Packages

mcp-memory-service v13.0.0: 5ms Agent Memory, LongMemEval Benchmarks & Security Audit

Released on PyPI on November 20, 2026, mcp-memory-service v13.0.0 brings 5ms local semantic recall, a causal knowledge graph, and autonomous consolidation to LangGraph, CrewAI, AutoGen, and Claude. We audit its LongMemEval benchmarks, dependency footprint, and 2026 security posture.

By 0xScorPionSon

8 min read

mcp-memory-service v13.0.0: 5ms Agent Memory, LongMemEval Benchmarks & Security Audit

mcp-memory-service v13.0.0 Python Agent Memory Architecture

Stateless agent runs force developers to re-inject architecture decisions, bug histories, and repository conventions into every new prompt—burning context tokens and inflating latency. On November 20, 2026, maintainer Heinrich Krupp (doobidoo) released mcp-memory-service v13.0.0 on PyPI, advancing an Apache-2.0 persistent memory backend for Python >=3.11 that unifies an MCP server, a FastAPI REST API, local ONNX embeddings, a causal knowledge graph, and autonomous memory consolidation in a single self-hosted service.

Executive Summary

  • Package & Version: mcp-memory-service v13.0.0 (Python / PyPI), released November 20, 2026 under the Apache-2.0 license (PyPI).
  • Runtime & Extras: Requires Python >=3.11 (tested on 3.11 and 3.12; uploaded via twine/7.0.0 on CPython 3.14.4). Optional PyPI extras include sqlite, sqlite-ml, ml, nli, clustering, milvus, dev, and full.
  • AI & Agent Relevance: Delivers 5 ms local retrieval via sqlite-vec + BM25 hybrid search, X-Agent-ID scoped multi-agent memory, causal knowledge-graph edges (causes, fixes, contradicts), and native integrations for LangGraph, CrewAI, AutoGen, Claude Code, Codex, and OpenCode.
  • Primary Upgrade Takeaway: Stay on the latest release—mcp-memory-service follows a forward-only security patch policy without backports (Greenlit Books), and running it over local stdio with MCP_HTTP_ENABLED=false (the default) avoids network-exposed attack surfaces.

Adoption Telemetry & Version Changelog

mcp-memory-service has grown from a lightweight sqlite-vec MCP server into one of the most actively iterated memory backends in the Python agent ecosystem:

Metric / Artifact Verified Value (v13.0.0) Source
Latest PyPI Release 13.0.0 (November 20, 2026) PyPI Release History
GitHub Community Scale 9,300+ stars; 400+ releases Awesome Claude Code / GitHub
Wheel / Sdist Size 1.7 MB wheel (py3-none-any); 44.6 MB sdist PyPI Release Files
PyPI Provenance None (not uploaded via Trusted Publishing) PyPI Security Metadata
Minimum Python Floor Python >=3.11 (raised from >=3.10 in earlier 11.5.2 builds) PyPI Metadata

Release Cadence & Breaking Milestones

Between 10.x and 13.0.0, the project maintained a rapid release cadence—shipping multiple minor releases per week across 11.x (June–October 2026), 12.x (October–November 16, 2026), and culminating in 13.0.0 on November 20, 2026. Key breaking and architectural transitions documented in the Installation & Migration Wiki include:

  • Deprecated MCP Tool Aliases Removed (v11+): Legacy MCP tool aliases were dropped in v11.0.0. Teams upgrading from 10.x or earlier must update client prompts and agent harnesses to use canonical tool names (memory_store, memory_search, memory_harvest, memory_bootstrap_profile).
  • Consolidation Schedules Opt-In (v10.47.x+): Autonomous background consolidation is disabled by default and requires explicit MCP_SCHEDULE_* environment variables.
  • Store-Scoped Partitions & Hybrid Sync Fixes (v12.x–v13.0.0): Multi-store isolation (default, docs, all) and Hybrid backend pull-sync fixes (skip_semantic_dedup=True on secondary pulls and store-scoped sqlite_vec updates in Issue #1875) hardened multi-device synchronization ahead of 13.0.0.
  • Supply-Chain Note: PyPI metadata shows mcp-memory-service 13.0.0 was uploaded without PEP 740 Trusted Publishing attestations (No provenance), so security-conscious teams should verify the SHA-256 checksums published on PyPI (dca5cb5e8c13caceb6b0c689bf3626b228eec5b1c4d9502898b3a603b53db712 for the 1.7 MB wheel).

