
What's Loaded MCP server
What fills your agent's context window before a session starts: skill descriptions, memory files.
0 stars35 downloads/wk
Reviews
Write oneNobody has reviewed What's Loaded yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
What's Loaded tools (5)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
context_budgetThe headline answer: how much of the context window is consumed before the conversation
duplicate_skillsSkills whose name appears more than once (same skill installed from several sources).
mcp_serversEvery MCP server configured across the agent clients on this machine, and which config
memory_filesCLAUDE.md / AGENTS.md files that load in full every session, including files pulled in by
skill_costsSkills ranked by how many tokens their always-loaded description costs. The top of this
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 14 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How What's Loaded compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 83% of 4,460 AI and agents servers
- Tools
- 5
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 35
- more than 25% of 1,538 AI and agents servers with a package
What its tools let an agent do: 5 read
Install What's Loaded in Claude Code, Cursor or VS Code
Runs npx -y whats-loaded-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add whats-loaded-mcp -- npx -y whats-loaded-mcp
What the publisher says
From the What's Loaded repository's README, as published. We do not edit it. Read it on GitHub
whats-loaded-mcp
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.
Why
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 half your window before the first message.
Nothing surfaces this. You notice it as sessions that compact sooner than they used to, and you have no idea which of the things you installed six months ago is responsible.
On the machine this was written on:
# Context budget — cost before you type a single character
**~95,316 estimated tokens always loaded.**
For scale: ~47.7% of a 200K window, ~9.5% of a 1M window.
| Source | Count | Est. tokens |
|----------------------------------------------|------:|-------------:|
| Skill descriptions | 1,767 | 92,884 |
| Memory files (CLAUDE.md/AGENTS.md + imports) | 3 | 2,432 |
| MCP servers configured | 10 | not measured |
| **Total measurable** | | **95,316** |
> **79 duplicate skill names** are costing ~9,435 tokens.79 names were installed more than once — the same skill picked up from several sources, like agent-browser appearing three times from three authors. But a shared name does not always mean a redundant copy: on that install only 34 groups were byte-identical (~1,523 tokens genuinely recoverable), while 45 shared a name and differed in content — different work wearing the same label, where deleting a copy loses something. duplicate_skills compares content hashes and reports those two groups separately, so the cleanup advice is safe to act on rather than merely impressive.
Tools
Install
Claude Desktop (one-click, no terminal): download the latest whats-loaded-mcp-.dxt from Releases and open it with Claude Desktop (double-click, or Settings → Extensions → Install Extension…). The server and its dependencies ship inside the bundle — no npm, no Node install.
Register with Claude Code (available in every session):
claude mcp add --scope user whats-loaded -- npx -y whats-loaded-mcpOr in any MCP client config:
{
"mcpServers": {
"whats-loaded": {
"command": "npx",
"args": ["-y", "whats-loaded-mcp"]
}
}
}From source
git clone https://github.com/stcmain/whats-loaded-mcp.git
cd whats-loaded-mcp
npm install && npm run build
# then point your client at node /path/to/whats-loaded-mcp/dist/index.jsShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
What's Loaded: common questions
- Is What's Loaded MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the What's Loaded safety report
- How do I install What's Loaded?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does What's Loaded need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is What's Loaded maintained?
- The last commit was 55 days ago (2026-09-10). The latest release is v0.2.5.
- What can I use instead of What's Loaded?
- Servers from other publishers that do the same job: Basic Memory MCP server, Watch Skill MCP server and Pm Claude Skills MCP server.
- How does What's Loaded compare with other AI and agents MCP servers?
- safety score 89/100 (higher than 83% of 4,460 AI and agents servers); tools 5 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to What's Loaded
Same job from other publishers: the closest match first, then the best rated.
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- Watch SkillWatch video and live sessions, keep timestamped evidence, and verify an agent's own work.not reviewedEstablishedB
- Pm Claude Skills1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.not reviewedEstablishedA
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
- MCP Server for WinDbg Crash AnalysisA Model Context Protocol server for Windows crash dump analysis using WinDbg/CDBnot reviewedEstablishedA