Accordly

Planned

Infrastructure for AI agents. Planned

Planned: an Accordly MCP layer that gives AI agents permission-scoped access to BookingHash and LedgerHash through the same Accordly API, with every action landing in the engines' hash-chained records.

How the planned agent layer would work

Planned

Planned. The MCP layer is not available and no release date is published.

Why a system of record matters for agents

  • An agent needs a fact it cannot quietly corrupt

    If an agent places a hold or posts an entry, the fact should be sealed the same way as a human action, and verifiable the same way.

  • Scope, not trust

    Access is planned to be permission-scoped through the Accordly API. An agent should only be able to do what its scope allows.

  • Deterministic answers

    Verification returns a recomputed result, not a confidence score. That is what an agent, or its operator, can act on.

What exists today

  • The engines' HTTP APIs with tenant-scoped keys (sandbox on staging).
  • Hash-chained records and verification endpoints in both engines.
  • The Portal, where sandboxes are created and the production waitlist lives.

What is planned Planned

  • An Accordly MCP layer exposing engine operations to AI agents.
  • Permission scopes per agent, applied through the same Accordly API.
  • Every agent action landing in the engines' hash-chained records with a hash reference in the response.

The MCP layer is planned. No release date is published, and nothing on this page is available to use today.

Start with a sandbox. Move to production when you are ready.

Sign up in the Portal, create an organisation, open a sandbox. When you need production, join the waitlist.

Start a free sandbox Join the production waitlist

Sandboxes run on staging with test data. Production access is by waitlist.