Context7
作者：upstash
Up-to-date docs for AI agents
电脑或云端★ 64,224MIT今天更新
安装
Agentimus
概览
作者提供的说明（英文原文）
heera.it via Agentimus: AI readiness, traffic, request log, search & index reports, by approval.
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。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
- 使用情况i尚未统计★ –
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: 在云端运行
- 传输方式: Streamable HTTP
- 分类: 搜索与 AI 记忆
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
- 在作者的服务器上运行：你向它提出的内容会经过他们的服务器。
- 注册中心没有列出需要填写的密钥。
你需要
- 在云端运行无需安装任何东西，通过互联网连接
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 …”。
适用于网页版、桌面版和手机版 Claude：
- 打开 Settings → Connectors
- 点击 Add custom connector
- 粘贴下面的地址，然后点击 Add
- 如果要求登录，请登录作者的服务
https://heera.it/wp-json/agentimus/v1/mcp在终端中运行这条命令
claude mcp add --transport http agentimus https://heera.it/wp-json/agentimus/v1/mcp或者自己复制设置
粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json
{
"mcpServers": {
"agentimus": {
"url": "https://heera.it/wp-json/agentimus/v1/mcp"
}
}
}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。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"agentimus": {
"type": "http",
"url": "https://heera.it/wp-json/agentimus/v1/mcp"
}
}
}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。
ChatGPT 只能连接互联网上的服务器：
- 打开网页版 ChatGPT → Settings → Connectors (Apps)
- 点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
- 粘贴下面的地址，起个名字，然后保存
- 如果要求登录，请登录作者的服务
https://heera.it/wp-json/agentimus/v1/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上，无需账户。
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
我们还没有读取这个服务器的工具列表；我们会轮流检查各个端点。
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
注册名称已通过域名 heera.it 验证（注册中心会核实域名所有权）
- … 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
- … 尚未检查
端点有响应
尚未检查；我们会轮流检查各个端点
- … 尚未检查
使用 OAuth 登录
尚未检查；我们会轮流检查各个端点
- … 尚未检查
工具描述中没有隐藏指令
尚未检查；我们会在检查端点时读取工具列表
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 7251 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 7251 个服务器的 27% 更新
- 基础检查结果等于或优于此分类中其他 7251 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
Agentimus 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？
注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端？
它在作者的云端运行。通过互联网连接，无需安装，但你发送的内容会经过作者的服务器。
它还在维护吗？
GitHub 仓库最后更新于–，最新版本（1.33.0）于3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。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。
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
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。
Agentimus
Two things for the age of AI agents. (1) Make any WordPress site legible and citable — llms.txt, a full-text edition, markdown delivery, JSON-LD, content-signal robots rules — then score how AEO/GEO-ready it is and what to fix next. (2) Let the AI tools you already use operate the site over MCP: a Model Context Protocol server ships inside the plugin, so Claude Code, Claude Desktop, Cursor or Codex can read your readiness/traffic/bot data and — at the level you choose — draft, edit and publish posts and pages, each write running as the signed-in user, permission-checked and audited. Lightweight, no SEO bloat, no framework.
Live on WordPress.org: https://wordpress.org/plugins/agentimus/
📖 Documentation: https://heera.github.io/agentimus/ — full user manual and developer reference.
Install
- From your dashboard — Plugins → Add New → search "Agentimus" → Install → Activate.
- From WordPress.org — https://wordpress.org/plugins/agentimus/.
- From source — clone this repo, run
npm install && npm run build(producesassets/admin/), then copy or symlink the folder intowp-content/plugins/.
What it does
| Signal | Endpoint / output | |
|---|---|---|
| Link index | /llms.txt | |
| Full-text edition | /llms-full.txt | |
| Markdown delivery | / .md; Accept: text/markdown on the page URL is opt-in (agentimus_negotiate_markdown filter, off by default — a CDN caches one answer per URL) | |
| Structured data | JSON-LD WebSite + Person/Organization + BlogPosting + BreadcrumbList (defers to SEO plugins) | |
| Topics for AI | Per-page topics → JSON-LD keywords + about DefinedTerm entities (with optional Wikidata sameAs via the agentimus_topic_links filter) + a Topics: line in / .md; static (editor) or derived from tags & categories | |
| AI description | Per-page one-line summary → JSON-LD description + the / .md lead + an authoritative (replaces the theme's, defers to an SEO plugin); editor-set, falling back to the excerpt or a ~30-word content summary. A settings sub-toggle can limit it to the JSON-LD + .md surfaces only | |
| Writing assistant (opt-in) | The quill button on every Agentimus screen opens a drawer: brief → editable outline → the article writes every section in parallel (/assistant/compose-section per part + one dressing call; long posts aren't capped by a single response, a failed part retries alone, and a mid-write reload resumes) → full preview (title, real blocks, AI description, topics, suggested categories/tags, draft/pending choice) → Create draft lands straight in the editor. Drafts are written to the same bar the Readability panel grades — a liftable opening summary, quotable paragraph lengths, plain sentences, cited sources (readability_rules(), its paragraph cap derived from PageCheck's own threshold). Creation only: a drafted post opens in the editor, where revision lives (the drawer's old edit path and its safe-block gate are gone — that gate existed because a drawer can only handle blocks it wrote itself, and declining real posts was the wrong answer to the right problem). Shapes are per type: Assistant::shape_for() writes a hierarchical type as a PAGE — no invented sections, no image slots, no taxonomy, [placeholder] where only the owner knows a fact — and MCP creation runs the same prompts. Images arrive as alt-filled placeholder blocks: Generate image from the alt text on every image block, a Featured image (AI) sidebar panel, and Ask AI at three scopes — one block, a multi-block selection (BlockSettingsMenuControls, since InspectorControls never renders during multi-select), or a document planner that returns an outline-scoped edit list applied one at a time against a re-read anchor map (replaceBlocks mints new clientIds, so stale ids silently no-op). Server-side it's the same audited write path as MCP (Assistant.php → ContentWriter), gated by enable_agent_writes + the user's own caps, with every generation routed through Assist::generate() (rate-limited, Content-Guidelines-aware) and status clamped to `draft\ | pending` — the assistant can never publish |
| Write with AI (opt-in) | Editor "Draft with AI" writes the AI description and "Suggest with AI" fills Topics, both from the page's own content; "Fix with AI" drafts a fix per AI-Readability warning (opening summary inserts in one click, the rest copy-only). Routes through the WordPress 7.0 AI Client — your own provider key, never handled by the plugin; hidden until a provider is configured under Settings → Connectors | |
| AI abilities | Two tiers via wp_register_ability, each ability permission-gated like its source screen. Read (always registered): agentimus/read-readiness, read-findings (the Findings screen's own ranked front door, bounded at 12 rows), read-audience (people and machines counted apart, never summed), read-ai-visibility, read-ai-traffic, read-request-log, read-edge-traffic, read-search-visibility, read-search-performance, read-search-opportunities, read-google-index (optional url answers from stored checks, no quota), identify-bot, read-content-issues (which pages need work, what each is flagged for, and how old that verdict is — the list read-findings summarises), read-terms (the categories and tags this site already uses, by the exact names the write tools expect), check-page, preview-schema/-markdown, scan-exposed-files, suggest-internal-links, read-settings, check-focus, read-citation-products, suggest-citation-questions, search-media (title + _wp_attachment_image_alt, gated on upload_files). Write (registered only while `enable_agent_writes` is on — off by default, requires the MCP server switch, and off means the abilities don't exist on any surface): create-content/update-content (draft-first; categories & tags by name with wp-admin's own creation rules, featured image by attachment ID or sideloaded URL, AI description/topics in the same call), write-description, write-topics, write-search-fields (the focus keyword and the SEO title — the two fields that decide how a page appears in a search result, and the last two an agent could not reach), and apply-fix (enacts a readiness check's own remediation from a closed vocabulary that can only enable documented features). update-settings and save-citation-product need agent_writes_settings, refresh-data and purge-edge-cache need agent_writes_maintenance, and list-content, create-term, update-term, import-media, update-media, trash-content and restore-content need agent_writes_content, all off by default. Scheduling with publish_at needs agent_writes_content and agent_writes_publish. Writes refuse markup that can run in a browser, under any login. status=publish needs agent_writes_publish (the "Publish without your review" extra) plus the user's own publish cap. The MCP card shows these switches as one choice, Off, Read or Write, plus extras (resources/admin/js/agentLevel.js) | |
| MCP server (opt-in) | /wp-json/agentimus/v1/mcp — the WordPress MCP Adapter ships inside the plugin (Composer-vendored, Jetpack-autoloader arbitrated) behind the enable_mcp_server switch (Settings → Discovery, off by default; WP 6.9+). External MCP clients (Claude Code, Claude Desktop, Codex) authenticate with an application password and get exactly the abilities above — the read-only tools, plus the write tools only at the Write level (enable_agent_writes), and four resources (llms.txt, llms-full.txt, discovery.json, the agent card) declared with meta.mcp.uri; a resource whose endpoint is switched off is never registered (the server's self-description says which tier it's running) — the adapter's generic execute-any-ability default server stays suppressed, every call is audited in Agent Access, and toggling off hard-disconnects live clients. At the Off level, the library is never loaded and no endpoint exists | |
| XML sitemap | /agentimus-sitemap.xml — opt-in fallback, generated only when neither WordPress core nor an SEO plugin already provides one (sitemap index + paginated sub-sitemaps) | |
| Crawler policy | robots.txt content-signal + training-crawler blocklist | |
| Discovery layer | /.well-known/discovery.json (+ agent-card.json, mcp.json) | |
| Change feed | /agentimus-changes.json?since= — recently added, updated and removed content as JSON, so an agent fetches only the delta (advertised in discovery.json; on by default) | |
| Crawl enforcement (opt-in) | hard-block (403) denylisted, spoofed-"scanner", or proven-impostor user-agents at the generated endpoints — ACME-safe, off by default; optional bot-identity verification (forward-confirmed reverse DNS + operators' published IP ranges, via an owner-editable Verified-bots registry) so a spoofed bot name can't earn the allowlist and a proven fake is refused |
In the admin
- Findings — one front door for everything open across the site, in the nav with its own count. A single ranked list — pages losing a click they already earn, plus anything the setup checks caught — ordered by what each one costs, every row carrying the button that lands on the fix. The count measures only work you can act on; anything merely waiting on a later report gets a quiet dot instead. Below it, the per-item content worklist: one row per published thing, what it's found for, whether it answers that, and what else it needs.
- Light / dark theme — a toggle showing the mode you're switching *to*. Dark is a hand-tuned palette, not an inversion, with its own dialect per WordPress admin colour scheme (Default keys neutral, Coffee keys brown and gold). A manual pick holds until the operating system next flips, then the device's rhythm wins again; the resolved mode rides on
- AEO/GEO score — one 0–100 score on the dashboard across five rungs (Findable / Readable / Trusted / Optimized / Mentioned), with the single most useful next step; each rung deep-links to where you act on it. Mentioned is opt-in (see Citations) and its weight redistributes across the others when off. A score of 99.6 reads 99 — 100 is earned, never rounded into.
- Work by issue — pick one check and every page it flags opens in Your Content, ranked and paged, rather than a sample of six. Fix what a filtered list was opened for and the row keeps its place, marked done, instead of vanishing before you can see the fix land.
- Reading that does not depend on WP-Cron — the content sweep is scheduled work, and on many hosts WordPress's scheduled jobs never run (a cached page never runs PHP, so the request that would start them never arrives). Agentimus notices when its own jobs are overdue and runs them from the admin screen you are already on, joining core's own lock so it can never double-run a job. A site whose cron works loads nothing extra.
- Optimize your content — per-page citability checks (thin content, something concrete to quote, quotable passages, freshness) over your articles, with a worklist of which pages to improve and a matching read-only panel in the editor. Commerce products, commerce plugins' designated pages (cart/checkout/account — WooCommerce options and FluentCart s
只显示了开头部分；其余内容请在仓库中阅读