MCP Tools DirectoryAbout this integration
What fills your agent's context window before a session starts: skill descriptions, memory files.
- Transport
- stdio
- Authentication
- none
- Initial setup
- none
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.2.5
- Package
- whats-loaded-mcp
- Last compatibility test
- Not independently tested
Connect your agent
whats-loaded-mcpThe server reads local agent and client configuration files. Publisher documentation says it emits environment variable names but not values and does not measure MCP tool definitions. The pinned source manifest reports 0.2.6 while the existing listing's separately sourced published version remains 0.2.5. Publisher documentation and executable manifest were reviewed; the package was not executed or independently security-audited.
Capabilities: Estimate context used by skill descriptions and memory files, Identify duplicate installed skills, Inventory configured MCP servers without exposing environment values
Connected profiles
Additional details
io.github.stcmain/whats-loaded-mcp
Source ↗ · Checked 2026-09-170.2.5
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17whats-loaded-mcp
Source ↗ · Checked 2026-09-190.2.6
Source ↗ · Checked 2026-09-19Node.js 18+ executable package configured as a user-scoped or client-managed MCP process; publisher documents bounded local file inspection without child processes or outbound network calls.
Source ↗ · Checked 2026-09-19Publisher explicitly states the only optional setting takes no credentials; no authentication is required for the local stdio process.
Source ↗ · Checked 2026-09-19Configure an MCP client to launch npx -y whats-loaded-mcp; WL_PROJECT_ROOT may optionally select the project directory.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19