# Bring Your Own Agent: Zevari REST API and Bearer Token URL: https://docs.zevari.ai/api/connect/bring-your-own-agent > 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 . 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](https://zevari.ai/dashboard/settings): 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. - [Approval gates over the API](https://docs.zevari.ai/api/connect/approval-gates) ## Rate limits and safety Reads are generous. Writes respect server-side weekly connection ceilings (100 on Free*, 150 on Premium, 200 on Sales Navigator), working hours, and burst caps. Responses carry rate-limit headers; back off on HTTP 429. No browser cookies are ever used. The weekly figure covers connection requests sent without a note: LinkedIn caps requests that carry a note at 3 a month on a free account, and gives Premium and Sales Navigator a far larger allowance, so Premium or Sales Navigator is the practical choice for real outbound (see zevari.ai/safety). ## Framework guides - [Bring your own agent (REST + bearer)](https://docs.zevari.ai/api/connect/bring-your-own-agent): The canonical path: connect any agent to LinkedIn over the Zevari REST API with a bearer token. - [OpenClaw integration](https://docs.zevari.ai/api/connect/openclaw): Wire an OpenClaw agent to Zevari via mcp.servers in openclaw.json or the REST API. - [Hermes Agent integration](https://docs.zevari.ai/api/connect/hermes-agent): Wire a Hermes Agent to Zevari via the mcp_servers map in config.yaml or the REST API. - [Approval gates over the API](https://docs.zevari.ai/api/connect/approval-gates): How a non-Claude agent stages a write, waits for human approval, then executes. ## Docs Links - [Help Center](https://docs.zevari.ai/help): Human-facing guide to Zevari skills, workflows, agents, videos, safety, and support. - [Workflow Guide](https://docs.zevari.ai/help/workflows): LinkedIn outreach, content, prospect research, audience analysis, campaign, inbox, and GTM workflows for Claude. - [Prompting Guide](https://docs.zevari.ai/help/prompting-guide): Copy-ready prompts that require AI assistants to read the MCP reference before acting. - [Workspaces and Sender Seats](https://docs.zevari.ai/help/workspaces-and-seats): Human-facing setup guide for free workspaces, payer-account billing, members, funded LinkedIn seats, and sender associations. - [Safety Center](https://docs.zevari.ai/help/safetycenter): Human-facing guide to Zevari safety guardrails, warm-up, pauses, blocked actions, and recovery state. - [Warm-Up](https://docs.zevari.ai/help/warm-up): Human-facing guide to LinkedIn sender warm-up and gradual activity ramping. - [API Playbooks](https://docs.zevari.ai/api/playbooks): Ordered REST call flows for developers and AI agents using the Zevari API. - [MoltSets + LinkedIn Workflows](https://docs.zevari.ai/api/moltsets-linkedin-workflows): Use MoltSets verified contact data with Zevari's LinkedIn enrichment, campaign, and approval-gated execution layer. - [MCP Reference](https://docs.zevari.ai/mcp/reference): Agent-facing tool schemas, capability contracts, examples, gotchas, and recovery guidance. - [API Reference](https://docs.zevari.ai/api/reference): Public REST API reference powered by the Zevari OpenAPI document. - [MCP Reference JSON](https://api.zevari.ai/v1/mcp-reference.json): Machine-readable MCP tool reference. - [LLMs Full](https://api.zevari.ai/llms-full.txt): AI-readable Zevari documentation bundle. - [Support](mailto:issues@zevari.ai): Send bug reports, support handoffs, and feature requests.