Manage cryptographically signed departure and admission records for AI agents using Ed25519 or P-256 signatures. Built for developers who need verifiable audit trails and secure agent lifecycle tracking.
io.github.hawthornhollows/passage-protocol
Local install
STDIO
No auth required
How models use it and what it is built for.
Manage cryptographically signed departure and admission records for AI agents using Ed25519 or P-256 signatures. Built for developers who need verifiable audit trails and secure agent lifecycle tracking.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Hawthornhollows Passage Protocol.
Paste any of these into Agent Studio after connecting Hawthornhollows Passage Protocol.
Common questions about connecting and running Hawthornhollows Passage Protocol.
What signature algorithms does this server support?
The Passage Protocol supports Ed25519 and P-256 (ECDSA) signatures for cryptographic verification of departure and admission records. Both are industry-standard algorithms suitable for agent authentication and audit logging.
How do I install and run this MCP server?
Install via npm with `npx @cellar-door/mcp-server@0.1.7`. The server communicates over stdio transport, so configure your MCP client to spawn the process and pipe messages through standard input/output.
What are departure and admission records used for?
Departure records log when an AI agent leaves or completes a task; admission records log when an agent enters or starts a session. Together they create a verifiable, signed audit trail of agent lifecycle events.
Can I query records by time range or agent identity?
The registry metadata indicates support for querying departure and admission records, though specific query parameters should be confirmed in the server's API documentation or by testing with your MCP client.
Is this server suitable for compliance and audit requirements?
Yes—cryptographic signatures (Ed25519/P-256) and structured record-keeping make this suitable for compliance scenarios where you need non-repudiation and verifiable agent activity logs.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams