Memra MCP Server

Persistent memory for AI agents — remote MCP 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detection — storing a fact that clashes with existing knowledge returns conflicts[] so the agent can supersede the outdated one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

Related MCP server: haksnbot-memory

Setup

Get an API key at usememra.com (free tier), then:

Claude Code

claude mcp add --transport http memra https://usememra.com/mcp --header "Authorization: Bearer memra_live_YOUR_KEY"

Cursor / Cline / any MCP client (mcp.json)

{
  "mcpServers": {
    "memra": {
      "url": "https://usememra.com/mcp",
      "headers": { "Authorization": "Bearer memra_live_YOUR_KEY" }
    }
  }
}

Fully offline alternative: pip install memra-local — same tools, SQLite + ONNX embeddings, zero cloud calls.

Docs

• llms-full.txt — complete machine-readable API reference

• OpenAPI · Changelog · Security · Data & privacy

SDKs: pip install memra-sdk · npm install @usememra/sdk · composer require memra/sdk