About this integration
Guardian layer for AI agents: identity, secrets, audit via MCP.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.0
- Package
- haldir
- Last compatibility test
- Not independently tested
Connect your agent
haldirPublisher documentation and executable manifest were reviewed from hash-pinned captures. The package, integration endpoint, and runtime were not executed or independently security-audited.
Capabilities: agent governance, scoped sessions, secret vault, spend controls, audit trail
Connected profiles
Additional details
io.github.ExposureGuard/haldir
Source ↗ · Checked 2026-09-170.1.0
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17haldir
Source ↗ · Checked 2026-09-190.3.0
Source ↗ · Checked 2026-09-19The publisher documents a client-managed `haldir-mcp` console command; no hosted-service request was made.
Source ↗ · Checked 2026-09-19HALDIR_API_KEY is supplied to the local MCP process for access to the hosted Haldir service.
Source ↗ · Checked 2026-09-19The documented client configuration starts `haldir-mcp` with HALDIR_API_KEY in the environment.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19