A Model Context Protocol (MCP) server implementation that integrates with Vectorize for advanced Vector retrieval and text extraction. For one-click installation, click one of the install buttons below: 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
Add this skill
npx mdskills install vectorize-io/vectorize-mcp-serverWell-documented MCP server with useful vector search tools but overly permissive access
1# Vectorize MCP Server23A Model Context Protocol (MCP) server implementation that integrates with [Vectorize](https://vectorize.io/) for advanced Vector retrieval and text extraction.45<a href="https://glama.ai/mcp/servers/pxwbgk0kzr">6 <img width="380" height="200" src="https://glama.ai/mcp/servers/pxwbgk0kzr/badge" alt="Vectorize MCP server" />7</a>8910## Installation1112### Running with npx1314```bash15export VECTORIZE_ORG_ID=YOUR_ORG_ID16export VECTORIZE_TOKEN=YOUR_TOKEN17export VECTORIZE_PIPELINE_ID=YOUR_PIPELINE_ID1819npx -y @vectorize-io/vectorize-mcp-server@latest20```2122### VS Code Installation2324For one-click installation, click one of the install buttons below:2526[](https://insiders.vscode.dev/redirect/mcp/install?name=vectorize&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40vectorize-io%2Fvectorize-mcp-server%40latest%22%5D%2C%22env%22%3A%7B%22VECTORIZE_ORG_ID%22%3A%22%24%7Binput%3Aorg_id%7D%22%2C%22VECTORIZE_TOKEN%22%3A%22%24%7Binput%3Atoken%7D%22%2C%22VECTORIZE_PIPELINE_ID%22%3A%22%24%7Binput%3Apipeline_id%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22org_id%22%2C%22description%22%3A%22Vectorize+Organization+ID%22%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22token%22%2C%22description%22%3A%22Vectorize+Token%22%2C%22password%22%3Atrue%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22pipeline_id%22%2C%22description%22%3A%22Vectorize+Pipeline+ID%22%7D%5D) [](https://insiders.vscode.dev/redirect/mcp/install?name=vectorize&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40vectorize-io%2Fvectorize-mcp-server%40latest%22%5D%2C%22env%22%3A%7B%22VECTORIZE_ORG_ID%22%3A%22%24%7Binput%3Aorg_id%7D%22%2C%22VECTORIZE_TOKEN%22%3A%22%24%7Binput%3Atoken%7D%22%2C%22VECTORIZE_PIPELINE_ID%22%3A%22%24%7Binput%3Apipeline_id%7D%22%7D%7D&inputs=%5B%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22org_id%22%2C%22description%22%3A%22Vectorize+Organization+ID%22%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22token%22%2C%22description%22%3A%22Vectorize+Token%22%2C%22password%22%3Atrue%7D%2C%7B%22type%22%3A%22promptString%22%2C%22id%22%3A%22pipeline_id%22%2C%22description%22%3A%22Vectorize+Pipeline+ID%22%7D%5D&quality=insiders)2728### Manual Installation2930For the quickest installation, use the one-click install buttons at the top of this section.3132To 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)`.3334```json35{36 "mcp": {37 "inputs": [38 {39 "type": "promptString",40 "id": "org_id",41 "description": "Vectorize Organization ID"42 },43 {44 "type": "promptString",45 "id": "token",46 "description": "Vectorize Token",47 "password": true48 },49 {50 "type": "promptString",51 "id": "pipeline_id",52 "description": "Vectorize Pipeline ID"53 }54 ],55 "servers": {56 "vectorize": {57 "command": "npx",58 "args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],59 "env": {60 "VECTORIZE_ORG_ID": "${input:org_id}",61 "VECTORIZE_TOKEN": "${input:token}",62 "VECTORIZE_PIPELINE_ID": "${input:pipeline_id}"63 }64 }65 }66 }67}68```6970Optionally, you can add the following to a file called `.vscode/mcp.json` in your workspace to share the configuration with others:7172```json73{74 "inputs": [75 {76 "type": "promptString",77 "id": "org_id",78 "description": "Vectorize Organization ID"79 },80 {81 "type": "promptString",82 "id": "token",83 "description": "Vectorize Token",84 "password": true85 },86 {87 "type": "promptString",88 "id": "pipeline_id",89 "description": "Vectorize Pipeline ID"90 }91 ],92 "servers": {93 "vectorize": {94 "command": "npx",95 "args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],96 "env": {97 "VECTORIZE_ORG_ID": "${input:org_id}",98 "VECTORIZE_TOKEN": "${input:token}",99 "VECTORIZE_PIPELINE_ID": "${input:pipeline_id}"100 }101 }102 }103}104```105106## Configuration on Claude/Windsurf/Cursor/Cline107108```json109{110 "mcpServers": {111 "vectorize": {112 "command": "npx",113 "args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],114 "env": {115 "VECTORIZE_ORG_ID": "your-org-id",116 "VECTORIZE_TOKEN": "your-token",117 "VECTORIZE_PIPELINE_ID": "your-pipeline-id"118 }119 }120 }121}122```123124## Tools125126### Retrieve documents127128Perform vector search and retrieve documents (see official [API](https://docs.vectorize.io/api/api-pipelines/api-retrieval)):129130```json131{132 "name": "retrieve",133 "arguments": {134 "question": "Financial health of the company",135 "k": 5136 }137}138```139140### Text extraction and chunking (Any file to Markdown)141142Extract text from a document and chunk it into Markdown format (see official [API](https://docs.vectorize.io/api/api-extraction)):143144```json145{146 "name": "extract",147 "arguments": {148 "base64document": "base64-encoded-document",149 "contentType": "application/pdf"150 }151}152```153154### Deep Research155156Generate a Private Deep Research from your pipeline (see official [API](https://docs.vectorize.io/api/api-pipelines/api-deep-research)):157158```json159{160 "name": "deep-research",161 "arguments": {162 "query": "Generate a financial status report about the company",163 "webSearch": true164 }165}166```167168## Development169170```bash171npm install172npm run dev173```174175### Release176Change the package.json version and then:177```bash178git commit -am "x.y.z"179git tag x.y.z180git push origin181git push origin --tags182```183184### Contributing1851861. Fork the repository1872. Create your feature branch1883. Submit a pull request189190
Full transparency — inspect the skill content before installing.