LinkedIn posts with Hermes Agent and Bolta
Draft and review social posts from Telegram, Slack or your terminal. Parts of the Hermes Agent route are not confirmed yet, and the note below says which. Nothing goes live on LinkedIn until you say yes.
Partly confirmed, see what is and is notChecked 2026-11-21
Hermes uses the generic route: a server address plus a Bolta API key.
Draft a LinkedIn post about our launch and save it for my review
Illustration of the reply: Bolta returns a draft showing the connected account and the scheduled time, with Approve, Edit and Reject actions.
What is and is not confirmed
Read this before you set up Hermes Agent
- Confirmed from the Hermes docs: Hermes reads remote MCP servers from an mcp_servers block in ~/.hermes/config.yaml, with a url and a headers map for a Bearer key. Bolta's server is https://mcp.bolta.ai/mcp and takes a key that starts with bolta_sk_.
- Not confirmed: we have not run this end to end in Hermes Agent. The OAuth option (auth: oauth) has never been tried against Bolta, so this page leads with the API key.
- Not confirmed: the skill install command against Bolta's skills repo, and the exact tool names Hermes shows for Bolta (expected to start with mcp_bolta_). If a step differs on your machine, trust what Hermes shows you.
What Bolta does on LinkedIn
Bolta writes the text, saves it as a draft on the account you name, and waits. Bolta lists each LinkedIn organization as its own account, so a company page is a separate choice from your personal profile.
- Text posts to a personal profile or to a company page you have connected.
- Posts visible to everyone by default, or to connections only if you ask for that.
LinkedIn limits and format rules
Network rules last checked 2026-07-28. Bolta's posting rules for your workspace (get-posting-rules) win if they differ from this page.
Not promised for LinkedIn from Hermes Agent: LinkedIn articles, newsletters and document carousels. LinkedIn supports them, but this page does not confirm that Bolta publishes them. Comment length limits. The one checked limit on this page is the feed post.
| What to know | LinkedIn's own rule | What Bolta does |
|---|---|---|
| Post length | A feed post is capped at 3,000 characters, counting spaces, line breaks, emoji and the full text of any link you paste. | Bolta does not check LinkedIn text length, so LinkedIn may refuse longer text. The draft has to fit before you say yes. |
| Opening lines | The feed cuts a post after the first few lines behind a see more link. | Bolta keeps your first lines as written. Put the point there. |
| Formatting | Not stated on this page. | Plain text only. Bold, italic and headings become look-alike characters, a list becomes bullets, and a link is written as label (url). #hashtags and @mentions are kept as typed. |
| Who can see it | Not stated on this page. | Everyone, unless you set the post to connections only. |
Hermes Agent jobs for LinkedIn, and how to write them
- Keep Hermes's cross-session memory for tone notes, while Bolta's voice profile keeps the actual drafts on brand
- Have Hermes check the Bolta inbox each morning and tell you what is waiting, then approve only what you pick
- Write to 3,000 characters including spaces, line breaks, emoji and any pasted link, because Bolta will not stop a post that is too long.
Example prompts for LinkedIn
Things to type in Hermes Agent. Each one asks for a draft and shows you the text first.
Draft a LinkedIn post about our launch and save it for my review
Draft a LinkedIn post about our new pricing page and leave it in Bolta for me to review.
Draft a LinkedIn post about what we learned from our last client project and show me the text before saving it
List my LinkedIn accounts in Bolta, then draft one post for the company page and a different one for my own profile
Bolta saves a draft, you read the exact text, you say yes
- 01
Bolta saves a draft
Hermes Agent asks Bolta for the LinkedIn post in your brand voice (save-post). A saved draft is never public.
- 02
You read the exact text
On LinkedIn the exact text includes where the line breaks fall, because the feed hides everything after the first few lines, and how any formatting was flattened to plain text.
- 03
You say yes
Only then does Bolta schedule or publish (publish-post), in your workspace's timezone. Safe Mode, client sign-off and brand approval rules still apply.
Using Hermes Agent for LinkedIn
Parts of this route are not confirmed. The note above says which.
For LinkedIn, Hermes Agent, from Nous Research, reaches Bolta through Remote MCP server in ~/.hermes/config.yaml. Sign-in: API key (Bearer header). OAuth is untested. The LinkedIn account itself is connected inside Bolta, not in Hermes Agent.
Hermes Agent is open source and self-hosted, reached from chat apps or the terminal, and has a built-in scheduler. A weekly LinkedIn drafting job is possible, with Bolta holding the approval step so nothing public goes out unreviewed.
This connection uses a Bolta API key, which acts as you. Safe Mode and client sign-off still apply to every LinkedIn post it saves, so keep them on.
