vettid/LEASH
LEASH — Lightweight Encrypted Agent Secret Handling. A proposed companion standard to MCP for secure, auditable, human-controlled secret access by AI agents.
Implements a three-tier architecture with a Connector (MCP server) mediating agent requests to vault backends over encrypted channels, ensuring secrets remain vault-resident while supporting per-request human approval workflows and cryptographically-auditable access logs. Designed as vault-agnostic protocol layer compatible with existing secrets managers (Vault, AWS Secrets Manager, 1Password) while addressing MCP's credential handling gap through action execution patterns that return results rather than exposing plaintext secrets to agent contexts.
Stars
7
Forks
1
Language
—
License
—
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/vettid/LEASH"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
quantifylabs/aegis-memory
Secure context engineering for AI agents. Content security · integrity verification · trust...
kahalewai/dual-auth
Dual-Auth provides AGBAC dual-subject Authorization for AI Agents and Humans using existing IAM...
The-17/agentsecrets
Zero-knowledge secrets infrastructure built for AI agents to operate, not just consume.
lelu-auth/lelu
The authorization layer for AI Agents
onecli/onecli
Open-source credential vault, give your AI agents access to services without exposing keys.