No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by FlowElement-ai · MCP Server · ★ 2.4k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is m_flow safe to install? View the security audit →
M-flow Graph RAG finds what's similar. M-flow finds what's relevant. Retrieval through reasoning and association — M-flow operates like a cognitive memory system. m-flow.ai · flowelement.ai · Quick Start · Architecture · Examples · OpenClaw Skill · Contact What is M-flow? The fundamental shift is this: existing systems build graphs but still retrieve by embedding distance. M-flow makes the graph the retrieval mechanism itself. RAG embeds chunks and ranks by vector similarity. GraphRAG goes further — it extracts entities, builds a knowledge graph, and generates community summaries. But when a query arrives, retrieval still reduces to embedding the query and matching against stored text. The graph informs what gets embedded; it does not participate in how results are scored. The retrieval step remains similarity-driven. M-flow takes a different approach: the graph is the scoring engine. When a query arrives, vector search casts a wide net across multiple granularities to f
| Stars | 2,389 |
| Forks | 238 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 72.5442826343232/100 |
| Open Issues | 19 |
| Last Updated | 2026-05-02 |
| Created | 2026-03-31 |
| Platforms | mcp, python |
| Est. Tokens | ~285k |
Looking for a m_flow alternative? If you're comparing m_flow with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI
A memory OS that makes your OpenClaw agents more personal while saving tokens.
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowl
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill r
Explore other popular mcp server tools:
m_flow is A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.. It is categorized as a MCP Server with 2.4k GitHub stars.
m_flow is primarily written in Python. It covers topics such as agent-memory, agentic-ai, ai-reasoning.
You can find installation instructions and usage details in the m_flow GitHub repository at github.com/FlowElement-ai/m_flow. The project has 2.4k stars and 238 forks, indicating an active community.
m_flow is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to m_flow on Agent Skills Hub include m_flow, code-graph-rag, EverMemOS. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: