How to connect Hermes Agent to LinkedIn - safely (2026)

The steps

Connect Hermes Agent to LinkedIn in four steps

1. 1

   Create a Zevari workspace token

   Sign in to Zevari, open Settings, and create a workspace API key. This bearer token is how your Hermes Agent authenticates - no LinkedIn password, no browser cookies, no extension. Treat it like any secret and store it in your agent's environment as ZEVARI_API_KEY.

2. 2

   Register Zevari in your Hermes Agent config (MCP or REST)

   Hermes Agent supports MCP servers natively, so add Zevari to the mcp_servers block in /opt/data/config.yaml and the agent discovers all 60+ LinkedIn tools automatically. Or call the REST API directly with the bearer token from the agent's own code. The MCP path is the cleanest; the REST path is the universal one for any runtime.

   Path A - MCP server in config.yaml

   config.yaml

   # /opt/data/config.yaml - register Zevari as an MCP server
   mcp_servers:
     - name: zevari
       type: http
       url: https://mcp.zevari.ai/mcp
       auth: "Bearer ${ZEVARI_API_KEY}"

   Path B - bearer-token REST from the agent

   terminal

   $ curl https://api.zevari.ai/v1/search/posts \
     -H "Authorization: Bearer $ZEVARI_API_KEY" \
     -d '{"query":"hiring an SDR","posted_within_days":30}'

3. 3

   Verify the connection

   Confirm the agent can see Zevari before you run anything live. A read-only call - get the safety status, or search for recent signal posts - proves the token works and returns your workspace context, Voice DNA, and the enforced weekly ceilings.

   terminal

   $ curl https://api.zevari.ai/v1/safety/status \
     -H "Authorization: Bearer $ZEVARI_API_KEY"
   # -> { "connected": true, "weekly_ceiling": 150, "incidents": 0 }

4. 4

   Run your first safe loop: find, score, stage, approve

   Tell the agent what you want: find people who posted about a topic in the last 30 days, ICP-score them, draft in your voice, and stage a campaign. Every send is held at the approval gate - you approve from chat, Slack, or a daily digest, and the agent executes inside your ceilings and working hours. Nothing fires unattended, even with a persistent, self-improving loop.

   A real loop

   You: Find 15 founders who posted about hiring an SDR in the last 30 days.

   Hermes Agent: Searches signals, ICP-scores each 1 to 5 with reasons, returns 15.

   You: Draft a warm-up plus connect sequence for the 4s and 5s, in my voice.

   Hermes Agent: Drafts in your Voice DNA, stages the campaign, stops at the approval gate.

   You: Approve.

   Hermes Agent: Executes within your weekly ceiling, on a human-paced schedule.

That is the whole connection. For the broader picture of running Hermes Agent outbound safely, see the Hermes Agent page; for any other runtime, the LinkedIn for AI agents pillar; and for the full endpoint reference, the developer docs.

FAQ

Connecting Hermes Agent to LinkedIn