Yes — Hermes Agent can verify email addresses and turn the clean ones into a campaign in WarmySender, all in plain language, through the same 78-tool connection Claude, ChatGPT, Cursor, Codex, OpenClaw, and Hermes Agent share. You ask in Hermes Agent’s chat, configured from ~/.hermes/config.yaml. It never sends a message itself and can never raise a limit: it writes the campaign and hands it to WarmySender’s scheduler, which paces every email, LinkedIn, Instagram and WhatsApp action inside safe limits no matter who is driving. Connecting and disconnecting accounts stays in the app.
Hermes Agent is configured from a file, and you talk to it in its own chat once the WarmySender block is loaded. It connects through a short block in ~/.hermes/config.yaml; run /reload-mcp in the chat and sign in when prompted. Verification via Hermes Agent suits repeatable list hygiene: with the config block loaded, submitting a list, following the batch and turning the safe addresses into a prospect list is a short exchange in the chat. Same allowance, same pacing as the app.
Every "can" below stands on a real tool in the WarmySender connection. Every "cannot" is not a setting — there is simply nothing an agent can call that does it.
| Can / cannot | What that means for email verification |
|---|---|
| Can | Check a single address on the spot — safe to send to, risky, or not deliverable. |
| Can | Submit a whole list and follow the results as they come in. |
| Can | Check how much of your allowance is left before committing a big list. |
| Can | Stop a batch that is still running. |
| Can | Turn the confirmed addresses into a prospect list, ready to enroll. |
| Can | Build and start the campaign around the clean list in the same conversation. |
| Cannot | Send to anyone — building the campaign only hands it to WarmySender’s scheduler. |
| Cannot | Verify faster than the app or raise your allowance — it shares the same monthly allowance and pacing. |
| Cannot | Buy credits — anything touching billing stays with you in the app. |
| Cannot | Find an address you do not have — verification confirms addresses, it does not discover them. |
| Cannot | Connect or disconnect a mailbox. |
Hermes Agent reads a short block in its config file, reloads, and signs in — after that, every WarmySender tool is one sentence away.
Add this to ~/.hermes/config.yaml, then run /reload-mcp in the chat and sign in when prompted.
File: ~/.hermes/config.yaml
mcp_servers:
warmysender:
url: "https://warmysender.com/mcp"
auth: oauthPrefer a key? Create one under Settings › API Keys and choose exactly which permissions it carries, including read-only. With a key, the Hermes Agent route is: Add this to ~/.hermes/config.yaml, then run /reload-mcp in the chat.
Both routes reach the same workspace and stay inside the same safe limits. Every agent's steps live on the AI Agents hub.
How much verification allowance do I have left this month?
Verify this list of 800 addresses and tell me when it is done.
Make a list of the addresses that came back safe to send, then build a campaign around them.
Stop the batch I started an hour ago.
Verify the addresses below, tell me when the batch finishes, and turn the safe ones into a prospect list.
Hermes Agent never sends a message itself and can never raise a limit. Creating or launching a campaign only writes it and hands it to WarmySender's scheduler, which paces every email, LinkedIn, Instagram and WhatsApp action inside safe limits and a gradual ramp — the same protections that apply when a human clicks the buttons. Connecting and disconnecting accounts stays in the app. Account safety always wins.
Yes. Connect Hermes Agent to WarmySender and ask in plain language, in Hermes Agent’s chat, configured from ~/.hermes/config.yaml — it can verify email addresses and turn the clean ones into a campaign. It never sends a message itself and can never raise a limit: it writes the campaign and hands it to WarmySender’s scheduler, which paces every email, LinkedIn, Instagram and WhatsApp action inside safe limits no matter who is driving. Connecting and disconnecting accounts stays in the app.
Hermes Agent reads a short block in its config file, reloads, and signs in — after that, every WarmySender tool is one sentence away. Add this to ~/.hermes/config.yaml, then run /reload-mcp in the chat and sign in when prompted. The block for ~/.hermes/config.yaml is: mcp_servers: warmysender: url: "https://warmysender.com/mcp" auth: oauth — the server address is https://warmysender.com/mcp. The steps are on this page under "Connect Hermes Agent", and the full install hub for every agent is at /ai-agents.
No. Nothing an agent can call moves a limit — not your monthly verification allowance or the pace at which a batch is checked. Hermes Agent can read where you are against a limit and tell you when a pause lifts; WarmySender’s scheduler decides what actually goes out.
No. Connecting and disconnecting accounts stays in the app on purpose — a credential should never pass through an agent or a chat log. Connect the mailbox once in WarmySender; after that Hermes Agent can use it.
Exactly as in the app: the agent shares the same monthly allowance and credits and cannot verify any faster. You are only charged for answers — one credit per confirmed result, nothing for one that cannot be confirmed either way — and credits never expire.
Under mcp_servers in ~/.hermes/config.yaml, exactly as shown on this page, with the address https://warmysender.com/mcp. Then run /reload-mcp in the chat and sign in when prompted — no restart needed.
Run /reload-mcp in the chat: Hermes Agent reads the file on reload, not on save. Then check the indentation of the block (the file is whitespace-sensitive) and that the address reads exactly https://warmysender.com/mcp.
Yes. Create a key under Settings › API Keys and use the key form of the block on the AI Agents hub; the sign-in form on this page is the one that stores no key in the file.
Last updated: 2026-09-09