Capacities Connector for AI agents.
10 live capabilities
Connect your personal knowledge graph to your AI client for structured note-taking.
Waiting for input…
Why people use Capacities
Capacities for Fixing Manual Research Logs
With this Connector, that friction disappears. You can just tell your AI client to save a link or a thought, and it handles the heavy lifting of finding the right space and creating the object. You get a clean, organized graph without the manual data entry.
What Vinkius changes
It turns your personal knowledge base into a live, editable database for your AI.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Capturing research sources
A researcher finds a great article and asks their agent to "Save this link to my Biology space.
- Real-world use case 02
Meeting preparation
A manager asks their agent to "Find my notes on Project X and summarize the last three updates.
- Real-world use case 03
Structured documentation
A developer asks their agent to "Create a new System Architecture object with these specs.
Complete set · 10capabilities
The complete Capacities capability set.
These are the exact actions your AI can choose when you ask it to work with Capacities.
01—04
4 capabilities in this set.
Part of 10 available through Capacities.
- 01 Capability
Get structures
View the metadata and definitions for every object type in a space. This ensures the agent knows the rules for creating new entries.
- 02 Capability
Lookup
Search for specific content or keywords within a single space. It helps you find specific nodes in your graph quickly.
- 03 Capability
Save weblink
Add a URL as a Weblink object with automatic previews. This is perfect for quickly saving research sources.
- 04 Capability
Save to daily note
Add Markdown text to your mapped daily note for quick logging. Use this to dump thoughts or summaries into your daily log.
05—07
3 capabilities in this set.
Part of 10 available through Capacities.
- 05 Capability
Get space info
Get the details of a space, including its specific object types and properties. Use this to see how your data is structured.
- 06 Capability
List spaces
See all your top-level containers in Capacities. This helps your agent understand the high-level organization of your data.
- 07 Capability
Create object
Make a new typed object that fits your specific graph rules. This allows the agent to build new entities in your workspace.
08—10
3 capabilities in this set.
Part of 10 available through Capacities.
- 08 Capability
Get object
Pull the full data for a specific object using its ID. Use this to let your agent read the full context of a specific note.
- 09 Capability
Save media
Attach an image or media file to an existing record. This helps keep your knowledge graph visually organized.
- 10 Capability
Add tag
Apply a categorical tag to group your graph items together. This keeps your related content linked and easy to find.
Set up in minutes
One URL. Then ask Capacities to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Capacities 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_ZID8SH13sQKM0vE5SjxHLtpxSSu31LjQiFG07vWF/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 Capacities, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Capacities for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_ZID8SH13sQKM0vE5SjxHLtpxSSu31LjQiFG07vWF/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 Capacities URL.
- Step 03
Save and start
Save the connection and enable Capacities in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"capacities": {
"url": "https://edge.vinkius.com/vk_preview_ZID8SH13sQKM0vE5SjxHLtpxSSu31LjQiFG07vWF/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 Capacities
Open Agent mode in chat and ask: "Using Capacities, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"capacities": {
"url": "https://edge.vinkius.com/vk_preview_ZID8SH13sQKM0vE5SjxHLtpxSSu31LjQiFG07vWF/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 Capacities
Ask Copilot: "Using Capacities, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"capacities": {
"url": "https://edge.vinkius.com/vk_preview_ZID8SH13sQKM0vE5SjxHLtpxSSu31LjQiFG07vWF/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 Capacities
Open Cascade and ask: "Using Capacities, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"capacities": {
"url": "https://edge.vinkius.com/vk_preview_ZID8SH13sQKM0vE5SjxHLtpxSSu31LjQiFG07vWF/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 Capacities
Ask Cline: "Using Capacities, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add capacities --transport http "https://edge.vinkius.com/vk_preview_ZID8SH13sQKM0vE5SjxHLtpxSSu31LjQiFG07vWF/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 Capacities
Ask Claude: "Using Capacities, show me...". 10 tools are ready
Where the request belongs
Work Capacities can move forward.
This is for anyone who manages a massive amount of personal information and wants an AI that can actually help them organize it, rather than just chatting about it.
Researcher
They use this to instantly capture web links and research notes into a structured graph without leaving their browser.
Knowledge Worker
They use this to query their own past notes to prep for meetings or find specific project details quickly.
Developer
They use this to have their AI assistant document system architectures as structured Markdown objects automatically.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsMem AI (Knowledge Workspace)
Manage your knowledge base via Mem.ai. create notes, run AI semantic search, and organize collections.
Reflect
Equip your AI to read, write, and explore your networked thought graph in Reflect Notes securely via their API.
Logseq (Knowledge Management)
Manage your knowledge base via Logseq. create pages, insert outliner blocks, and search across your local graph.
Amplenote
Connect your Amplenote workspace to your AI agent. search notes, manage tasks, and organize ideas via natural language.
Memo Meister
Create and organize smart notes with AI-powered tagging, search, and knowledge connections that make your ideas retrievable.
OneNote
Connect your AI agent to Microsoft OneNote to search, read, extract, and append content to your personal or enterprise notebooks seamlessly.
Bring your own AI
Change the model, client or framework. Keep Capacities 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 Capacities.
The practical details behind the request, access and result.
How does the Capacities MCP help with my personal knowledge management?
It connects your Capacities workspace to your AI client so you can manage your notes using natural language. You can ask your agent to find, create, or update objects without manually clicking through your folders.
Can the Capacities MCP automatically organize my research links?
Yes, it can. You can tell your agent to save URLs as Weblink objects, and it will handle the injection into your specific spaces while generating previews automatically.
Will the Capacities MCP mess up my existing note structures?
No, it's designed to follow your rules. The agent can check your object structures first to ensure every new entry it creates matches your predefined graph parameters.
Can I use the Capacities MCP to search my old notes for specific info?
Absolutely. You can ask your agent to look up specific keywords or titles across your spaces to find old notes, meeting summaries, or project details instantly.
Does the Capacities MCP support adding images to my notes?
Yes, it can attach media payloads to your existing records. This allows your AI agent to help you build a more visually rich and complete knowledge graph.
Is the Capacities MCP good for daily journaling?
It's great for that. You can have your agent append summaries, thoughts, or even code snippets directly into your daily note log as you work through your day.
Can my AI agent automatically funnel research links into my Capacities daily note?
Yes. It can append raw Markdown to your Daily Note dynamically, or use the dedicated WebLink endpoint to natively scrape and save beautifully previewed URLs into your specified space. This gives you a fast workflow for daily link-hoarding right from your chat capabilities.
Will the agent know the specific object structures configured in my custom Capacities space?
Absolutely. Before creating nodes, your agent pulls constraints using the get_structures capability. It reads the schemas, understands which properties are locked or required (e.g., Dates vs Checkboxes), and constructs the new object JSON mapping perfectly inside the space.
Is the agent capable of categorizing objects with new tags automatically?
Yes. Once an object is created or fetched via lookup, the AI can employ the tag modification capability to link categorical boundaries accurately. It's a frictionless way to organize hundreds of loosely coupled notes into connected knowledge topics without any manual toggles.
One connection away
Give your agent a direct line to Capacities.
Connect Capacities once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available