AI agents & API
Let Claude, ChatGPT, Codex, Cursor and your own scripts work in your workspace with API tokens, connected apps, spend caps, approvals and webhooks.
10 articles
Understand AI agents and the APIWhat AI agents such as Claude, ChatGPT, Claude Code, Codex and Cursor can do in your Clevera workspace, the ways to connect them, plans (Pro and up), limits, roles, costs and safety.6 min readConnect Claude, ChatGPT, Codex or Cursor to CleveraAdd Clevera to Claude or ChatGPT as a custom connector with a sign-in, or set up Claude Code, Codex CLI, Cursor and other MCP clients with an API token. Server URL, setup snippets and troubleshooting.7 min readCreate an API token for an AI agentCreate an API token in the four-step wizard (Purpose, Permissions, Limits, Review): presets, permissions, expiry, doc sites, spend caps and IP allowlist. The token is shown once.7 min readUse the Clevera REST APICall Clevera from your own scripts: base URL, bearer-token authentication, endpoints and the permission each needs, the quote-then-start flow for paid work, idempotency, error format and rate limits.8 min readChoose permissions for an AI agentEvery permission an API token or connected app can hold, what it allows, which preset includes it, and which roles (owner, admin, editor, Content Creator) can grant it.6 min readManage, regenerate and revoke API tokensFind your API tokens, regenerate a secret (once, with an optional 24-hour overlap), revoke a token, understand expiry and IP allowlists, and see why a token stopped working.7 min readSet up webhooks for agent eventsGet a signed POST on your own https endpoint when an agent's job finishes or fails, an agent waits for approval, or a doc site publishes. Events, payloads, signature verification, retries and auto-disable.8 min readControl agent spending and approve requestsHow agents start paid work: quotes, spend caps per job, day and month, Approve automatically below, and approving or denying agent requests. Who decides, expiry and every refusal message.6 min readRead the AI agent activity logSee what agents did in your workspace: what they created and changed, jobs and credits, refused calls and daily reads. Columns, results, action names, filters and retention.4 min readFix AI agent and API errorsEvery message an AI agent, script or person may see with Clevera's API, MCP server and AI agents & API page, grouped by cause: tokens, plan, permissions, paid work, rate limits, conflicts and connecting apps, with the fix.10 min read