Memnode
Memnode is an MCP server that provides persistent, inspectable agent memory with lineage and correction over a hosted endpoint.
About
Memnode is a Model Context Protocol server that gives developers persistent, inspectable memory for AI coding agents. Instead of repeating project context every session or hoping the model recalls prior decisions, Memnode stores facts with lineage and supports corrections when something was wrong or outdated. That matters when you ship agent-heavy workflows—support bots, internal tools, or long-running refactor assistants—where drift and silent hallucinated “memory” create real bugs. The catalog entry exposes a hosted streamable-HTTP endpoint, so you can register it in Claude Desktop, Claude Code, Cursor, or other MCP clients without standing up your own bridge on day one. Pair it with your agent skills for planning and code review: memory holds stable constraints (stack choices, API contracts, user preferences) while skills handle execution. Treat Memnode as infrastructure, not a substitute for git, docs, or ticket systems—use it where session continuity and accountable updates beat raw chat history.
- Hosted streamable-HTTP MCP at https://api.memnode.dev/mcp (no local server required for remote use)
- Persistent memory with lineage so you can see how facts evolved
- Correction workflow so agents can fix wrong memories instead of blindly appending
- Inspectable store—audit what the agent remembered before you trust it in production
- Version 0.1.0 MCP server in the official catalog schema
Memnode by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --transport http memnode https://api.memnode.dev/mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Transport | HTTP |
|---|---|
| Auth | None |
What it does
Give Claude Code or Cursor a durable memory layer with traceable edits instead of stuffing everything into the context window.
Who is it for?
Best when you're running long-horizon agent workflows and need accountable, editable memory beyond the current chat.
Skip if: Skip if you only need one-off codegen with no cross-session state, or anyone unwilling to curate what gets stored in agent memory.
What you get
After you register the Memnode MCP endpoint, agents read and update durable memories with visible history and explicit corrections instead of fragile chat-only recall.
- Registered hosted Memnode MCP connection in your agent client
- Persistent memory records agents can read, inspect, and correct across sessions
By the numbers
- Catalog version 0.1.0
- Remote transport: streamable-http at https://api.memnode.dev/mcp
- Capabilities called out in catalog: persistent memory, lineage, correction, inspectability
Recommended MCP Servers
0Latency MemoryPersistent memory layer for AI agents.
0nMCP — Universal AI API OrchestratorUniversal AI API Orchestrator — 1,554 tools, 96 services.
0xHumans Protocol MCPMCP for AI agents: financing, skills, lending on Base1k Patient Mcp1k patient MCP server
1trippulse1trip PULSE: 21-tool AI travel planner.
3D AI Agent Avatar3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.89How it compares
Hosted memory MCP for agents—not a vector DB skill or a generic note-taking integration.
FAQ
Who is dev.memnode/memnode for?
Developers shipping agent-assisted products who want durable, auditable memory in Claude Code, Cursor, or other MCP clients.
When should I use dev.memnode/memnode?
Use it during Build when your agent must retain project facts, preferences, and corrections across many sessions without bloating every prompt.
How do I add dev.memnode/memnode to my agent?
Add the remote MCP server URL https://api.memnode.dev/mcp (streamable-http) in your client’s MCP settings, then invoke memory tools from your agent session.