Vectorize MCP server
Commit Nov 2, 2026Lets an AI client run vector retrieval, extract and chunk documents into Markdown, and generate deep research reports from a Vectorize pipeline.
Also known as vectorize-io/vectorize-mcp-server
- Stars
- 116
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 2, 2026
- License
- MIT
What is Vectorize MCP?
Vectorize lets an AI client run vector retrieval, extract and chunk documents into Markdown, and generate deep research reports from a Vectorize pipeline.
Summary generated from the project's README
About Vectorize MCP server
Performing vector retrieval and document extraction from inside an AI client is what this server enables for developers using the Vectorize platform. It connects your local environment to a Vectorize pipeline, allowing an AI to interact with your data through specialized tools. Users can set this up in environments like Claude, Windsurf, Cursor, or Cline by providing a Vectorize Organization ID, an authentication token, and a specific Pipeline ID via environment variables.
The server provides three primary capabilities. It can perform vector searches to find relevant documents based on a specific question, extract text from files like PDFs and convert them into Markdown chunks, and run deep research tasks. By integrating these functions, an AI assistant can move beyond simple chat to actively querying your vector database and processing complex documents for research purposes.
What you can do with it
- 1Vector document retrievalAsk your AI to find specific information from your indexed datasets using vector search.
- 2Document to Markdown conversionConvert uploaded files like PDFs into structured Markdown text for better AI processing.
- 3Automated deep researchInstruct your AI to generate comprehensive research reports using your existing data pipelines.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
VECTORIZE_ORG_IDVECTORIZE_PIPELINE_IDVECTORIZE_TOKEN
| Name | Description | |
|---|---|---|
| VECTORIZE_ORG_ID | — | |
| VECTORIZE_PIPELINE_ID | — | |
| VECTORIZE_TOKEN | — |
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubVectorize MCP Server
A Model Context Protocol (MCP) server implementation that integrates with Vectorize for advanced Vector retrieval and text extraction.
Installation
Running with npx
export VECTORIZE_ORG_ID=YOUR_ORG_ID
export VECTORIZE_TOKEN=YOUR_TOKEN
export VECTORIZE_PIPELINE_ID=YOUR_PIPELINE_ID
npx -y @vectorize-io/vectorize-mcp-server@latest
VS Code Installation
For one-click installation, click one of the install buttons below:
Manual Installation
For the quickest installation, use the one-click install buttons at the top of this section.
To install manually, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "org_id",
"description": "Vectorize Organization ID"
},
{
"type": "promptString",
"id": "token",
"description": "Vectorize Token",
"password": true
},
{
"type": "promptString",
"id": "pipeline_id",
"description": "Vectorize Pipeline ID"
}
],
"servers": {
"vectorize": {
"command": "npx",
"args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],
"env": {
"VECTORIZE_ORG_ID": "${input:org_id}",
"VECTORIZE_TOKEN": "${input:token}",
"VECTORIZE_PIPELINE_ID": "${input:pipeline_id}"
}
}
}
}
}
Optionally, you can add the following to a file called .vscode/mcp.json in your workspace to share the configuration with others:
{
"inputs": [
{
"type": "promptString",
"id": "org_id",
"description": "Vectorize Organization ID"
},
{
"type": "promptString",
"id": "token",
"description": "Vectorize Token",
"password": true
},
{
"type": "promptString",
"id": "pipeline_id",
"description": "Vectorize Pipeline ID"
}
],
"servers": {
"vectorize": {
"command": "npx",
"args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],
"env": {
"VECTORIZE_ORG_ID": "${input:org_id}",
"VECTORIZE_TOKEN": "${input:token}",
"VECTORIZE_PIPELINE_ID": "${input:pipeline_id}"
}
}
}
}
Configuration on Claude/Windsurf/Cursor/Cline
{
"mcpServers": {
"vectorize": {
"command": "npx",
"args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],
"env": {
"VECTORIZE_ORG_ID": "your-org-id",
"VECTORIZE_TOKEN": "your-token",
"VECTORIZE_PIPELINE_ID": "your-pipeline-id"
}
}
}
}
Tools
Retrieve documents
Perform vector search and retrieve documents (see official API):
{
"name": "retrieve",
"arguments": {
"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):
{
"name": "extract",
"arguments": {
"base64document": "base64-encoded-document",
"contentType": "application/pdf"
}
}
Deep Research
Generate a Private Deep Research from your pipeline (see official API):
{
"name": "deep-research",
"arguments": {
"query": "Generate a financial status report about the company",
"webSearch": true
}
}
Development
npm install
npm run dev
Release
Change the package.json version and then:
git commit -am "x.y.z"
git tag x.y.z
git push origin
git push origin --tags
Contributing
- Fork the repository
- Create your feature branch
- Submit a pull request
Vectorize MCP questions
How do I configure the Vectorize MCP server?
Set the VECTORIZE_ORG_ID, VECTORIZE_TOKEN and VECTORIZE_PIPELINE_ID environment variables and run the package with npx. The same env block can be added to a claude/windsurf/cursor/cline mcpServers config.
Can the Vectorize MCP server search my pipeline and return documents?
Yes, the retrieve tool performs vector search and retrieves documents for a question, with a k parameter for the number of results.
Can it convert documents to Markdown?
Yes, the extract tool extracts text from a document and chunks it into Markdown format, taking a base64 document and its content type.
Does Vectorize support deep research queries?
Yes, the deep-research tool generates a private deep research report from your pipeline, optionally with web search enabled.
What authentication does the server need?
It needs a Vectorize token along with your organization ID and pipeline ID, passed as environment variables.