openagentidentityprotocol/agentidentityprotocol
Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.
Implements authentication and authorization through cryptographically-signed Agent Authentication Tokens (AAT) that encode agent identity, user binding, and capabilities, with runtime enforcement via a transparent MCP proxy that verifies signatures, checks revocation lists, and evaluates policies before each tool call. Built in Go with Layer 1 establishing agent identities through a root registry and Layer 2 enforcing permissions via DLP scanning and audit logging at the tool-call boundary, designed to address the "god mode" problem where agents currently inherit full user credentials without distinction from human actions.
Stars
18
Forks
4
Language
—
License
Apache-2.0
Category
Last pushed
Mar 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/openagentidentityprotocol/agentidentityprotocol"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Chimera-Protocol/csl-core
Deterministic safety layer for AI agents. Z3-verified policy enforcement.
AndrewAltimit/template-repo
Agent orchestration & security template featuring MCP tool building, agent2agent workflows,...
agentralabs/agentic-contract
Policy engine for AI agents — enforceable rules, risk limits, approval gates, obligation...
behrensd/mcpwall
Deterministic security proxy for MCP tool calls — iptables for MCP
portofcontext/pctx
pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers...