Slab Connector for AI agents.
12 live capabilities
Query and manage your company wiki documentation with your agent.
Waiting for input…
Why people use Slab
Slab Wiki Search for Internal Knowledge Management
This Connector changes that by giving your agent direct access to the Slab workspace. You just ask a question in your chat and the agent does the digging for you. It pulls the exact content you need, whether it's a snippet or a full guide, and puts it right in front of you.
What Vinkius changes
Your team's wiki becomes a searchable, editable database for your AI agent.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Finding specific API endpoints
A developer asks the agent to find the auth endpoint.
- Real-world use case 02
Drafting a new PRD
A product manager asks the agent to create a new post in the 'Product Specs' topic.
- Real-world use case 03
Verifying team permissions
An admin asks the agent to list all organization members.
Complete set · 12capabilities
The complete Slab capability set.
These are the exact actions your AI can choose when you ask it to work with Slab.
01—04
4 capabilities in this set.
Part of 12 available through Slab.
- 01 Capability
Get organization
Retrieve the Slab organization profile. This provides context about your workspace's basic information.
- 02 Capability
List posts
List all wiki posts in the Slab workspace. Use this to see the full scope of your documentation.
- 03 Capability
Get post details
Retrieve the full content and metadata of a specific Slab post. This lets the agent read the entire article.
- 04 Capability
Search posts
Perform a full-text search across all Slab posts. This is the primary way to find specific information quickly.
05—08
4 capabilities in this set.
Part of 12 available through Slab.
- 05 Capability
List topics
List all topics organizing posts in the Slab workspace. Use this to understand the high-level wiki structure.
- 06 Capability
Get topic details
Get a list of all posts within a specific Slab topic. This helps the agent understand what's inside a folder.
- 07 Capability
List users
List all members of your Slab organization. This is useful for identifying team members or checking permissions.
- 08 Capability
Create post
Create a new wiki post using Markdown content. This allows your agent to draft and publish new documentation.
09—12
4 capabilities in this set.
Part of 12 available through Slab.
- 09 Capability
Update post
Update an existing Slab post title or content. This lets your agent keep your documentation current as requirements change.
- 10 Capability
Create topic
Create a new topic in Slab to organize posts. This helps the agent build out your wiki's folder structure.
- 11 Capability
Archive post
Archive an existing Slab post. Use this to keep your active wiki clean and organized.
- 12 Capability
List recent posts
List the most recently updated posts. This is perfect for seeing what's changed lately.
Set up in minutes
One URL. Then ask Slab to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Slab from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Slab, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Slab for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Slab URL.
- Step 03
Save and start
Save the connection and enable Slab in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"slab": {
"url": "https://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Slab
Open Agent mode in chat and ask: "Using Slab, help me...". 12 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"slab": {
"url": "https://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Slab
Ask Copilot: "Using Slab, help me...". 12 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"slab": {
"url": "https://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Slab
Open Cascade and ask: "Using Slab, help me...". 12 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"slab": {
"url": "https://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Slab
Ask Cline: "Using Slab, help me...". 12 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add slab --transport http "https://edge.vinkius.com/vk_preview_IfZmivQXV8XLoMGDXYhcVahnahQo9NcBqGlkU0Ik/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Slab
Ask Claude: "Using Slab, show me...". 12 tools are ready
Where the request belongs
Work Slab can move forward.
This is for the team that's tired of "where is that link?" messages. It's for the people who need to keep documentation accurate without the manual overhead of constant updates.
Software Engineer
Pulls API specs and architectural rules into the IDE while coding to avoid constant context switching.
Product Manager
Drafts feature requirements and release notes directly into the wiki from a chat conversation.
HR Coordinator
Fetches the latest company policies to help onboard new hires quickly without manual searching.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsTettra
Search, read, and create internal wiki pages on your Tettra knowledge base directly from your AI agent.
Guru
Manage enterprise knowledge cards, track collections, and search your wiki via AI agents with Guru.
Wiki.js
Manage your Wiki.js instance—create, search, and update documentation pages directly from your AI agent.
FlowUs
All-in-one knowledge management and collaboration platform. manage pages, blocks, and databases via AI.
Logseq (Knowledge Management)
Manage your knowledge base via Logseq. create pages, insert outliner blocks, and search across your local graph.
Slite
Manage your Slite knowledge base, notes, and AI insights with AI agents.
Bring your own AI
Change the model, client or framework. Keep Slab connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Slab.
The practical details behind the request, access and result.
Can the Slab MCP help my team find company policies faster?
Yes. It allows your agent to perform full-text searches across your entire Slab workspace to find specific guidelines or protocols instantly.
Can my AI agent actually write new documentation in Slab?
Yes, it can. Your agent can use the create_post capability to draft new articles or project specs in Markdown format directly into your wiki.
How does the Slab MCP organize my workspace?
It can create new topics to act as folders and even archive old posts, helping your agent keep your knowledge base structured and clean.
Can I use this to see who is currently in my Slab organization?
Yes. Your agent can list all members of your Slab organization to help you identify team members or check permissions.
Does this Connector work with my existing AI client?
It works with any MCP-compatible client, including Claude, Cursor, and Windsurf, giving your agent a direct connection to your Slab data.
Can my agent update existing Slab posts?
Yes. It can modify both the titles and the content of existing posts, making it easy to keep your documentation current as projects evolve.
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.
One connection away
Give your agent a direct line to Slab.
Connect Slab once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available