whats-loaded-mcp

stcmain/whats-loaded-mcp
★ 0 stars JavaScript AI/LLM Updated today
Shows what consumes your agent's context window before the conversation starts — skill descriptions, memory files and their imports, configured MCP servers. Read-only, MIT.
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "whats-loaded-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "stcmain/whats-loaded-mcp"
      ]
    }
  }
}

README Excerpt

**Your context window is already half spent before you type.** An MCP server that shows what is consuming it — every skill description, every memory file and its hidden `@imports`, every configured MCP server — ranked by cost, with duplicates called out. Skills are cheap to install and permanently expensive to keep. A skill's `name` and `description` go into the system prompt of **every session, forever** — only the body is loaded on demand. Install a few hundred and you've quietly mortgaged hal

Tools (6)

WL_PROJECT_ROOTcontext_budgetduplicate_skillsmcp_serversmemory_filesskill_costs

Topics

ai-agentsclaudeclaude-codecontext-windowdevtoolsmcpmcp-servermodel-context-protocoltoken-optimizationtypescript