Traffalyzer

com.traffalyzer由 traffalyzer.com 發布官方發布者v1.0.0更新於 Oct 29, 2026

SEO & UX audits for your websites: findings, Search Console data, growth plan and site scans.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取資料與分析

概覽

AI 產生的概覽

Traffalyzer 提供的遠端 MCP 端點,讓助理取得網站的 SEO 與 UX 稽核結果,包括問題發現、Search Console 資料和成長計畫。

可以做什麼
取得網站的 SEO 與 UX 稽核發現,包括站點掃描找出的問題和 Search Console 資料,並依據這些結果處理成長計畫。清單未列出個別工具,因此具體操作未在此說明。
適用情境
適合想讓助理檢視網站 SEO 與 UX 狀況、在對話中帶入 Search Console 指標,或直接梳理成長計畫的情境。
執行需求
需要連線到 traffalyzer.com 的遠端 streamable HTTP 端點,不需本機套件或執行環境。清單未宣告身分驗證、環境變數或標頭,但存取站點資料與 Search Console 很可能需要 Traffalyzer 帳號並連結對應資源。
安裝前請注意
此伺服器涉及 Search Console 資料與站點稽核,可能將私密的流量與成效資訊暴露給助理及 Traffalyzer。清單未宣告身分驗證,連線前應確認你的站點存取實際上如何受到保護。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Traffalyzer,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.traffalyzer%2Ftraffalyzer/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "traffalyzer": {
      "type": "http",
      "url": "https://traffalyzer.com/api/mcp"
    }
  }
}

工具

15

list_domains

List domains

List all website projects (domains) in the user's Traffalyzer account, including their domain id, URL, plan status (free or paid) and the latest scan result with its overall score. Call this first — every domain-scoped tool needs a domain id from this list.

無需輸入參數。

next_actions

What to work on next

The prioritised to-do list across ALL of the user's domains in a single call: critical and high-severity issues, open quests, the next unfinished growth-plan step, projects with a missing or stale scan, and missing integrations. Start here when the user asks what to improve, what to do next, or to 'optimise the site' without naming a specific domain — it saves querying every project separately. Each entry names the domain, an id or key to work with, and which tool to call next.

輸入參數limitdomainId

run_scan

Run scan

Start a new SEO/UX scan (crawl) for one of the user's domains. Scans run asynchronously and usually take a few minutes; poll get_scan_status for progress and the resulting scores. If a scan is already in progress, its id is returned instead of starting a duplicate.

輸入參數domainId必填

get_scan_status

Scan status

Status and results of the most recent scan of a domain: whether it is pending, running, completed or failed, the overall score and its sub-scores (technical, on-page, engagement, AI visibility), pages crawled and the number of issues found.

輸入參數domainId必填

search_console_queries

Search Console keywords

Keyword data from Google Search Console for one domain. intent=top returns the strongest keywords, intent=opportunities keywords ranking on positions 5-20 with potential, intent=movers the biggest winners and losers versus the previous period of equal length. Requires the user to have connected Search Console. Responses follow the account language (German by default).

輸入參數limitintentwindowdomainId必填

keyword_history

Keyword history

Month-by-month history of a single keyword from Google Search Console (clicks, impressions, impression-weighted position) plus the pages ranking for it. Use it to see how a query developed, whether it is seasonal, or which page Google shows for it. Pass the query exactly as Search Console lists it. 16 months for paid domains, 3 months otherwise. Requires the user to have connected Search Console. Responses follow the account language (German by default).

輸入參數query必填monthsdomainId必填

search_console_pages

Search Console pages

Page-level Search Console performance for one domain: which pages get clicks and impressions, at which average position. Useful to find the pages that carry the organic traffic and the ones that underperform. Responses follow the account language (German by default).

輸入參數limitwindowdomainId必填

page_report

Page report

A full report for a single page of the domain: search performance, analytics behavior (sessions, bounce rate, engagement time where connected), page classification and its top search queries. Responses follow the account language (German by default).

輸入參數path必填domainId必填

traffic_trend

Traffic trend

Search performance over time for the whole site or a single page — is it getting better or worse, did a change have an effect. Weekly by default, daily with granularity=day when an exact date matters. Includes Plausible visitor data for the same buckets where the integration is connected. Responses follow the account language (German by default).

輸入參數pathwindowdomainId必填granularity

timeline_events

Timeline events

Dated events on the site's history timeline: measures the user logged themselves, completed quests, fixed issues, ticked plan steps, CMS edits, detected wins, scans and Google ranking updates (core, spam …) with their rollout dates. Use it to explain why a curve moved, what was changed when, or whether a measure worked; pair it with traffic_trend. Free domains only get the last 28 days. Responses follow the account language (German by default).

輸入參數pathkindswindowdomainId必填

log_measure

Log measure

Log a change the user made to their website themselves (e.g. 'added internal links to /blog/x', 'new images in the guide') on the history timeline. Traffalyzer then measures its effect automatically: 28 days before vs. 28 days after, adjusted for the rest of the site. Backdating is allowed up to 16 months; old enough entries are measured right away. Free domains can have 3 active measures. Never call this without an explicit user request.

輸入參數datenotepagestitle必填categorydomainId必填

growth_plan

Growth plan

The domain's current growth plan: diagnosis, bottleneck, phases and steps. Without a stepKey the structure with all step keys is returned; with a stepKey the full step including rationale, implementation guidance and verification status. On free domains some step details are locked. Responses follow the account language (German by default).

輸入參數stepKeydomainId必填

quests_and_issues

Quests and issues

The domain's task list: quests (concrete recommendations with implementation guidance and XP rewards) and issues (technical findings from the latest crawl with affected URLs). Use kind=quest or kind=issue; pass an id for full details of a single entry. Responses follow the account language (German by default).

輸入參數idkind必填limitstatusdomainId必填

complete_quest

Complete quest

Mark one of the user's quests as implemented after the recommended change has actually been made. Awards the quest's XP and starts result verification. Only quests with status OPEN can be completed; get quest ids from quests_and_issues with kind=quest. Never call this without an explicit user request.

輸入參數questId必填

complete_plan_step

Complete plan step

Tick off (or un-tick with done=false) a step of the domain's growth plan after the work has actually been done. Awards XP on first completion and starts result verification. Step keys come from the growth_plan tool. Only available on paid domains — the free preview is read-only. Never call this without an explicit user request.

輸入參數donestepKey必填domainId必填

版本歷史

1
  1. v1.0.0最新Sep 19, 2026

評分

已滿足適用檢查項的 72%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分

    請在註冊中心條目中發布圖示。

  • 文件15 分

    請宣告包含 README 的 GitHub 儲存庫,或在 OAuth 受保護資源後設資料中提供 resource_documentation。

  • 授權條款不適用

    託管服務按其提供方的條款使用,因此這裡不要求授權條款。此檢查項不計入百分比。