KogCat
AI makes the answer smoother. KogCat makes the judgment sound.
English | 中文 · Website: https://www.kogcat.com
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx kogcat-mcp==0.46.2Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add com.kogcat-kogcat-mcp -- uvx kogcat-mcp==0.46.2在終端機中執行。
{ "mcpServers": { "com.kogcat-kogcat-mcp": { "command": "uvx", "args": [ "kogcat-mcp==0.46.2" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
AI makes the answer smoother. KogCat makes the judgment sound.
English | 中文 · Website: https://www.kogcat.com
Local-first judgment layer: counter-examples & blind spots from your own knowledge base.
A local-first judgment calibration layer for Claude Code and Codex. Before you act on an AI answer, it surfaces the counterexamples, the boundaries, the blind spots — drawn from a knowledge base that lives on your machine. It won't replace your model. It won't slow you down. The call stays yours.
"I read 30 minutes a day but nothing sticks. Should I take more detailed notes?"
Plain AI — Try the Cornell method, highlight key passages, add Anki for spaced repetition.
KogCat — More notes will likely make it worse. The bottleneck isn't capture. It's retrieval. Your knowledge base holds a claim you marked high-confidence: the "I get it" feeling while re-reading is the least reliable signal of real recall. So try this once — finish a section, close the book, write what you remember. Then compare it to what you thought you had.
Built for judgment, not lookup. KogCat speaks up for the calls that cost you when they're wrong — decisions, tradeoffs, comparisons, critiques, strategy. It stays quiet for the rest: lookups, definitions, code, summaries, translation. And even on a judgment call, it adds a note only when it sees something the model didn't.
/kogcat:query <question> puts your knowledge base first: a conclusion, the conditions that change it, a next step.Claude Code
/plugin marketplace add KogCat/cc-kogcat
/plugin install kogcat
Codex
codex plugin marketplace add KogCat/cc-kogcat
codex plugin add kogcat@kogcat
After installing, fully quit and reopen Claude Code (or restart Codex). The first-run download only starts on the next fresh session — the install command alone won't begin it.
On first launch, KogCat quietly downloads its engine (~40 MB) and embedding model (~90 MB). Once. About a minute on a good connection. Keep working while it does — run /kogcat:status anytime to watch each piece come online.
KogCat's calibration engine runs as a local sidecar; the Claude Code / Codex plugin is just one client of it. Any MCP-capable tool — Cursor, Cline, Zed, VS Code, Claude Desktop — can use the same engine through a standalone stdio MCP server.
Add this to your client's MCP config (field names vary slightly by client; most use an mcpServers map):
{
"mcpServers": {
"kogcat": {
"command": "uvx",
"args": ["kogcat-mcp"]
}
}
}
Requires uv, on macOS (Apple Silicon) or Windows x86_64 (same engine, same platforms as below). On first run it downloads the engine + embedding model and registers a background sidecar — the same one-time setup as the plugin, shared by every client on the machine. It exposes the knowledge-base tools (search, node, edges, calibrate, calibrate_review, and the memory_* family) for your model to call.
What you give up vs. the plugin. The Claude Code / Codex plugin adds two host conveniences a generic MCP client has no hook for: calibration that fires automatically on judgment questions, and a memory index injected into context at session start. With a standalone server your model reaches the same knowledge base, but it's the model that decides to call those tools — or you ask it to "use KogCat" — rather than a hook firing them for you. You never type the tool names (search, calibrate_review, memory_*); they're the model's to call.
No account. No subscription. No one else holding your knowledge.
Automatic calibration needs no command.
PATH — already there on macOS; on Windows, install it yourself (tick Add python.exe to PATH)FSL-1.1-MIT — see LICENSE. Converts to MIT two years after each release.
Local-first judgment layer: counter-examples & blind spots from your own knowledge base.
{ "mcpServers": { "com.kogcat-kogcat-mcp": { "command": "uvx", "args": [ "kogcat-mcp==0.46.2" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Kogcat 透過 stdio 在本機執行。
上次檢查時間:2026-11-08。 Local-first judgment layer: counter-examples & blind spots from your own knowledge base.