v10.36 — Now Available

MCP Memory Service

Persistent memory for AI agents. Semantic search, knowledge graph, automatic consolidation — now accessible from Claude.ai via Streamable HTTP.

GitHub PyPI Package

What's New in v10.36

Session-level memory ingestion: LongMemEval R@5 86.0% (+5.6% vs turn-level) — new memory_store_session MCP tool and POST /api/sessions HTTP endpoint.

📚

Session-Level Ingestion

New memory_store_session MCP tool stores a full conversation as one memory unit — all turns concatenated as [role] content lines, stored with memory_type=session and auto-tagged session:<id>.

📈

+5.6% Recall Improvement

LongMemEval R@5 improves from 80.4% to 86.0% with session-mode ingestion. Largest gains in multi-session (+15.2%) and temporal-reasoning (+10.6%) categories — zero LLM API calls.

REST + Benchmark Support

New POST /api/sessions HTTP endpoint mirrors the MCP tool for HTTP API consumers. --ingestion-mode session|turn|both flag added to LongMemEval benchmark for direct strategy comparison.

How It Works

Claude.ai connects to your memory server through Streamable HTTP with OAuth 2.1 authentication.

Browser
Claude.ai
Transport
Streamable HTTP
Auth
OAuth 2.1 + PKCE
Server
MCP Memory
Storage
Knowledge Graph
Data flow Auth boundary

Built for Production

Battle-tested with comprehensive testing and optimized for performance.

0
Tests
0
AI Apps Supported
0
Read Latency
0
Cache Speedup

Get Started in Seconds

Install from PyPI and connect your AI agents to persistent memory.

Click to copy pip install mcp-memory-service