
Microsoft toolkit for policy enforcement, identity and audit of autonomous agents
- Open source
- Open-source agent
- 6.6K GitHub stars
- Security

Microsoft toolkit for policy enforcement, identity and audit of autonomous agents
Postgres gateway for AI agents with table grants, column masking and approval for writes
Runs locallyEncrypted vault for .env files with scoped, audited MCP access for coding agents
Read-only audit of agent skills in one workspace, plus a package manager for them
Runs locallyPassive audit that checks whether an MCP endpoint exposes its tools without authentication
Runs locallyA lockfile for MCP tools: blocks changed tool definitions and signs a receipt per call
Runs locallyScore a domain's DNS, email authentication and TLS posture, with fixes
Browser actions for AI agents that are classified, approved and logged
Runs locallyRead-only Trino access for agents, run as the verified user so Trino policy decides
Runs locallyOpen-source MCP gateway that pins tools, holds risky calls and limits egress
Runs locally
Open-source control plane that firewalls MCP tool calls and caps agent model spend
Policy-gated agent spending with signed receipts and audit against the payment rail
Runs locallySealed microVM sandboxes for agents to run untrusted code, locally or in the cloud
Not checked yetOne call to verify agent output, price its resource use and enforce spending mandates
Not checked yet
Offline AI-law rule checks for the EU AI Act, NYC LL 144, GDPR and HIPAA
Runs locallyRecord AI agent actions as hash-only, tamper-evident audit evidence
Runs locallyOpen-source scheduler that runs coding agents in parallel under policy-as-code rules
Runs locallyGrade your installed MCP servers A to D from public signals, with safer alternatives
Runs locallyGuard that checks MCP tool calls against a passkey-signed permission and logs receipts
Runs locallyAudit remote MCP servers for OAuth 2.1 gaps, and generate tested connectors
Runs locally
Hash and sign evidence of what AI agents did, mapped to AI governance frameworks
Runs locally
Action catalog and approval policy that let agents run server tasks without SSH
Not checked yetProxmox VE access across many clusters, with deletes held behind plan, approve and apply
Runs locallyRegistry that records who authorised an AI agent, within what limits and until when
Runs locallyRust MCP server for the Juniper Mist cloud with scoped tokens and two-person changes
Runs locallyRust MCP server for UniFi controllers with scoped tools and two-person change control
Runs locallyRun MCP servers with a scoped environment, audit trail and discovery from registries
Runs locallyMCP server giving agents a signed identity and hash-anchored settlements on Midnight
Runs locallyOperate Proxmox through an AI agent with planned changes, receipts and undo
Runs locallyOffline MCP scanner that inventories quantum-vulnerable cryptography in a code repository
Runs locally