Emisar is an open-source MCP server providing a governed, zero-trust gateway for AI agents. It connects tools like Claude, Cursor, and ChatGPT to production infrastructure using a finite catalog of actions, policy enforcement, human-in-the-loop approvals, and immutable audit trails. Safe read operations run automatically while risky changes require approval. It is designed for developers and SREs who want to leverage AI agents for debugging, incident response, and operations without compromising security.
emisar sits in PulseGate's LLM eval & observability category. Safely and auditably giving AI coding agents access to production systems without exposing SSH keys, VPNs, or standing shell access. It is built as an open-source project for developers. There is a free tier. The product ships for the web and the command line, and it can be self-hosted.
Andrew Dryga builds and maintains emisar, and the product first shipped in 2026. Development happens publicly on GitHub with 535 stars and 2.4k commits in the last 90 days. Key capabilities include Zero-Trust Gateway, Policy Gates, and Human Approvals. It exposes integrations via an MCP server and a public API.
Latest indexed changes and source events
AndrewDryga/emisar verified by the PulseGate indexer
Other apps tracked under the same category.
