deep-research
Generate a deep research on the configured pipeline.
LABSCO SUMMARY
Your own indexed corpus answers, rather than the model's memory.
retrieve pulls the passages behind an answer out of the pipeline you already built, so what supports a claim is a document you own. extract runs the other direction — a file arrives base64-encoded and comes back as chunks — and deep-research takes a question broad enough that one retrieval would not settle it.
What it is
A client for a configured Vectorize pipeline: retrieval of the documents that answer a question, text extraction and chunking of a document you pass in, and a deep-research run over the same pipeline.
What you get
- Documents retrieved from the configured pipeline for a question, with k setting how many come back
- Text extracted and chunked from a base64-encoded document of a content type you declare
- A deep research run generated over the pipeline, optionally widened with web search
Requirements
A Vectorize organisation and pipeline — VECTORIZE_ORG_ID and VECTORIZE_PIPELINE_ID — with a token in VECTORIZE_TOKEN, plus npx on your PATH.
Setup effort
One command plus a key — npx -y @vectorize-io/vectorize-mcp-server@latest, then supply credentials
USE CASES
01
Answering from your own document set
Retrieval runs against the pipeline you configured, and k decides how many documents come back, so the answer rests on material you control rather than on what the model remembers.
02
Getting a research write-up out of the corpus
For a question one retrieval will not settle, the deep-research call works the pipeline and can be widened with web search when the corpus alone is too narrow.
03
Turning a raw file into chunks
Pass the document base64-encoded with its content type and it comes back as extracted, chunked text — the step that usually needs its own parsing script.
3 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
extract
Perform text extraction and chunking on a document.
retrieve
Retrieve documents from the configured pipeline.
BEFORE YOU INSTALL
What to know first
Tools you get
3 tools when we connected. Names are hyphenated rather than snake_case: retrieve, extract and deep-research.
Requires
- npx on PATH
- VECTORIZE_ORG_ID in your environment
- VECTORIZE_TOKEN in your environment
- VECTORIZE_PIPELINE_ID in your environment
Where it runs
All 6 documented setups run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 3 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @vectorize-io/vectorize-mcp-server@latestMCP Clients
VS Code — user, workspace
JSON
{
"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}"
}
}
}
}Claude Desktop, Windsurf, Cursor, Cline
JSON
{
"mcpServers": {
"vectorize": {
"command": "npx",
"args": [
"-y",
"@vectorize-io/vectorize-mcp-server@latest"
],
"env": {
"VECTORIZE_ORG_ID": "<YOUR_VECTORIZE_ORG_ID>",
"VECTORIZE_TOKEN": "<YOUR_VECTORIZE_TOKEN>",
"VECTORIZE_PIPELINE_ID": "<YOUR_VECTORIZE_PIPELINE_ID>"
}
}
}
}
