Sign inStart free
AppsPlatformMarketplaceDocsPricingSign in
Documentation

Agents

obop treats AI agents as first-class users that are limited on purpose. This page explains the model; the next pages show how to set one up.

The agent model ​

An agent is anything that acts on obop with an agent token: an MCP client such as Claude Desktop or Cursor, a script that calls the REST API, or the command line. Agents work on the same records and through the same commands as people. Four rules make that safe.

  1. Scoped. An agent token carries a list of permission groups (its scopes). It can only narrow what its owner may do, never widen it. Asking for a group the owner does not hold is refused.
  2. Masked. Personal data comes back as stable placeholder tokens such as EMAIL_1. Financial, HR and special-category fields are withheld. An agent can still reason about records and pass tokens back, but it never sees the real values. See Masking tokens.
  3. Propose, don't commit. An agent can run ordinary actions within its scopes, but for anything irreversible (posting an invoice, paying, refunding, sending, publishing, deleting) it can only propose. The server returns a plan id and changes nothing. A person approves. See The approval loop.
  4. Same door. REST, MCP and the CLI go through one dispatcher, so an agent has exactly the same permissions, masking and approvals whichever way it connects.

Three ways to connect ​

SurfaceUse it whenPage
MCP over stdioAn MCP client (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and others) should call obop as tools.Connect over MCP
RESTA script or service calls HTTP endpoints.Use the REST API
CLIA shell or a cron job calls obop call.Use the CLI

Set-up in five steps ​

  1. Decide what the agent should do, and which groups that needs. Less is better.
  2. Create an agent token with only those scopes.
  3. Connect the agent over MCP, REST or the CLI.
  4. Try a harmless read, then a change that needs approval, and approve it as a person.
  5. Read Safety best practices before you give the token to anything unattended.

What exists today, and what does not ​

  • Built: scoped tokens, masking and restore, approval plans, MCP over stdio, REST and the CLI.
  • Not built yet: an HTTP (remote) MCP transport with OAuth, so hosted instances cannot yet be reached over MCP; a screen for creating or revoking agent tokens; a list of pending approvals in the interface. Agent tokens do not expire and there is no revoke command yet. These are called out again where they matter.

See Example workflows for prompts and flows to start from, and Troubleshooting when something does not work.