Architecture, Storage Backends & Fast-Startup CLI

All deployment topologies share the same storage engines and environment-variable configuration, differing only in transport exposure (Production Guide):

  • SQLite-vec (Default Local): Single-file local vector store paired with local ONNX embeddings and BM25 lexical search (mode="ranked" weighs recency, access frequency, and quality).
  • Hybrid (5 ms Reads + Background Sync): Serves local reads in 5 ms from sqlite-vec while syncing asynchronously to a secondary Cloudflare D1/Vectorize backend or a second self-hosted HTTP mcp-memory-service instance (MCP_HYBRID_SECONDARY_BACKEND=http). Separately enabled delta-sync is off by default.
  • Milvus: Supports embedded Milvus Lite files, self-hosted Docker Milvus, or managed Zilliz Cloud (with official docs recommending Docker Milvus or Zilliz Cloud over Milvus Lite for long-lived services).
  • Lean CLI Lifecycle: Commands such as memory launch, memory launch --port 8192, memory info, memory logs --lines 50, and memory stop are optimized for fast startup and defer loading heavy ML dependencies until semantic operations are invoked.

Security Patches, Breaking Changes & Internals

Because a persistent memory store acts as long-term context injection for coding and operations agents, its authorization and transport boundaries are critical.

Patched Advisories & 2026 Security Posture

  1. GHSA-2r68-g678-7qr3 / CVE-2026-49291 (CVSS 8.1 High, CWE-862): Published in May/June 2026 for versions <= 10.65.1 and patched in 10.65.3 (GitHub Advisory). The HTTP /mcp JSON-RPC endpoint previously checked only require_read_access at the route level, allowing an OAuth token with scope: read to invoke store_memory and delete_memory via tools/call—bypassing the 403 insufficient_scope guard enforced on POST /api/memories. The fix enforces per-tool authorization inside tools/call.
  2. September 2026 Advisories & Health Route Fix: As documented in Greenlit Books' September 25, 2026 code audit, v11.13.0 closed three critical advisories, followed by commit 4a22534 (September 24, 2026) stopping GET /mcp/health from leaking storage statistics.
  3. Default Safe Boundaries:
    • Local-First by Default: MCP_MEMORY_STORAGE_BACKEND defaults to sqlite_vec, MCP_HTTP_ENABLED defaults to false (running over stdio), and HTTP binds to 127.0.0.1 unless explicitly overridden with --host 0.0.0.0.
    • Network Transport File Guard: Two stdio tools accept caller-controlled filesystem paths; those tools are hidden and rejected over network transports.
    • Opt-In Egress Caveat: Default ONNX embeddings and quality scoring run locally with zero telemetry. Enabling MCP_SEARCH_SUMMARIZE_ENABLED=true, Groq/Gemini scoring, or memory_harvest transcript extraction sends excerpts to your configured external LLM provider (api.groq.com or your OpenAI-compatible endpoint).

Clean Setup & Usage Example (v13.0.0)

Install with the [sqlite] extra so the local ONNX embedding model is bundled (without [sqlite], semantic search falls back to hash embeddings):

uv tool install "mcp-memory-service[sqlite]"
claude mcp add memory -- memory server
memory launch --port 8000

When calling the FastAPI REST API from LangGraph, CrewAI, or AutoGen pipelines (http://127.0.0.1:8000/api/docs), pass X-Agent-ID: <agent_name> on POST /api/memories to automatically tag memories with agent:<agent_name> for scoped retrieval via POST /api/search/by-tag, or pass conversation_id to bypass deduplication for incremental conversation logs. Beyond Python SDK pipelines, the repository ships native hook installers for Codex (python3 codex/install_hooks.py to inject context and checkpoint outcomes before compaction), Claude Code session capture hooks, an OpenCode /memory slash command, and OAuth 2.0 Remote MCP support for browser-based claude.ai and ChatGPT Developer Mode clients behind Cloudflare Tunnel, nginx, Caddy, or Docker.

Retrieval Benchmarks: LongMemEval Turn vs. Session Mode

In the official BENCHMARKS.md suite, mcp-memory-service evaluates retrieval across both fine-grained turn-level storage (the default) and whole-session storage (memory_store_session), noting that session mode boosts R@5 by +5.6% (86.0% vs 80.4% baseline) at the cost of lower MRR because fewer redundant hits appear from the same session:

Question Type Mode Recall@5 (R@5) MRR / NDCG@10
single-session-assistant Turn Mode (Baseline) 100.0% 99.1% MRR / 99.3% NDCG@10
single-session-user Turn Mode (Baseline) 91.4% 83.8% MRR / 86.0% NDCG@10
single-session-preference Turn Mode (Baseline) 86.7% 79.2% MRR / 83.4% NDCG@10
knowledge-update Turn Mode (Baseline) 84.6% 95.5% MRR / 86.2% NDCG@10
multi-session Session Mode 85.9% 89.7% MRR
temporal-reasoning Session Mode 82.6% 80.9% MRR

Maintainer Heinrich Krupp also explicitly caveats viral 96.6% competitor claims from MemPalace (citing Issue #27, where whole-session ChromaDB storage bypassed Palace's advertised architecture).

