vectorize.io
Vectorize provides hosted tools for building retrieval-augmented generation pipelines and managing data ingestion, retrieval, and chat endpoints for AI applications. It also offers Hindsight Cloud, a managed memory system for AI agents that stores, retrieves, and reasons over persistent agent memory.
vectorize.io exposes three authenticated HTTP integration surfaces for Vectorize RAG pipelines/API, plus Hindsight Cloud as an authenticated HTTP API, MCP server (single-bank and multi-bank endpoints), and CLI.
- Vectorize APIdiscovered
- Vectorize pipeline retrieval endpointdiscovered
- Hindsight Cloud APIdiscovered
- Hindsight CLIdiscovered
Sign in to the Vectorize platform. Open the token management UI from the dashboard gear menu Access Tokens, or from a pipeline’s Connect tab via Manage access tokens. Click New Access Token, choose a name and expiration, then copy the token when shown; it is only displayed once. These tokens are used for the Vectorize API and pipeline retrieval/chat endpoints.
Point your MCP client at the server URL and approve access in the browser. The server supports OAuth Dynamic Client Registration (RFC 7591), so the client registers itself automatically — no developer-portal app, client_id, or client_secret to create.
conventions · 0/8 published
- integrations.json✗
/.well-known/integrations.json - llms.txt✗
/llms.txt - API catalog✗
/.well-known/api-catalog - OpenAPI document✗
/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json - MCP server card✗
/.well-known/mcp/server-card.json - OAuth protected resource✗
/.well-known/oauth-protected-resource - Agent card✗
/.well-known/agent-card.json - Agent skills✗
/.well-known/agent-skills/index.json
Publish these signals → /publishing