Conxt Memory Layer
Persistent AI memory layer for developers. Stores decisions, coding rules, preferences, tool choices, and workflows across Claude, ChatGPT, Gemini, Cursor, and Windsurf. 8 MCP…
Overview
MCP.so lists Conxt Memory Layer as an MCP server. The source repository is pgavali0318/conxt-engine. The connection metadata specifies stdio. The listing supplies a remote address for clients that support this connection type. Check the project documentation for access requirements.
MCP server address
Use this endpoint in an MCP client that supports remote servers. Follow the project documentation for authentication and permissions.
https://mcp.conxt.dev/mcp
Getting started
Add the documented server address in your MCP client, then follow the project documentation for authentication.
Compatibility and requirements
stdio
Frequently asked questions
Where can I find the documentation for Conxt Memory Layer?
Open the project documentation linked on this page. The MCP.so listing is also included under Sources and documentation.
How do I connect to Conxt Memory Layer?
The source lists https://mcp.conxt.dev/mcp as the remote address. Check the project documentation for authentication.
What connection type or credentials do I need?
The source lists stdio. Check the project documentation for the exact client configuration and access requirements.
Sources and documentation
Related MCP servers and skills
- PMB (Personal Memory Brain) | Local first memory layerMCP server
- MGC Blackbox – Local Encrypted Execution LayerMCP server
- Becomer: LLM-agnostic persistent memory API. Store and recall memories across GPT, Claude, Gemini, or any model — zero tokens per recall.MCP server
- Memory MCP ServerAgent skill
- Claude Memory SkillAgent skill
- plugged.in MCP Hub — Proxy · Knowledge · Memory · ToolsAgent skill