GRAFOMEM CGR Capture

Overview

GRAFOMEM CGR Capture is a Model Context Protocol (MCP) server: Record agent judgments and their real outcomes on GRAFOMEM Cloud. Capture now, score later. Because it speaks the Model Context Protocol, AI assistants can use GRAFOMEM CGR Capture as a set of callable tools instead of you copy-pasting between apps.

It runs locally: the Python package grafomem-cgr (via uvx) speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need GRAFOMEM_CGR_TENANT_KEY, GRAFOMEM_CGR_TENANT. The current release is v0.1.0, published under the MIT license, with source at GNS-Foundation/grafomem on GitHub.

On mcp.site, GRAFOMEM CGR Capture sits in the AI & Agents category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain GRAFOMEM CGR Capture for grafomem.com, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "grafomem_cgr_capture": {
      "command": "uvx",
      "args": [
        "grafomem-cgr"
      ],
      "env": {
        "GRAFOMEM_CGR_TENANT_KEY": "<grafomem-cgr-tenant-key>",
        "GRAFOMEM_CGR_TENANT": "<grafomem-cgr-tenant>"
      }
    }
  }
}

Requires GRAFOMEM_CGR_TENANT_KEY, GRAFOMEM_CGR_TENANT