原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

TokenKnows

作者:johnnywuj81版本 0.3.0i★ –i在你的电脑上运行
注册名称io.github.johnnywuj81/tokenknows

安装

概览

作者提供的说明(英文原文)

Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 搜索与 AI 记忆
  • 你需要填写:TOKENKNOWS_API_TOKEN

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: TOKENKNOWS_API_BASE, TOKENKNOWS_API_TOKEN, TOKENKNOWS_DEFAULT_PROJECT, TOKENKNOWS_WEB_BASE

标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。

你需要

  • PyPI已安装 Python 的 uv(用于 uvx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "tokenknows": {
      "command": "uvx",
      "args": [
        "tokenknows-mcp"
      ],
      "env": {
        "TOKENKNOWS_API_BASE": "your-value",
        "TOKENKNOWS_API_TOKEN": "your-value",
        "TOKENKNOWS_DEFAULT_PROJECT": "your-value",
        "TOKENKNOWS_WEB_BASE": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add tokenknows --env TOKENKNOWS_API_BASE=your-value --env TOKENKNOWS_API_TOKEN=your-value --env TOKENKNOWS_DEFAULT_PROJECT=your-value --env TOKENKNOWS_WEB_BASE=your-value -- uvx tokenknows-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "tokenknows": {
      "command": "uvx",
      "args": [
        "tokenknows-mcp"
      ],
      "env": {
        "TOKENKNOWS_API_BASE": "your-value",
        "TOKENKNOWS_API_TOKEN": "your-value",
        "TOKENKNOWS_DEFAULT_PROJECT": "your-value",
        "TOKENKNOWS_WEB_BASE": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "tokenknows": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "tokenknows-mcp"
      ],
      "env": {
        "TOKENKNOWS_API_BASE": "your-value",
        "TOKENKNOWS_API_TOKEN": "your-value",
        "TOKENKNOWS_DEFAULT_PROJECT": "your-value",
        "TOKENKNOWS_WEB_BASE": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • TOKENKNOWS_API_BASE env
    Self-hosted TokenKnows backend URL
  • TOKENKNOWS_API_TOKEN 机密 env
    API token (tkk_...) or JWT bearer for the backend; create one in the web UI under Project Settings - MCP Access (optional for default local deployments)
  • TOKENKNOWS_DEFAULT_PROJECT env
    Default project_id for event submission and distill
  • TOKENKNOWS_WEB_BASE env
    Web UI base URL used to build view_url links returned by distill/list tools (login required to open them)

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 johnnywuj81 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 7258 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 7258 个服务器的 16% 更新
  • 基础检查结果等于或优于此分类中其他 7258 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

TokenKnows 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

你需要填写:TOKENKNOWS_API_TOKEN

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.3.0)于5个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它?

同一分类中有:Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者:upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT今天更新
安装

Codebase Memory

作者:DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT20天前更新
安装

Exa

作者:exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT上个月更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

TokenKnows

Distill AI coding sessions into living knowledge — weekly reports, ADRs, incident reviews, books, agent skills, and a knowledge graph.

English | 简体中文


What is TokenKnows?

You spend hours pair-programming with Claude Code, Codex, and Cursor. The decisions, bug hunts, and design trade-offs from those sessions evaporate the moment the terminal closes. TokenKnows captures them automatically and distills them into structured, evidence-linked knowledge assets:

capture (6 collectors) → distill (5-stage LLM pipeline) → assets (7 document types) → review / redact / publish

  • 📡 Captures everything — Claude Code, Codex, Cursor, VS Code, GitHub PRs/commits/issues, and local docs, all via local file watchers and API polling. No webhooks, no tunnels.
  • 📝 Seven asset types — weekly reports, tech designs, ADRs, incident reviews, long-form books, reusable agent skills (SKILL.md), and an entity knowledge graph.
  • 🔗 Evidence-linked — every paragraph traces back to the original PR / conversation / commit, ranked by cosine × trust × recency across ≥2 sources.
  • 🔒 Local-first, zero egress by default — a three-layer LLM egress gate (instance ∧ project ∧ task) with full audit logging. Pair it with Ollama and run the whole pipeline with zero cloud keys.

Demo

WorkbenchDocument page
Evidence drawerPublish receipt + version diff

▶ Full walkthrough: engineering_handoff/walkthrough.mp4 (5 min, Chinese narration + subtitles)

All 12 screens

1 Workbench2 Event drawer3 Document list4 Document page
5 Evidence drawer6 Regenerate dialog7 Review8 Redaction
9 Publish dialog10 Publish receipt + diff11 LLM egress12 Admin

Install the plugin

Prerequisite: the TokenKnows backend at http://localhost:8001 and the web UI at `http://localhost:5173` (see Quick start), plus uv (the plugin pulls the MCP server from PyPI via uvx). All plugin env vars have working local defaults — export TOKENKNOWS_API_BASE / TOKENKNOWS_API_TOKEN / TOKENKNOWS_DEFAULT_PROJECT / TOKENKNOWS_WEB_BASE only for non-default setups. Register/login in the web UI and create an API token under Project Settings → MCP 接入 when your backend requires auth.

PlatformHow
Claude Code/plugin marketplace add johnnywuj81/tokenknows → /plugin install tokenknows@tokenknows — full walkthrough in tokenknows-plugin/README.md (5-minute quickstart)
Codexcodex plugin marketplace add johnnywuj81/tokenknows → codex plugin add tokenknows@tokenknows (loads skills, commands and the MCP server; local-clone alternative in codex-plugin/README.md)
CursorAdd the tokenknows MCP block to ~/.cursor/mcp.json (uvx config example in code/tokenknows-mcp/README.md)
VS CodeDownload the .vsix from Releases → code --install-extension tokenknows-vscode-*.vsix

The plugin gives your AI tool MCP tools (submit_session_events, distill_document, list_assets, get_asset, get_asset_chapters, search_entity) plus slash commands like /tokenknows:weekly and /tokenknows:adr.

Quick start

# 1. (Optional but recommended) Ollama — fully local inference, zero cloud keys

ollama serve & ollama pull minimax-m2:cloud # or gpt-oss:20b, qwen2.5, ...

2. Backend (FastAPI + SQLite persistence + 3-layer LLM egress gate)

cd code/tokenknows-api python3 -m venv .venv && .venv/bin/pip install -e ".[dev]" cp .env.local.example .env.local # defaults to Ollama; edit to add cloud providers .venv/bin/uvicorn app.main:app --host 127.0.0.1 --port 8001

3. Frontend (React 19 + Vite)

cd code/tokenknows-web npm install npm run dev

open http://localhost:5173 — talks to the real backend (mocks are opt-in via ?msw=1)

(Optional) seed demo data

./engineering_handoff/demo-seed.sh

Platform support: macOS — full experience (collectors auto-start via launchd). Linux — backend, frontend, and collectors all run manually (python3 plugins/ /sync.py --watch); the launchd scripts don't apply. Windows — untested; WSL2 recommended.

Data collectors

All local — no ngrok, no public webhooks. On macOS they restart on crash and on reboot (launchd).

CollectorSourceMode
claude-code~/.claude/projects/*.jsonl30s polling, incremental offsets
codex~/.codex/sessions/**/rollout-*.jsonl30s polling, incremental offsets
cursorCursor's state.vscdb (read-only SQLite)60s polling
githubGitHub REST API · PRs / issues / commits5min polling (gh auth token)
vscodeVS Code extension onDidSaveTextDocumentbuffered, 10s flush
local-docs~/Documents .md .txt .pdf (watchdog)realtime, 2s debounce
./scripts/launchd/install.sh          # macOS: install all 5 Python collectors as LaunchAgents

launchctl list | grep com.tokenknows tail -f ~/Library/Logs/tokenknows/*.log

Every event carries a trust score (0.6 × source_authority + 0.4 × extraction_confidence); the evidence stage ranks citations by 0.6 × cosine + 0.25 × trust + 0.15 × recency and enforces ≥2 distinct sources.

Architecture

Collectors feed an event store (SQLite). A five-stage pipeline (collect → outline → content → evidence → assess) turns events into assets. The LLM Gateway unifies four providers (Anthropic / OpenAI / MiniMax / Ollama) with per-task routing and fallback chains — and refuses any cloud call unless all three egress switches are on.

CI

WorkflowRunnerTrigger
ci.ymlubuntu-latest (GitHub-hosted)push to main + every PR
ci-macos.ymlself-hosted macOS ARM64maintainer pushes to main only — never runs external PR code

Privacy & local-first

  • Zero egress by default — cloud LLM calls require the instance and project and task switches all on
  • Bring your own keys; the audit log never leaves your machine
  • One-click kill switch drops the instance into fully-offline mode

Details: PRD §6.7 data residency & egress control (Chinese).

Documentation

TopicDoc
Product requirements, user journeysPRD (zh)
Technical design, API, schemaTDD (zh)
Macro architecture & milestonesArchitecture (zh)
Per-screen engineering decisionsTaskTechDesign (zh)
Pixel-level UI mockupsmockups/ — open in a browser

Most in-depth docs are in Chinese (the project's working language). Code comments are predominantly Chinese too; issues and PRs in English or Chinese are both welcome.

Community

CONTRIBUTING · Roadmap · Code of Conduct · Security policy · Issues

License

MIT © 2026 johnnywuj81

问 PopNx