About 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 tools including get_context, add_memory, search_decisions, and team workspaces
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.conxt.dev/mcp/claude mcp add --transport http conxt-engine https://mcp.conxt.dev/mcp/{"mcpServers":{"conxt-engine":{"type":"http","url":"https://mcp.conxt.dev/mcp/"}}}Open in Cursor{"servers":{"conxt-engine":{"type":"http","url":"https://mcp.conxt.dev/mcp/"}}}Open in VS Code{"mcpServers":{"conxt-engine":{"type":"http","url":"https://mcp.conxt.dev/mcp/"}}}{"mcpServers":{"conxt-engine":{"serverUrl":"https://mcp.conxt.dev/mcp/"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://mcp.conxt.dev/mcp/Auth requiredTools
17| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | |
| query | string | Yes | |
| user_id | string | No |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.