---
title: "StudioMeyer Memory: REST API and MCP"
description: "REST and MCP APIs to build with StudioMeyer: memory backend, knowledge graphs and agent tools. EU hosting, GDPR-compliant, open source."
canonical: "https://studiomeyer.io/en/developers/memory"
language: en
last_updated: 2026-11-04
image: "https://studiomeyer.io/og-developers.png"
markdown_versions: ["https://studiomeyer.io/de/developers/memory.md", "https://studiomeyer.io/en/developers/memory.md", "https://studiomeyer.io/es/developers/memory.md"]
publisher: "StudioMeyer, https://studiomeyer.io (llms.txt: https://studiomeyer.io/llms.txt)"
---

[Part of StudioMeyer Memory](https://studiomeyer.io/en/services/memory)REST API + MCP Protocol

# StudioMeyer Memory, as an API

A memory backend for AI agents, apps, and automations. Store facts, search semantically, build knowledge graphs, import your ChatGPT, Claude and Gemini history. Your LLM provider stays your choice, we only ship the memory. Live at memory.studiomeyer.io. REST + MCP, EU hosting, GDPR-compliant.

terminal

```
curl -X POST https://memory.studiomeyer.io/api/search \
  -H "Authorization: Bearer nex_YOUR_MEMORY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "what do we know about Q1 sales", "limit": 10}'
```

[Get API Key](https://studiomeyer.io/en/services/memory)[Documentation](https://memory.studiomeyer.io/api)[Memory API overview](https://studiomeyer.io/en/api)

## What this actually is

An HTTP API that gives your AI agent long-term memory. No RAG pipeline to build, no vector DB to host, no embedding pipeline to maintain. POST JSON to /api/learn, /api/search, /api/entity, we store, index and link. For REST, send the tenant API key as a Bearer token. MCP clients such as Claude Desktop, Cursor and Codex connect through the Memory server’s own OAuth sign-in flow. Your LLM stays your LLM.

Quick Start

## Integrated in 3 steps

01

### Create Account

Enter your email, click the magic link, get your API key. 5,000 requests a day on Free, no card needed.

02

### Build Memory

POST /api/learn for facts, POST /api/decide for decisions, POST /api/entity for knowledge graphs. Or POST /api/import with a ChatGPT export, we parse and structure it.

03

### Query

POST /api/search with a question. Semantic + full-text + knowledge graph in one call. Or connect Claude Desktop via MCP and your agent has instant access.

Code Examples

## Integrate instantly

```
curl -X POST https://memory.studiomeyer.io/api/search \
  -H "Authorization: Bearer nex_YOUR_MEMORY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "what do we know about Q1 sales", "limit": 10}'
```

Authentication & Limits

## Auth and daily limits

### Authentication

- Bearer token in the Authorization header, no API keys in query params.
- Use the tenant API key as a Bearer token for your own REST requests. For normal MCP connections, the client uses OAuth 2.1 with PKCE at the Memory server. The memory scope grants full account access, not separate read and write permissions.

`Authorization: Bearer nex_YOUR_MEMORY_API_KEY`

### Limits by plan

Plan

Requests per day

Free

5,000

Pro (9 EUR/mo)

50,000

Team (19 EUR/mo)

unlimited

Every call counts, searches included. The allowance starts fresh every day.

## Ready to give your AI a memory?

[Get API Key](https://studiomeyer.io/en/services/memory)[API Docs](https://memory.studiomeyer.io/api)[OpenAPI Spec](https://memory.studiomeyer.io/openapi.json)

## Sitemap

Every page of this site as Markdown: [sitemap](https://studiomeyer.io/sitemap.md). Curated entry point: [llms.txt](https://studiomeyer.io/llms.txt).