How do I connect Slab to my AI client?

You subscribe to the MCP on Vinkius and provide your Slab Access Token. Once connected, you can use any compatible client like Claude or Cursor to interact with your wiki.

Can my AI agent write new articles?

Yes. The MCP includes a capability to create new posts in Slab using Markdown, allowing your agent to draft and publish documentation.

The MCP uses your Slab Access Token to interact with your workspace, ensuring the agent only accesses what your token permits.

Can I organize my wiki through the AI?

Yes. You can use the MCP to create new topics or archive existing posts to manage your information architecture.

What happens if I archive a post?

Archiving a post via the MCP is an irreversible action through the API.

Can my AI use existing wiki guidelines to write new code or copy?

Absolutely. You can request your agent to 'search the Slab wiki for our Frontend Coding Standards' or 'find our Brand Voice Guidelines'. The agent will retrieve the exact Markdown content of those articles and use them as system instructions for the rest of your conversation.

How do I easily publish my AI chat output back to Slab?

When your AI agent generates a good technical specification or summary, simply tell it: 'Create a new post in Slab called [Name], using this entire response as the content, and place it in the Engineering topic.' The agent will format the Markdown and publish it immediately through the create_post capability.

Can my agent clean up outdated company documentation?

Yes. If an article is deprecated, you can tell your AI: 'Archive the post with ID XYZ' or 'Find the old setup guide and archive it.' The agent can execute the archive_post command to hide outdated information and keep your knowledge base pristine.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Slab to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Let your AI agent read and write your company wiki.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 12 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Slab.

01
List posts
This capability returns a list of all post IDs and titles within your Slab workspace.
02
Create post
Use this to create a new wiki post in Slab using Markdown content.
03
Create topic
This capability creates a new topic in Slab to help organize your posts.
04
Get post details
This capability retrieves the full content and metadata for a specific Slab post.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Slab.

05
List recent posts
Use this to get a list of the most recently updated posts in your workspace.
06
List topics
This capability lists all the topics currently organizing your Slab workspace.
07
List users
This capability retrieves a list of all registered members in your Slab organization.
08
Search posts
This capability performs a full-text search across every post in your Slab workspace.

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Slab.

09
Update post
Use this to change the title or the content of an existing Slab post.
10
Archive post
This capability archives a Slab post, which cannot be undone via the API.
11
Get organization
This capability pulls the profile information for your Slab organization.
12
Get topic details
This capability retrieves specific details and the list of posts for a given Slab topic.

Real work

What teams actually run

Technical Onboarding

An agent reads through existing technical docs to answer a new hire's questions about the codebase.

Meeting Documentation

A user dictates meeting notes to their agent, which then formats and saves them as a new Slab post.

Policy Retrieval

An employee asks their agent for the latest remote work policy, which the agent finds in Slab.

Project Planning

A manager creates a new topic for a project and starts populating it with specs drafted in chat.

Automate a task

Put Slab to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Slab works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Slab to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

916ms average. Fast in production.

Slab is checked daily against the live service.

Daily averagePeak 1060ms

Oct 3Today

Fastest day: 713ms
Slowest day: 1060ms
14-day trend: Slowing+19%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Slab, so you can see the experience inside your AI.

It does not authenticate your account with Slab. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Slab Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Slab capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "slab-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Slab in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Slab owners hand off.

This MCP is built for teams that rely on Slab as their central source of truth.

01
Software Developers
Pull API docs and architecture guidelines into an IDE without switching windows.
02
Product Managers
Draft feature specs and publish them to specific Slab topics via chat.
03
HR and Onboarding
Have an agent fetch company policies or build reading lists for new hires.

FAQ

Questions Slab owners ask.

01
How do I connect Slab to my AI client?
You subscribe to the MCP on Vinkius and provide your Slab Access Token. Once connected, you can use any compatible client like Claude or Cursor to interact with your wiki.
02
Can my AI agent write new articles?
Yes. The MCP includes a capability to create new posts in Slab using Markdown, allowing your agent to draft and publish documentation.
03
Is my data secure?
The MCP uses your Slab Access Token to interact with your workspace, ensuring the agent only accesses what your token permits.
04
Can I organize my wiki through the AI?
Yes. You can use the MCP to create new topics or archive existing posts to manage your information architecture.
05
What happens if I archive a post?
Archiving a post via the MCP is an irreversible action through the API.
06
Can my AI use existing wiki guidelines to write new code or copy?
Absolutely. You can request your agent to 'search the Slab wiki for our Frontend Coding Standards' or 'find our Brand Voice Guidelines'. The agent will retrieve the exact Markdown content of those articles and use them as system instructions for the rest of your conversation.
07
How do I easily publish my AI chat output back to Slab?
When your AI agent generates a good technical specification or summary, simply tell it: 'Create a new post in Slab called [Name], using this entire response as the content, and place it in the Engineering topic.' The agent will format the Markdown and publish it immediately through the create_post capability.
08
Can my agent clean up outdated company documentation?
Yes. If an article is deprecated, you can tell your AI: 'Archive the post with ID XYZ' or 'Find the old setup guide and archive it.' The agent can execute the archive_post command to hide outdated information and keep your knowledge base pristine.

Explore

More in Knowledge Management

Connect Slab to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

List posts

Create post

Create topic

Get post details

05-08

List recent posts

List topics

List users

Search posts

09-12

Update post

Archive post

Get organization

Get topic details

What teams actually run

Technical Onboarding

Meeting Documentation

Policy Retrieval

Project Planning

Building your own app? The connector is yours to use.

Slab Connector

Claude Desktop

Software Developers

Product Managers

HR and Onboarding

How do I connect Slab to my AI client?

Can my AI agent write new articles?

Is my data secure?

Can I organize my wiki through the AI?

What happens if I archive a post?

Can my AI use existing wiki guidelines to write new code or copy?

How do I easily publish my AI chat output back to Slab?

Can my agent clean up outdated company documentation?

Tettra AI Connector

GitScrum Knowledge AI Connector

Document360 AI Connector

Mattermost (Secure Team Collaboration) AI Connector

Suggestions

Helpjuice AI Connector

Nuclino AI Connector

Guru AI Connector

BlogIn AI Connector