mcp-memory-service v11.7 — Now Available

Memory for AI Agents

Persistent memory for AI agents — REST API, MCP, OAuth, CLI, dashboard. Semantic search, knowledge graph, automatic consolidation. One self-hosted service, every transport.

Try the Live Demo Codeberg PyPI Package

Interactive 3D knowledge graph — every memory a glowing node, every relationship a curved edge.

What's New in v11.7

MINOR release, in substance a security release: three unconditional TLS certificate-verification bypasses are gated behind explicit opt-in, and a real credential committed in the bundled hooks config is gone. ~2,725 tests.

🔒

TLS Bypasses Gated Behind Opt-In

claude-hooks, the opencode plugin, and examples/http-mcp-bridge.js all skipped certificate verification unconditionally. All three now require an explicit allowSelfSignedCerts opt-in and log a warning on every use. (#198, #210, timkjr; bridge fix)

🔑

Committed Credential Removed

The bundled claude-hooks/config.json shipped with a live apiKey and a maintainer-local path since 24af496c. Both are now placeholders, and a new CI gate fails the build if either comes back. (#197/#200, reported by timkjr)

🔧

Backend & Container Fixes

Milvus's store(), count_all_memories(), and search_memories() accept the store keyword like every other backend (#148, closes #133, reported by @ghulands); MCP_QUALITY_ONNX_MODEL_DIR fixes non-root container deployments (#171/#209, reported by @tecnobrat).

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

In the Media

Talks and coverage from the community.

Get Started in Seconds

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

Click to copy pip install mcp-memory-service

Deploying for a team?

I help teams run self-hosted memory in production — OAuth, hybrid sync, multi-client rollout. Free 30-minute intro call.

Get in touch