An illustration from the Hermes Agent guide, not real output. You ask: Draft a LinkedIn post about our new pricing page and leave it in Bolta for me to review. The reply goes along these lines: I checked the LinkedIn posting rules and saved one draft in your brand voice. It is waiting in Bolta. Say yes after you read it and I will move it forward. Draft saved. Waits for your yes.
An illustration from the Hermes Agent guide, not real output. You ask: What is waiting for my approval, and how did last month's posts do? The reply goes along these lines: Three drafts are in your inbox. I read your LinkedIn account numbers for the last 30 days and can suggest a topic. I will not approve anything unless you tell me which ones. Read only. Approval stays with you.
Under mcp_servers, add bolta with url set to https://mcp.bolta.ai/mcp and a headers map holding Authorization with the value Bearer followed by your bolta_sk_ key. Save, then type /reload-mcp in a chat to pick up the edit without restarting.
Anyone who can message your Hermes bot can ask it things. Restrict who can reach it in Hermes before connecting a Bolta key with publish permission.
Hermes keeps memory across sessions, so it can remember that you prefer short openings or that a product name has a special spelling. That memory lives on your Hermes install.
- Review and approval. Hermes can list what is waiting and tell you about it. Approving, rejecting and sending for team review are separate calls you choose to allow, and a post moves only on your yes.
- Replies and inbound messages. Hermes can draft a reply to a comment or message for you to check. Sending the reply is its own step with its own yes.
- Hermes finds your workspace and accounts. Before drafting, Hermes asks Bolta which workspaces and brands this key can reach, so a post is never aimed at a brand you did not name.
- It reads how you sound. Hermes keeps its own memory across sessions, but the voice that matters for drafts is the one stored in Bolta, so it reads that before writing.
- Setup: Ask for your first draft. Try: "Draft three LinkedIn posts about our launch in our brand voice and send them to review." Open Bolta to read them. They stay drafts until you approve each one yourself.
- Setup: Check the connection. In a Hermes chat type /reload-mcp, or in a terminal run hermes mcp test bolta. You should see Bolta's tools listed. The Hermes docs name MCP tools with an mcp_ prefix and the server name, so expect names like mcp_bolta_save_post.
- MCP with an API key. The route this page leads with. The mcp_servers shape with a url and a Bearer header comes from the Hermes docs, and Bolta's server takes a bolta_sk_ key. We have not run the pair together.
- A Bolta routine runs on Bolta's side, so it keeps going when Hermes is switched off. It stays off until you separately say to activate it.
- Add Bolta to config.yaml. In Bolta, make a key at Settings, then API Keys. Under mcp_servers in ~/.hermes/config.yaml add a bolta entry with url https://mcp.bolta.ai/mcp and an Authorization Bearer header.
Connect Hermes Agent to Bolta
Hermes uses the generic route: a server address plus a Bolta API key.
LinkedIn questions, answered for Hermes Agent
- How long can a LinkedIn post be when it comes from Hermes Agent?
- A LinkedIn feed post is capped at 3,000 characters, and the count includes spaces, line breaks, emoji and the full text of any link you paste. Bolta does not check LinkedIn length, so Hermes Agent should write inside the limit and show you the final text before you say yes.
- Can Hermes Agent post to a LinkedIn company page and not only my profile?
- Bolta lists each LinkedIn organization as its own account, so you can name the page when you ask (list-accounts). The company page has to be connected in Bolta first. If it is not there, ask for a connect link (get-connect-link) and finish the sign-in in your browser.
- What is Hermes Agent, and is it the same as the Hermes models?
- Hermes Agent is an open-source agent from Nous Research that you install and run yourself. It is not the same thing as the Hermes language models, which are models, not an agent program. This page is about the agent.
- Do I need the Bolta skill as well as the MCP connection?
- No. The connection is enough to call Bolta's tools. The skill adds instructions so Hermes handles things like posting rules in the right order. We have not tested the skill install in Hermes.
- One connection covers which brands?
- A Bolta API key belongs to one organization, so it reaches the brands in that organization. Ask Hermes to list your workspaces first, and name the brand when you ask for a draft.
- Bolta tools are missing after I edited config.yaml.
- Hermes does not reread the file on its own. Type /reload-mcp in the chat, or restart Hermes, then run hermes mcp test bolta again.
- Does Hermes Agent publish LinkedIn posts without my yes?
- No. Nothing is approved, scheduled or published until you say yes to that LinkedIn post. Whether Hermes Agent completes the connection is not fully confirmed, so read the note above first.
More from Hermes Agent
Hermes Agent can work with the other networks Bolta publishes to. Each page has its own limits and review notes.
LinkedIn from other AI agents
The same LinkedIn limits apply whichever agent asks. The connection and the setup are what change.
Try a LinkedIn draft from Hermes Agent
Connect Hermes Agent, ask for a LinkedIn draft and read the exact text. Nothing goes live until you say yes.