Vectorize
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
what is Vectorize?
Vectorize is a Model Context Protocol (MCP) server designed for advanced vector retrieval, private deep research, and converting various file formats into Markdown.
how to use Vectorize?
To use Vectorize, set up your environment with your organization ID and API key, then run the MCP server using npx. You can perform document retrieval, text extraction, and deep research through its API.
key features of Vectorize?
- Advanced vector search capabilities for document retrieval
- Text extraction and chunking into Markdown format
- Private deep research generation from specified pipelines
use cases of Vectorize?
- Retrieving relevant documents based on specific queries.
- Extracting text from various file types and converting them into Markdown.
- Conducting in-depth research on topics using private pipelines.
FAQ from Vectorize?
- What types of documents can Vectorize process?
Vectorize can process various document types, including PDFs and other text formats.
- Is there a limit to the number of documents I can retrieve?
The limit depends on the configuration of your pipeline and the parameters set during the retrieval process.
- How secure is the data processed by Vectorize?
Vectorize ensures that all data processed is handled securely, especially during private deep research.
# Vectorize MCP Server
A Model Context Protocol (MCP) server implementation that integrates with [Vectorize](https://vectorize.io/) for advanced Vector retrieval and text extraction.
Features
Installation
Running with npx
```bash export VECTORIZE_ORG_ID=YOUR_ORG_ID export VECTORIZE_API_KEY=YOUR_API_KEY npx -y @vectorize-io/vectorize-mcp-server ```
Configuration on Claude/Windsurf
```json { "mcpServers": { "vectorize": { "command": "npx", "args": ["-y", "@vectorize-io/vectorize-mcp-server"], "env": { "VECTORIZE_ORG_ID": "your-org-id", "VECTORIZE_API_KEY": "your-api-key" } } } } ```
Tools
Retrieve documents
Perform vector search and retrieve documents (see official [API](https://docs.vectorize.io/api/api-pipelines/api-retrieval)):
```json { "name": "retrieve", "arguments": { "pipeline": "your-pipeline-id", "question": "Financial health of the company", "k": 5 } } ```
Text extraction and chunking (Any file to Markdown)
Extract text from a document and chunk it into Markdown format (see official [API](https://docs.vectorize.io/api/api-extraction)):
```json { "name": "extract", "arguments": { "base64document": "base64-encoded-document", "contentType": "application/pdf" } } ```
Deep Research
Generate a Private Deep Research from your pipeline (see official [API](https://docs.vectorize.io/api/api-pipelines/api-deep-research)):
```json { "name": "deep-research", "arguments": { "pipelineId": "your-pipeline-id", "query": "Generate a financial status report about the company", "webSearch": true } } ```
Development
```bash
Install dependencies
npm install
Build
npm run build
```
Contributing
- Fork the repository
- Create your feature branch
- Submit a pull request
