API Overview - Zevari Docs

One engine, two front doors

Zevari is reachable over MCP (for in-agent use - Claude, Codex, ChatGPT) and over a REST API (for your own backend, cron, or non-MCP runtimes). Same capabilities and the same approval gate on both. Base URL https://api.zevari.ai; methods at /v1/...

Authentication

Create a key in the Zevari app. Keys start zvr_api_ and authenticate with Authorization: Bearer <key>. A key binds one workspace and one sender. Keys are not scoped (there are no read-only keys today). Store keys in a secret manager.

Environments

There is no sandbox or test mode. Writes act on production LinkedIn, behind the approval gate. Test with low volume and the approval queue.

Verbs

Endpoints use endpoint-specific verbs: GET for reads, PATCH for updates, DELETE for deletes, POST for actions and creates. Not all-POST.

Errors

Errors use a stable envelope: { error: { code, message, docs_url, suggested_action } }.

Rate limits

600 requests per key per hour; exceeding it returns HTTP 429 with error code rate_limited. There are no Retry-After or X-RateLimit headers, so back off on a fixed schedule.

Pagination

Entity list endpoints use offset/limit; LinkedIn search endpoints use an opaque cursor.

Idempotency

Idempotency keys are not supported. For approval-gated writes, the safe-retry mechanism is re-calling with the same confirmation_id.

Approvals

LinkedIn and other sensitive writes are approval-gated. See the Approvals contract.

• Approvals

Where next

• REST API Reference
• MCP Reference
• API Playbooks
• Help Center

  Human-facing guide to Zevari skills, workflows, agents, videos, safety, and support.

• Workflow Guide

  LinkedIn outreach, content, prospect research, audience analysis, campaign, inbox, and GTM workflows for Claude.

• Prompting Guide

  Copy-ready prompts that require AI assistants to read the MCP reference before acting.

• Workspaces and Sender Seats

  Human-facing setup guide for workspaces, members, billing, add-on LinkedIn sender seats, and teammate LinkedIn connections.

• Safety Center

  Human-facing guide to Zevari safety guardrails, warm-up, pauses, blocked actions, and recovery state.

• Warm-Up

  Human-facing guide to LinkedIn sender warm-up and gradual activity ramping.

• API Playbooks

  Ordered REST call flows for developers and AI agents using the Zevari API.

• MoltSets + LinkedIn Workflows

  Use MoltSets verified contact data with Zevari's LinkedIn enrichment, campaign, and approval-gated execution layer.

• MCP Reference

  Agent-facing tool schemas, capability contracts, examples, gotchas, and recovery guidance.

• API Reference

  Public REST API reference powered by the Zevari OpenAPI document.

• MCP Reference JSON

  Machine-readable MCP tool reference.

• LLMs Full

  AI-readable Zevari documentation bundle.

• Support

  Send bug reports, support handoffs, and feature requests.