Bring Your Own Agent: Zevari REST API and Bearer Token
Connect any AI agent, cron job, or script to LinkedIn over Zevari's REST API: create a bearer token, call the core endpoints, and stage every write behind the approval gate.
What this is
The universal path for any self-hosted runtime, scheduled runner, or custom script to drive LinkedIn through Zevari over plain HTTP with a bearer token. It is the same engine and the same approval gate as the MCP connection, exposed as a REST API at https://api.zevari.ai. Agents that speak MCP can connect that way instead; everything else uses this.
Create a workspace token
Create API keys in the Zevari app at Dashboard Settings - API Keys. Keys start with zvr_api_ and authenticate requests with Authorization: Bearer <key>. The key fixes the active workspace and LinkedIn sender, so you never pass cross-workspace IDs. Store it in a secret manager or environment variable; keep it out of prompts, client code, logs, and committed files.
- Create API key
Open Zevari settings and use the API Keys section.
Core endpoints
An agent uses five call families: search (find signal posts and people), score (ICP-score a prospect), draft (voice-matched copy), campaign (create and advance sequences), and approve (the confirmation flow). All calls are JSON over HTTPS against https://api.zevari.ai with the bearer header. See the API Reference for exact schemas and the API Playbooks for call order.
The approval-gate handshake
For any LinkedIn write, first stage an approval with confirmations.requestAction using the action_type that matches the write you intend. A human approves out of band (chat, Slack, a daily digest, or an approval endpoint), then you execute the write referencing the approved confirmation. A self-hosted bot cannot send unattended. Full detail on the dedicated approval-gates page.
Rate limits and safety
Reads are generous. Writes respect server-side weekly connection ceilings (Free 40, Premium 80, Sales Navigator 150), working hours, and burst caps. Responses carry rate-limit headers; back off on HTTP 429. No browser cookies are ever used.
Framework guides
- Bring your own agent (REST + bearer)
The canonical path: connect any agent to LinkedIn over the Zevari REST API with a bearer token.
- OpenClaw integration
Wire an OpenClaw agent to Zevari via the SOUL.md MCP stanza or the REST API.
- Hermes Agent integration
Wire a Hermes Agent to Zevari via the config.yaml MCP stanza or the REST API.
- Approval gates over the API
How a non-Claude agent stages a write, waits for human approval, then executes.
Docs Links
- 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.
- 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.