Editorium iconEditorium
Editorium iconEditorium
FeaturesPricingMCP
editorium.net/mcp - Agents in your newsroom
🤖 Model Context Protocol

Built for Writers and Their Agents

Editorium speaks MCP. Give Claude, ChatGPT, Grok, Cursor — or anything that speaks the Model Context Protocol — its own login to your newsroom, with a name, a role, limits you set, and a full audit trail.

Get Started FreeSee the setup steps

Already have an account? Create an agent under Settings → Agents.

What an agent can do

An agent is a teammate, not an integration. It gets its own name, its own permissions, and its own row in your audit log.

📚

Read the newsroom

Browse articles by editorial state, read full drafts, and look up the categories and tags you already use — so its work lands where it belongs.

✍️

Draft and edit

Create drafts, rewrite bodies in MDX, fix SEO descriptions, retag, and move pieces through review — all attributed to the agent, never to a person who didn't do it.

🤝

Hand work back to you

When a piece is ready, the agent marks it ready_for_publication and leaves a note explaining what it changed. You read the note and press Publish.

The endpoint

One URL, one key. The key comes from the agent you create inside Editorium.

MCP address

https://www.editorium.net/api/mcp

Auth header

Authorization: Bearer PASTE_YOUR_KEY_HERE

One-link version (for apps with no header field)

https://www.editorium.net/api/mcp?key=PASTE_YOUR_KEY_HERE

Transport

Streamable HTTP, stateless. JSON-RPC 2.0 over POST.

Protocol versions

2024-11-05, 2025-03-26, 2025-06-18

Auth

Authorization: Bearer, X-API-Key, or ?key= on the URL.

Prefer plain REST?

The same actions are available at https://www.editorium.net/api/v1/cms, described by /openapi.

Connect in four steps

No terminal required, unless you want one.

01

Create an agent

In Editorium, go to Settings → Agents and press “Add an agent”. Give it a name, like Editor in Chief. That name shows on everything it does.

02

Copy the connection details

You get an MCP address and a key. Most AIs accept the one-link version, where the key is already in the URL. The full key is shown once, but you can make a new one any time.

03

Paste it into your AI

Find your app below for the exact clicks. Then ask it: “Are you connected to my newsroom?” The agent's card in Editorium flips to “Connected” the moment it calls in.

04

Stay in control

By default the agent writes and edits, but a person presses Publish. Flip “Can publish live” on the agent's card whenever you trust it.

Exact steps for your AI

Wherever you see PASTE_YOUR_KEY_HERE, use the key Editorium shows you when you create the agent.

Claude

claude.ai or the Claude desktop app

  1. 1In Claude, open Settings → Connectors and choose “Add custom connector”.
  2. 2Name it Editorium and paste the connection link below into the URL field. Leave the OAuth fields empty.
  3. 3Start a new chat, turn the Editorium connector on, and ask: “Are you connected to my newsroom?”

Connection link

https://www.editorium.net/api/mcp?key=PASTE_YOUR_KEY_HERE

ChatGPT

Connectors or a custom GPT

  1. 1Quickest: Settings → Connectors → Create. Paste the connection link as the server URL and choose “No authentication” (the link already carries your key). This needs Developer mode turned on under Settings → Connectors → Advanced.
  2. 2Or build a custom GPT: Explore GPTs → Create → Configure → Actions → “Import from URL” and paste the API description link. Set Authentication to API Key, type Bearer, and paste the key.
  3. 3Then ask it: “Are you connected to my newsroom?”

Connection link

https://www.editorium.net/api/mcp?key=PASTE_YOUR_KEY_HERE

API description link (for custom GPT actions)

https://www.editorium.net/api/v1/cms/openapi

Grok chat

grok.com or the Grok app — everyday chat, not Grok Bot

  1. 1Go to grok.com/connectors, click New Connector, and choose Custom.
  2. 2Paste the connection link as the server URL. Leave authentication empty — the link already carries the key.
  3. 3Start a new chat, turn the Editorium connector on, and ask: “Are you connected to my newsroom?”

Connection link

https://www.editorium.net/api/mcp?key=PASTE_YOUR_KEY_HERE

Grok Bot

Named Bots in the Grok Bot app — not the same as grok.com chat

  1. 1Open Grok Bot → Settings → Plugins, then add a custom MCP server (sometimes labeled “custom connector”).
  2. 2Name it Editorium. Paste the MCP address as the server URL, then add the auth header below. If the form has no header field, paste the connection link instead — the key is already in the URL.
  3. 3Save it. Grok Bot only talks to public https:// URLs; localhost will not work because the Bot runs in the cloud.
  4. 4In a Bot chat, type @ and pick Editorium, then ask: “Are you connected to my newsroom?” Paste the job instructions into that Bot so it knows how to work.

MCP address

https://www.editorium.net/api/mcp

Auth header

Authorization: Bearer PASTE_YOUR_KEY_HERE

Connection link (if the form has no header field)

https://www.editorium.net/api/mcp?key=PASTE_YOUR_KEY_HERE

Cursor / Windsurf

Any app that takes an MCP JSON config

  1. 1Open the app's MCP settings (Cursor: Settings → MCP → “Add new global MCP server”).
  2. 2Paste the JSON below into the config file it opens, then save.
  3. 3Look for a green dot next to “editorium”, then ask the AI: “Are you connected to my newsroom?”

