Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Recall, check, search, timeline, and graph tools for fiction writers via Seizn Memory v3.
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。
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。
选择你使用的 AI 应用,然后复制设置。
SEIZN_API_KEY, SEIZN_API_BASE_URL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
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": {
"author": {
"command": "npx",
"args": [
"-y",
"@seizn/author-mcp-server"
],
"env": {
"SEIZN_API_KEY": "your-value",
"SEIZN_API_BASE_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add author --env SEIZN_API_KEY=your-value --env SEIZN_API_BASE_URL=your-value -- npx -y @seizn/author-mcp-server运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"author": {
"command": "npx",
"args": [
"-y",
"@seizn/author-mcp-server"
],
"env": {
"SEIZN_API_KEY": "your-value",
"SEIZN_API_BASE_URL": "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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"author": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@seizn/author-mcp-server"
],
"env": {
"SEIZN_API_KEY": "your-value",
"SEIZN_API_BASE_URL": "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。
SEIZN_API_BASE_URL env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。
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8日
注册名称已通过 GitHub 账户 litheonhq 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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。
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。
你需要填写:SEIZN_API_KEY
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)。
GitHub 仓库最后更新于–,最新版本(0.1.1)于6个月前进入注册中心。
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 Node.js。
同一分类中有:Context7, Codebase Memory, Exa
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
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
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。
MCP server exposing Seizn Author canon recall, conflict check, semantic search, timeline, and relationship graph tools to any MCP-compatible AI agent (Claude Desktop, Claude Code, Cursor, Cline, Continue, Zed, etc.).
Bring Seizn canon into the AI tool you already use. No new editor required.
When connected, your AI agent gains six tools:
| Tool | Purpose |
|---|---|
seizn_author_recall | Get canon for a named entity (character, place, object, rule, event, promise) — returns last 3 mentions, current state, pending conflicts |
seizn_author_check | Check a passage of prose for canon conflicts (P1 critical / P2 warning / P3 stylistic) |
seizn_author_remember | Approve a fact as canon (writer-confirmed source of truth) |
seizn_author_search | Semantic search across all project entities |
seizn_author_timeline | Chapter-by-chapter beats, optional range filter |
seizn_author_graph | Relationship graph subset rooted at an entity |
All tools call the Seizn Author REST API (/api/v1/*) with your Bearer token.
Generate one at https://seizn.com/dashboard/account/api-keys (Free tier: 100 calls/day, BYOK required).
npm install -g @seizn/author-mcp-server
Or use npx:
npx @seizn/author-mcp-server
Add to claude_desktop_config.json:
{
"mcpServers": { "seizn-author": { "command": "npx", "args": ["-y", "@seizn/author-mcp-server"], "env": { "SEIZN_API_KEY": "sk_seizn_..." } } } }
claude mcp add seizn-author -e SEIZN_API_KEY=sk_seizn_... -- npx -y @seizn/author-mcp-server
See your client's MCP server documentation. The package supports:
| Env var | Default | Description |
|---|---|---|
SEIZN_API_KEY | (required) | Bearer token from seizn.com/dashboard/account/api-keys |
SEIZN_API_BASE_URL | https://seizn.com/api/v1 | Override for staging or self-hosted |
In your AI chat:
'Recall everything Seizn knows about Seoyun in project ch7-draft.'
→ invokes
seizn_author_recallwith name=Seoyun
'Check this scene for canon conflicts: ...'
→ invokes
seizn_author_checkwith the pasted text
'Show me the timeline from Ch.5 to Ch.7.'
→ invokes
seizn_author_timelinewith from=ch5, to=ch7
The AI decides when to call each tool based on the conversation. You don't have to remember tool names.
| Plan | Quota | Price |
|---|---|---|
| Free | 100 recall calls/day | $0 |
| Indie | 1,000 calls/month | $9/month |
| Pro | 10,000 calls/month | $19/month |
| Studio | 100,000 calls/month + 5 API keys per user | $99/month |
| Studio Managed (Q3+) | + 500 managed Opus calls/month | $299/month |
| Enterprise | Volume + SOC 2 + SSO | Custom |
Track 2 plan covers Track 2 surface (API + MCP) only. Seizn Author has separate plans for the web dashboard (Track 1, KRW) and the Tauri desktop app (Track 3, KRW). One Stripe customer holds multiple subscriptions, billed independently. See https://seizn.com/pricing for cross-track upsell details.
No subscription required for AI inference. Tools split into two groups:
| Tool | Backend LLM | Needs BYOK? |
|---|---|---|
seizn_author_recall / _remember / _graph / _search | ❌ DB only | ❌ Works on Free, no key needed |
seizn_author_check / _timeline | ✅ Sonnet/Opus | ✅ BYOK or Studio Managed |
The Seizn subscription covers the canon backend and recall infrastructure. The two AI-enhanced tools (check, timeline) require either your own LLM key (BYOK, any tier) or Studio Managed ($299/mo) which includes 500 Opus calls.
Your host AI agent's LLM is separate. Whether you use Claude Pro/Max subscription via Claude Code/Desktop, Cursor Pro, or BYOK in Cline/Continue — the host handles its own LLM cost. Seizn doesn't double-charge.
See https://seizn.com/pricing for full details.
While the package is on 0.x.y we may ship breaking changes on minor bumps (0.2.0 etc.) — we'll call them out clearly in CHANGELOG.md. Once we tag 1.0.0, strict semver applies: major = breaking, minor = additive, patch = fix-only.
Each release is published with a matching GitHub tag (v0.1.0, …) and a CHANGELOG.md entry.
MIT © Litheon LLC
https://github.com/litheonhq/seizn/issues (label: track-2-platform)