Cover Image for Hashnode MCP server: manage your blog from Claude, ChatGPT, and Cursor

Hashnode MCP server: manage your blog from Claude, ChatGPT, and Cursor

Connect once with your Hashnode login. Publish, draft, edit, search, and upload images without leaving your chat.

Ipseeta PriyadarshiniIpseeta Priyadarshini4 min read

What is the Hashnode MCP server?

The Hashnode MCP server lets Claude, ChatGPT, Cursor, and other AI clients publish, draft, edit, search, and delete posts on your Hashnode blog. Add one URL, log in with your Hashnode account, and you're connected. No API token, nothing to install.

https://mcp.hashnode.com/mcp

How to connect

In Claude Code, run one command:

claude mcp add --transport http hashnode-mcp https://mcp.hashnode.com/mcp

Your browser opens Hashnode. Log in and approve access. That's it.

In Cursor, add the URL to your mcp.json:

{
  "mcpServers": {
    "hashnode": {
      "url": "https://mcp.hashnode.com/mcp"
    }
  }
}

In ChatGPT and other clients, paste the same URL wherever the client asks for a remote MCP server.


What your agent can do

Ask in plain language. "Publish notes.md to my blog." "Save notes.md as a draft." "Submit it for review." "Find my posts about Postgres and fix the tags." "Use cover.png as the cover image." "Credit Priya as the author." Your agent picks the right tool.

There are 32:

ToolWhat it does
create_postPublish a new post
update_postEdit an existing post
delete_postDelete a post
create_draftSave a new draft without publishing
update_draftEdit a draft
get_draftRead a draft
list_draftsList your drafts in a publication
publish_draftPublish a draft as a post
delete_draftDelete a draft
submit_draft_for_reviewSubmit your draft to the owner and admins for review
reject_draft_submissionSend a submitted draft back to its author
list_submitted_draftsSee drafts waiting for review
list_all_drafts, list_scheduled_drafts, list_all_scheduled_draftsSee everyone's drafts, or the ones scheduled for later
get_post, get_post_by_slugRead a post by id or by slug
list_postsList your publication's posts
search_postsSearch your publication's posts
list_series, get_seriesBrowse your series
list_membersSee who's on your publication
list_publications, get_publicationFind the publications you own and read their details
list_static_pagesRead a publication's static pages
list_comments, top_commentersRead a post's comments, or see who comments most
create_image_upload_url, confirm_image_uploadUpload a local image
whoami, get_user, get_tagLook up yourself, another user, or a tag

You stay in control

You never handle a token. Every client you connect shows up in Developer Settings, and you can disconnect any of them at any time. Access stops immediately.


MCP server or agent skill?

If you work in a coding agent and want the whole GraphQL API, use the GraphQL skill. If you work in a chat client, or you'd rather not manage a token, use the MCP server. Both follow the same Pro rules, and you can use both.


Before you publish

  • Posts go live immediately. To look first, ask your agent to save a draft, then publish it when you're ready.

  • Contributors can't publish directly. Ask your agent to submit your draft for review, and an owner or admin publishes it.

  • Deleting a post removes it from your blog, and the API can't bring it back. Only the author or a publication admin can delete.


What you need

  • A Hashnode account

  • A publication on Hashnode Pro

  • An MCP client that supports remote servers


FAQ

Is the Hashnode MCP server free?

Connecting is free. Your publication needs Hashnode Pro.

Do I need an API token?

No. You log in with your Hashnode account.

Which clients does it work with?

Any client that supports remote MCP servers, including Claude Code, Cursor, and ChatGPT.

How do I disconnect a client?

Open Developer Settings and remove it from your connected apps.


The launch note is in the changelog.

Written by

Software Developer @Bug0 | @Hashnode, Contributing writer to The Foreword by Hashnode

More from The foreword

Comments (1)

Leave a comment
  1. BotSailor
    BotSailorBuilding the infrastructure for omnichannel automation. Insights on APIs, webhooks, and scaling AI-driven customer journeys.

    This is a really interesting step for AI-assisted content workflows. I like that the MCP server isn’t just about publishing posts—it can handle drafts, editing, searching, comments, images, and even review workflows through natural language.

    The fact that authentication happens through the Hashnode login instead of making developers manage API tokens is a nice touch too. It makes the whole experience feel much more approachable.

    I especially appreciate the reminder to use drafts before publishing. Giving the agent powerful tools is great, but keeping that final human checkpoint is what makes the workflow feel practical and trustworthy. Excited to see where this kind of MCP integration goes next!