MCP config (JSON)

{
  "mcpServers": {
    "editorium": {
      "url": "https://www.editorium.net/api/mcp",
      "headers": {
        "Authorization": "Bearer PASTE_YOUR_KEY_HERE"
      }
    }
  }
}

Claude Code

Terminal

  1. 1Run the command below in your terminal.
  2. 2Start Claude Code and ask: “Are you connected to my newsroom?”

Command

claude mcp add --transport http editorium "https://www.editorium.net/api/mcp" --header "Authorization: Bearer PASTE_YOUR_KEY_HERE"

Other / API

Zapier, Make, n8n, custom code

  1. 1Use the API address with the key as a Bearer token. The API description link imports into most tools automatically.
  2. 2Test it with the command below — it should reply with the agent's name and permissions.

API address

https://www.editorium.net/api/v1/cms

API description (OpenAPI)

https://www.editorium.net/api/v1/cms/openapi

Test command

curl "https://www.editorium.net/api/v1/cms/me" -H "Authorization: Bearer PASTE_YOUR_KEY_HERE"

Give the agent its job

Most apps let you set standing instructions. Paste something like this so the agent knows how your newsroom works — then adjust the name and the house style to taste.

Job instructions

You are "Editor in Chief", an AI editor for our newsroom on Editorium. Start every session by calling get_helper_info to learn what you may do. Edit drafts carefully and keep the writer's voice. Leave a note on any article you change, explaining what you did and why. When a piece is ready, set its state to ready_for_publication so a person can publish it. Never publish live unless get_helper_info says you may.

The tools an agent gets

Eleven tools, all scoped to the workspace the key belongs to. Anything the agent isn't allowed to do comes back as a plain-English refusal it can act on.

  • get_helper_info

    Check the connection and see who the agent is in your newsroom: its name, role, permissions, and daily limits. Agents should call this first.

  • list_articles

    List articles, newest first, optionally filtered by editorial state. Paginated with a cursor. Archived articles stay hidden.

  • get_article

    Read one article, including its full MDX body.

  • list_categories_and_tags

    See the categories and tags your newsroom already uses, so work gets filed in the right place.

  • create_article

    Create a draft with a title, MDX body, SEO description, category, and tags. Starts as in_progress.

  • update_article

    Change an article's title, body, SEO, category, tags, or state. Edits to a published article are saved as a draft until someone publishes again.

  • publish_article

    Publish live — blocked unless you have granted that agent permission to publish.

  • unpublish_article

    Take a published article back offline.

  • delete_article

    Archive an article (soft delete) so a person can restore it later.

  • add_article_note

    Leave an editorial note for your human team. Notes appear in the article editor — this is how an agent explains what it changed or asks a question.

  • list_article_notes

    Read the editorial notes on an article, newest first.

Editorial states

in_progress

Being written.

ready_for_review

Needs an editor's eyes.

requires_review

Sent back with changes.

ready_for_publication

Approved and waiting for a person to publish.

published

Live.

unpublished

Taken offline.

You stay in control

An agent with a key is still an agent on a leash. Here is what that leash looks like.

✋

A person publishes

New agents cannot publish live. They prepare work and set it to ready_for_publication, and you press Publish. Turn publishing on per agent when you're ready.

🗂️

Archiving is off by default

Most agents only need to write, edit, and review. Archiving is a separate switch, and archived articles are recoverable anyway.

⏲️

Rate limits per agent

Each agent carries its own policy: publishes per day, edits per hour, which editorial states and categories it may touch.

📝

Everything is logged

Every create, edit, state change, publish, and note is written to your audit log under the agent's name — not a shared account.

💬

Agents talk to your team

Agents leave editorial notes on articles. The notes show up in the editor, so your writers see what changed and why.

🔌

Off in one click

Disable an agent, rotate its key, or remove it entirely. Access stops immediately, and the old key stops working right away.

Questions we get

How do I know it actually connected?

Ask your AI: “Are you connected to my newsroom?” It will call get_helper_info and tell you its name, role, and limits. In Editorium, the agent's card flips to “Connected” the moment the first call comes in.

Which plans include agents?

Free includes one agent so you can try it. Pro and BYOK add agents as an add-on, and Enterprise is unlimited.

Can an agent publish something I haven't seen?

Not unless you turn that on. New agents are created without live publishing, so the most they can do is set an article to ready_for_publication and leave you a note.

What if a key leaks?

Rotate it from the agent's card — the old key stops working immediately — or disable or remove the agent entirely. Everything the key ever did is in your audit log under that agent's name.

Does it work with a local AI on my machine?

Yes, if the app runs on your computer (Claude Code, Cursor, Windsurf). Cloud AIs like Grok Bot can only reach public https:// addresses, so a localhost Editorium won't work for them.

My client says the event stream returned 405.

That's expected. The server is stateless and never pushes notifications, so it declines the server-to-client stream. Official MCP SDKs treat that as “no stream available” and carry on.

Hire your first agent

Create a workspace, add an agent, and paste one link into the AI you already use. You keep the Publish button.

Get Started Free →Open Agent Settings
Editorium iconEditorium
HomePricingPrivacyTerms

© 2026 Editorium