MCP setup

Connect your AI agent to your project's living memory. The SoluCortex MCP server lets Claude Code, Cursor and any MCP-compatible client recall your project's approved decisions before it works, and remember what it learns when it's done.

💡 The MCP server is a thin wrapper over the SoluCortex REST API. It runs locally as a subprocess of your agent and speaks MCP over stdio — nothing else to host.

Requirements

A SoluCortex project and its API key (scx_…) and Project ID (UUID). See Quickstart.
uv (recommended) or Docker.

1. Claude Code

One command registers the server with your key baked into its environment:

bash

claude mcp add solucortex \
  -e SOLUCORTEX_API_KEY=scx_your_key \
  -e SOLUCORTEX_PROJECT_ID=your-project-uuid \
  -- uvx solucortex-mcp

Restart Claude Code. The four solucortex_* tools become available — see the tools reference.

2. Claude Desktop / Cursor / Cline

Add SoluCortex to the client's MCP config (claude_desktop_config.json, Cursor mcp.json, etc.):

json

{
  "mcpServers": {
    "solucortex": {
      "command": "uvx",
      "args": ["solucortex-mcp"],
      "env": {
        "SOLUCORTEX_API_KEY": "scx_your_key",
        "SOLUCORTEX_PROJECT_ID": "your-project-uuid"
      }
    }
  }
}

Environment variables

Variable	Required	Description
`SOLUCORTEX_API_KEY`	Yes	Project API key (`scx_…`).
`SOLUCORTEX_PROJECT_ID`	Recommended	Default project UUID. Can be overridden per tool call.
`SOLUCORTEX_URL`	Optional	API base URL. Defaults to `https://solucortex.ai`.

🔒 Never commit your API key. Keep it in the client's env block or a local .env that is git-ignored.

Verify the connection

In your agent, ask it to recall context for a task. It should call solucortex_recall and return your project's memories. If you get an authentication error, re-check the API key and Project ID.

✓ Connected. Your agent now starts each task with the approved context already in place — and can propose new memories when it closes. Next: the tools reference.