What MCP Memory Servers Are and How to Pick the Right One

·1 views

An MCP memory server is a specialised server built on Anthropic's Model Context Protocol, which was open-sourced in November 2024, designed to store and retrieve an AI agent's memories — such as facts, preferences, and past conversations — across sessions and tools. Unlike a vector database, which is purely a storage engine for embeddings, an MCP memory server acts as the layer above, deciding what gets stored and exposing it to agents as callable tools like store_memory and search_memory. The protocol is now supported by major AI clients including Claude, ChatGPT, Cursor, VS Code, and Windsurf, making memory a shared service any compatible agent can access. Anthony Conti, who develops the MIND MCP memory server at Astra AI, published the explainer on September 7, 2026, offering a technical breakdown alongside an honest comparison of competing open-source options. The piece also clarifies that while most memory servers use RAG-style retrieval internally, MCP and RAG are distinct concepts — one is a protocol, the other an algorithm.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

How One AI Pipeline Learned to Catch Valid but Wrong-Shaped JSON Responses

On March 3, 2026, a content automation pipeline built by an IT analyst failed not because an AI model returned invalid JSON, but because it returned a bare array instead of the expected envelope object. The error passed JSON parsing cleanly but was caught only later by Zod schema validation, highlighting a lesser-known second layer of structured-output failure. To fix the issue, the developer embedded the exact JSON schema directly into the prompt and added a deterministic code fallback to wrap bare arrays automatically. The approach was later codified as a standing rule across two levels of project configuration to ensure it applied to all future work. The lesson proved broadly relevant when the same pipeline was extended to support three interchangeable AI backends, confirming that prompt-plus-code defenses are necessary regardless of the underlying model.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Agent Memory Explained: Four Types Every AI Developer Should Know

AI agent memory is the mechanism that allows agents to retain information — such as facts, preferences, and past actions — across sessions and tool handoffs, rather than resetting with each new conversation. Developer Anthony Conti of Astra AI outlines four distinct memory types: working memory (context window), long-term semantic memory (external storage), episodic memory (timestamped event logs), and procedural memory (learned behavioral patterns). As agents increasingly handle multi-day tasks in 2026, the limitations of even million-token context windows have made persistent external memory a critical engineering concern. Most practical systems require only working memory combined with long-term semantic memory, while episodic and procedural types become essential for complex, extended workflows. Conti also clarifies that retrieval-augmented generation is a retrieval technique, not a memory system itself — agent memory additionally governs what information gets written and when.

0 comments Read more at DEV Community

ProgrammingHacker News ·

LibreOffice hits download record after proudly announcing no AI features

LibreOffice, the open-source office suite, has broken its own download records following a public declaration that it contains no AI features. The announcement appears to have resonated strongly with users who are increasingly wary of AI being embedded in productivity software. The surge in downloads suggests a growing segment of users actively seeking software free from AI integration. This trend highlights a counter-movement to the industry-wide push by major software companies to incorporate AI into their products.

0 comments Read more at Hacker News

ProgrammingDEV Community ·

Critical Magento Zero-Day CVE-2026-75650 Exploited Before Patch, Rust Backdoor Deployed

Adobe released an emergency out-of-band patch on September 8, 2026 for CVE-2026-75650, a maximum-severity CVSS 10.0 unauthenticated remote code execution vulnerability affecting Adobe Commerce and Magento Open Source versions 2.4.4 through 2.4.9. Security firm Sansec, which named the flaw StyleSmuggler, confirmed attackers began exploiting it four days earlier on September 4, giving them a head start on unpatched merchants. The vulnerability resides in Magento's template system and allows a single unauthenticated HTTP request to execute arbitrary code by injecting PHP through the email template path used for payment failure reminders. Observed payloads include a Rust-based Linux backdoor that communicates with an external server and a PHP web shell capable of writing arbitrary code to checkout hosts. Adobe's advisory requires merchants to apply the VULN-39341 hotfix from repo.magento.com and mandatorily rotate encryption keys, as the keys protect stored payment configurations, API credentials, and integration tokens that may have been exposed during the zero-day window.

0 comments Read more at DEV Community