
MIT.
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
- gatewayOAuthai.sealgate
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Related MCP Servers
evav-gatewayofficial
AlicenseNot gradedqualityDmaintenanceGoverned MCP gateway that lets AI agents call tools with policy enforcement, prompt-injection screening, a kill-switch, and tamper-evident signed audit logs.Apache 2.0- AlicenseNot gradedqualityBmaintenanceProvides a governance layer for MCP servers, enforcing policy-based allow/deny/approval rules, requiring human approval for risky calls, and recording an auditable trail of every AI agent tool call.MIT
- AlicenseNot gradedqualityBmaintenanceEnforces allow/deny/ask policies on MCP tool calls before they reach downstream servers, with tamper-evident audit logging.MIT