Markdown Semantic Chunker Connector for AI agents.
3 live capabilities
Preserve document hierarchy during markdown chunking for RAG.
Waiting for input…
Why people use Markdown Semantic Chunker
Stop broken context with Markdown Semantic Chunker parsing
This Connector changes the workflow entirely. Instead of fighting with broken text fragments, you get chunks that are logically grouped by their original structure. You end up with much cleaner retrieval and far fewer hallucinations.
What Vinkius changes
You get cleaner, more context-aware data for your retrieval pipelines.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Broken context in RAG
You ask your agent about a specific setup step, but it can't find the answer because the splitter cut the header from the instructions.
- Real-world use case 02
Large documentation parsing
You have massive markdown files that overwhelm your context window.
- Real-world use case 03
Analyzing document structure
You need to understand how a complex manual is organized.
Complete set · 3capabilities
The complete Markdown Semantic Chunker capability set.
These are the exact actions your AI can choose when you ask it to work with Markdown Semantic Chunker.
01—03
3 capabilities in this set.
Part of 3 available through Markdown Semantic Chunker.
- 01 Capability
Generate semantic chunks
Creates structured text segments by following your markdown headers and paragraphs. It ensures every chunk stays semantically intact.
- 02 Capability
Get header structure
Extracts the full hierarchy of headers from your document. This lets you preview the outline before processing.
- 03 Capability
Calculate markdown token density
Measures how many tokens are packed into your markdown content. Use this to monitor text density across segments.
Set up in minutes
One URL. Then ask Markdown Semantic Chunker to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Markdown Semantic Chunker 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_7rlgv7c4pKsFI7OUQzClGBELy5KOHUclBVDqK0KP/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 Markdown Semantic Chunker, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Markdown Semantic Chunker for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_7rlgv7c4pKsFI7OUQzClGBELy5KOHUclBVDqK0KP/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 Markdown Semantic Chunker URL.
- Step 03
Save and start
Save the connection and enable Markdown Semantic Chunker in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"markdown-semantic-chunker": {
"url": "https://edge.vinkius.com/vk_preview_7rlgv7c4pKsFI7OUQzClGBELy5KOHUclBVDqK0KP/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 Markdown Semantic Chunker
Open Agent mode in chat and ask: "Using Markdown Semantic Chunker, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"markdown-semantic-chunker": {
"url": "https://edge.vinkius.com/vk_preview_7rlgv7c4pKsFI7OUQzClGBELy5KOHUclBVDqK0KP/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 Markdown Semantic Chunker
Ask Copilot: "Using Markdown Semantic Chunker, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"markdown-semantic-chunker": {
"url": "https://edge.vinkius.com/vk_preview_7rlgv7c4pKsFI7OUQzClGBELy5KOHUclBVDqK0KP/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 Markdown Semantic Chunker
Open Cascade and ask: "Using Markdown Semantic Chunker, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"markdown-semantic-chunker": {
"url": "https://edge.vinkius.com/vk_preview_7rlgv7c4pKsFI7OUQzClGBELy5KOHUclBVDqK0KP/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 Markdown Semantic Chunker
Ask Cline: "Using Markdown Semantic Chunker, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add markdown-semantic-chunker --transport http "https://edge.vinkius.com/vk_preview_7rlgv7c4pKsFI7OUQzClGBELy5KOHUclBVDqK0KP/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 Markdown Semantic Chunker
Ask Claude: "Using Markdown Semantic Chunker, show me...". 3 tools are ready
Where the request belongs
Work Markdown Semantic Chunker can move forward.
AI engineers and RAG developers who are tired of seeing their agents hallucinate because the retrieved context was cut in half by a bad splitter.
AI Engineer
Building high-precision retrieval systems for large document sets.
Data Scientist
Preparing unstructured markdown datasets for fine-tuning or RAG.
Content Engineer
Managing complex documentation structures that need to be searchable.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
Markdown Semantic Chunker
A deterministic engine for splitting Markdown text into semantically coherent chunks based on header hierarchy and paragraph boundaries.
RAG Chunk Boundary Optimizer
Analyze text chunking integrity in RAG pipelines by measuring overlap, sentence breaks, and semantic continuity.
RAG Payload Metadata Extractor
Extracts metadata and calculates data density for RAG source documents.
RAG Chunk Size Optimizer
Evaluate RAG chunking strategies by calculating segmentation metrics, embedding costs, and context viability.
Document Paginator Engine
Mathematically slice massive text blocks into token-safe chunks without ever truncating critical sentences.
TextRazor
Advanced Natural Language Processing (NLP) to extract entities, topics, and relations from text or URLs.
Bring your own AI
Change the model, client or framework. Keep Markdown Semantic Chunker 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 Markdown Semantic Chunker.
The practical details behind the request, access and result.
How does Markdown Semantic Chunker prevent broken sentences?
It uses a deterministic approach that prioritizes paragraph boundaries. If a chunk reaches its size limit, the engine looks for the nearest double newline to split the text safely.
Can I use Markdown Semantic Chunker for large technical manuals?
Yes. It is specifically designed to handle complex hierarchies in markdown files, ensuring that even deeply nested sections remain contextually linked.
Does Markdown Semantic Chunker support all markdown header levels?
It supports the standard hierarchy from level 1 (#) through level 6 (######), preserving the structural path for every chunk created.
How do I integrate Markdown Semantic Chunker into my RAG pipeline?
You connect it to your AI client via Vinkius. Once connected, you can pass markdown content directly to the capability to receive structured chunks for your vector database.
Will Markdown Semantic Chunker help with hallucination issues?
By ensuring that headers and their related content are never separated during chunking, it provides much higher quality context to your agent, which directly reduces hallucinations.
How does the chunking process maintain context?
The capability assigns a hierarchical path to every chunk, representing its position in the document tree (e.g., Parent > Child). This ensures that even when text is split, the structural lineage remains attached to the content.
What happens if a section is too large for the token limit?
If a header group exceeds the maxChunkSizeTokens, the engine identifies paragraph boundaries marked by double newlines and splits the content at these points to create smaller, valid chunks.
Can I preview the document structure before chunking?
Yes, you can use the get_header_structure capability to extract and view the identified heading hierarchy without performing the full chunking operation.
One connection away
Give your agent a direct line to Markdown Semantic Chunker.
Connect Markdown Semantic Chunker once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available