# memra

**Category:** 🧠 Knowledge & Memory  
**Repository:** https://github.com/usememra/mcp  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/memra-2

## Description
Persistent memory for AI agents. EU-hosted, privacy-first, hybrid recall, contradiction detection.

## Claude Desktop Quick Installation
Heuristic fallback — verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low):

```json
"mcpServers": {
  "memra": {
    "command": "npx",
    "args": ["-y","memra-2"]
  }
}
```

## Documentation & README

# Memra MCP Server

Persistent memory for AI agents — remote [MCP](https://modelcontextprotocol.io) server. EU-hosted (Helsinki), privacy-first, deterministic recall with no LLM in the hot path.

**Endpoint:** `https://usememra.com/mcp` (Streamable HTTP) · **Registry:** `com.usememra/memra` · **Free tier, no credit card.**

## What it gives your agent

- **memra_remember / memra_recall** — store facts, decisions, patterns; hybrid semantic + lexical (BM25) search that also matches exact identifiers and error codes
- **Write-time contradiction detection** — storing a fact that clashes with existing knowledge returns `conflicts[]` so the agent can supersede the outdated one
- **Read-your-writes** — every write returns a `revision` token; recall with `wait_for_revision` is deterministic
- **memra_supersede + memra_history** — memories retire with full audit chains instead of going stale
- **Staleness signals** — every result carries `staleness_score` / `last_confirmed`; the agent decides what to trust
- **Token-budget recall** — `max_tokens: 2000` returns the best memories that fit your context window
- **memra_bootstrap** — priority context at session start
- Multi-tenant namespaces, PII masking (7 EU language models), read-only scoped keys for subagents

## Setup

Get an API key at [usememra.com](https://usememra.com) (free tier), then:

**Claude Code**
```bash
claude mcp add --transport http memra https://usememra.com/mcp --header "Authorization: Bearer memra_live_YOUR_KEY"
```

**Cursor / Cline / any MCP client** (`mcp.json`)
```json
{
  "mcpServers": {
    "memra": {
      "url": "https://usememra.com/mcp",
      "headers": { "Authorization": "Bearer memra_live_YOUR_KEY" }
    }
  }
}
```

**Fully offline alternative:** [`pip install memra-local`](https://github.com/usememra/memra-local) — same tools, SQLite + ONNX embeddings, zero cloud calls.

## Docs

- [llms-full.txt](https://usememra.com/llms-full.txt) — complete machine-readable API reference
- [OpenAPI](https://usememra.com/docs/openapi.json) · [Changelog](https://usememra.com/changelog) · [Security](https://usememra.com/security) · [Data & privacy](https://usememra.com/data-privacy)

SDKs: [`pip install memra-sdk`](https://github.com/usememra/memra-python) · [`npm install @usememra/sdk`](https://github.com/usememra/sdk-typescript) · [`composer require memra/sdk`](https://github.com/usememra/sdk-php)