Ecosystem Comparison & Upgrade Checklist

Package / Solution License & Cost Default Storage & Embeddings Transport & Auth Retrieval / Graph Features
mcp-memory-service 13.0.0 Apache-2.0 ($0 self-hosted) sqlite-vec + local ONNX (or Hybrid / Milvus / Cloudflare) MCP (stdio, Streamable HTTP + OAuth 2.0) + FastAPI REST Hybrid BM25 + vector (5 ms), causal knowledge graph, autonomous consolidation
Official @modelcontextprotocol/server-memory MIT ($0 self-hosted) Local JSONL knowledge graph MCP stdio Simple entity-relation graph; no vector search or REST API
Mem0 (OSS / Hosted) Apache-2.0 / Commercial SaaS Configurable vector/graph DBs (often cloud LLM calls) Python/TS SDK + Hosted API LLM-extracted fact memory; higher API token overhead
MemPalace Open Source ChromaDB (session-level units) MCP Session-granularity LongMemEval (96.6% raw ChromaDB mode disputed in Issue #27)

Safe Upgrade & Pinning Checklist

  1. Pin Exact Wheel Versions & Verify Hashes: Pin mcp-memory-service==13.0.0 in pyproject.toml or uv.lock and verify PyPI SHA-256 hashes, since Trusted Publishing provenance is absent.
  2. Audit 10.x -> 13.0.0 Tool Names: If upgrading from v10.x or earlier, replace any deprecated MCP tool aliases removed in v11.
  3. Keep stdio Default for Single-Machine Agents: Leave MCP_HTTP_ENABLED=false unless you specifically need multi-agent REST or Remote MCP; if exposing HTTP, bind to 127.0.0.1 or terminate TLS behind a reverse proxy with OAuth 2.0 enabled.
  4. Monitor Release Advisories: Because fixes are not backported to older branches, subscribe to GitHub release notifications for doobidoo/mcp-memory-service.

Frequently Asked Questions

What is new in mcp-memory-service 13.0.0?

Released on November 20, 2026 on PyPI, mcp-memory-service 13.0.0 advances the Apache-2.0 Python >=3.11 memory backend with multi-store partition isolation, Hybrid sync deduplication fixes, an 8-tab FastAPI web dashboard, causal knowledge-graph edges, and 5 ms local vector+BM25 retrieval.

Is mcp-memory-service safe to run with Claude Desktop or Cursor?

Yes, when run in its default stdio mode with sqlite-vec and local ONNX embeddings, where nothing leaves your machine. Keep the package updated to the latest release (since security fixes are forward-only) and manually review any stdio file-reading tool calls.

Why does pip install mcp-memory-service[sqlite] matter?

The [sqlite] extra installs the local ONNX embedding runtime. Without it, mcp-memory-service falls back to basic hash embeddings, which degrades semantic search quality.

Does mcp-memory-service require an OpenAI or Anthropic API key?

No. Core storage, ONNX embeddings, BM25 + vector search, and local quality scoring run offline with zero API keys. External LLM keys are only needed if you opt into MCP_SEARCH_SUMMARIZE_ENABLED=true, cloud-LLM quality scoring, or memory_harvest transcript extraction.

How does mcp-memory-service prevent read-only OAuth clients from deleting memories?

Following CVE-2026-49291 (GHSA-2r68-g678-7qr3, patched in 10.65.3), the /mcp JSON-RPC dispatcher enforces per-tool OAuth scopes at tools/call time, rejecting store_memory and delete_memory calls from tokens that only hold read scope.

Sources

More on Packages

Packages

OpenAI @openai/codex 0.171.0: GPT-6.2 Sol Default, TUI Workspace, and Sandbox Hardening

OpenAI released @openai/codex 0.171.0 on November 20, 2026, switching the default CLI model to GPT-6.2 Sol, enabling the TUI workspace with document and image previews by default, and adding remote app-server execution. Backed by 23.2 million weekly npm downloads and a Rust 1.99.1 core, the release also hardens Linux seccomp sandboxing and enterprise MCP sign-in.

8 min read

Packages

FastMCP 4.2.3: Breaking Changes, OAuth & OpenTelemetry Security Fixes, and Production Upgrade Guide

FastMCP 4.2.3 ships with opt-in parent_task_spans tracing and OpenAPI path validation fixes, capping a week of rapid 4.2.x updates that dropped Python 3.10 support and patched critical OAuth and OpenTelemetry ReDoS flaws. With 64.5 million monthly PyPI downloads, upgrading safely requires checking your Python runtime floor, OAuth consent behavior, and deprecated 4.1 skills APIs. Here is the exact changelog breakdown, ecosystem comparison against the official MCP Python SDK 2.3.0, and a step-by-step upgrade checklist.

9 min read

Tell us what is not working

A thirty-minute call, no deck and no obligation. You will leave with a straight answer about whether this is worth building - including if that answer is no.

Start a project

Direct line

hello@codebumble.net
Dhaka, Bangladesh  :   local timeCalls in English or Bangla