GlockApps — Inbox Placement Testing

com.glockapps由 glockapps.com 發布官方發布者v1.0.0更新於 Oct 27, 2026

Inbox placement tests across Gmail, Outlook, Yahoo and 30+ providers.

已驗證Streamable HTTP可網頁執行溝通與協作資料與分析商業與電商

概覽

AI 產生的概覽

GlockApps MCP 在 Gmail、Outlook、Yahoo 等 30 多家服務商上執行郵件收件匣到達率測試,讓助理發起測試、讀取結果並診斷進垃圾郵件的原因。

可以做什麼
  • 發起與管理收件匣到達率測試:建立測試、取得種子位址與標記、等待完成、刪除測試。
  • 讀取結果與診斷:各信箱的投遞結果、收件匣與垃圾郵件匣分布、內容分析,以及依嚴重程度排序的修正建議。
  • 比較多次測試,判斷修正是否奏效。
  • 列出專案、資料夾、服務商、測試與種子清單,並查詢剩餘測試額度。
  • 在訂閱支援時取得可分享的報告連結。
適用情境
適合電子郵件行銷與送達率團隊,希望不離開助理就能查看活動在各服務商的投遞位置並取得優先修正建議。也適合在調整內容或寄送設定後,把新測試與先前的測試做比較。
執行需求
遠端端點 streamable HTTP,無需在本機安裝。需要已開通 API 存取權的 GlockApps 帳戶,以及 Account → API / MCP 中的 API 金鑰。預設使用 OAuth;不支援 OAuth 的用戶端可在 Authorization 標頭以 Bearer 方式送出金鑰。每次測試消耗一個測試額度。
安裝前請注意
每次 create_test 消耗一個測試額度,未帶標記的寄送同樣會扣掉額度;delete_test 僅在尚無結果送達時退還額度。delete_test 會刪除測試及其結果。建立測試有每小時與每日的頻率限制。API 金鑰屬於憑證:使用靜態金鑰方式時,重新產生金鑰會使連線失效。此連接器本身不能寄送郵件,活動需由你從自己的平台寄出。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 GlockApps — Inbox Placement Testing,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 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.glockapps%2Fmcp/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。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "glockapps-inbox-placement-testing": {
      "type": "http",
      "url": "https://api.glockapps.com/mcp"
    }
  }
}

README

GlockApps MCP

Run real inbox placement tests from your AI assistant. Ask it to start a test, and it hands you the seed addresses to send to; ask again once you have sent, and it tells you who put you in the inbox, who put you in spam, and what to fix first.

The seed network is live mailboxes at Gmail, Outlook, Yahoo, AOL, Zoho, corporate Exchange and 30+ other providers.

https://api.glockapps.com/mcp

This repository is documentation and the registry manifest. The server itself is hosted by GlockApps — there is nothing here to install or run.

What you need

  • A GlockApps account with API access on the plan. Your API key is on Account → API / MCP.
  • Test credits. Every test costs one, whether it is started here or in the GlockApps web app.

Quick connect

Claude.ai, Claude Desktop

Settings → Connectors → Add custom connector. Paste the address above and leave Client ID and Client Secret empty. Select Connect: a GlockApps page opens and asks for your API key once.

Claude Code

bash
claude mcp add --transport http glockapps https://api.glockapps.com/mcp

Then /mcp in the session, and authenticate in the browser window it opens.

ChatGPT

Turn on developer mode (Settings → Security and login), then Plugins → + → Create app → Create MCP App. Paste the address, leave Authentication on OAuth, select Create, and paste your API key on the GlockApps page that opens. Developer mode is required while the connector is not yet in the ChatGPT directory.

Cursor, Windsurf, Continue and other clients

Clients that cannot do OAuth can send the API key directly. Copy a config from configs/ and put your key in it:

json
{    "mcpServers": {        "glockapps": {            "url": "https://api.glockapps.com/mcp",            "headers": { "Authorization": "Bearer YOUR_GLOCKAPPS_API_KEY" }        }    }}

Full per-client instructions: docs/connect.md.

How a test works

The one thing to understand before you start: this connector cannot send your email. It gives you addresses to send to, and it reads what arrives.

  1. list_projects — resolves the project everything else needs.
  2. create_test — costs 1 credit. Returns the seed addresses and a marker.
  3. You send. Send the campaign you want to test, from the platform you are testing, to every seed address, with the marker included — either the X-API-Campaign-id header or the id: ... line in the body.
  4. wait_for_test — results are usually usable about 10 minutes after sending.
  5. get_results, then diagnose for what to fix, worst first.

A send without the marker never matches the test. Nothing arrives, the test never finishes, and the credit is still spent. If that happens, ask your assistant to delete the test: the credit comes back while no result has arrived.

Some providers accept mail slowly, so a test that has not "finished" after an hour is normal, not broken.

Things to ask it

  • "Start an inbox placement test on my main project."
  • "Has the test finished? What is the inbox rate?"
  • "Why did this campaign land in spam?"
  • "Compare this test with yesterday's. Did the fix work?"
  • "Which providers are filtering us, and what should I change first?"

Tools

Fifteen tools, thirteen of them read-only. Full reference with parameters: docs/tools.md.

Readlist_projects list_folders list_providers list_tests get_balance get_seed_list get_test_status wait_for_test get_results diagnose get_content_analysis compare_tests get_shared_link
Writecreate_test — costs 1 credit
Destructivedelete_test — removes the test and its results; refunds the credit only while no result has arrived

Security

  • Scopes. inbox_placement:read and inbox_placement:write. The connector cannot see or change your password, billing details or sending accounts.
  • It never sends email. Your campaign is sent by you, from your own platform.
  • Your key is not shared with the AI provider. In the OAuth flow it is exchanged on a GlockApps page for a token scoped to this connector; it stays on your GlockApps account.
  • Regenerating your key does not break an OAuth connection. The connector records which account it is linked to, not the key, and picks up the current one on each call. It does end any connection using the static-key method above.
  • Rate limits. Test creation is capped per hour and per day on top of your credit balance. get_balance reports the effective number.

Troubleshooting

"No test credits left" — top up in GlockApps, or run the test from the web app. get_balance tells you what is left before you start.

The test never finishes and shows nothing — almost always a send without the marker. Delete the test to get the credit back, start a fresh one, and follow its sending instructions exactly.

Some results missing after an hour — usually fine; slower providers take hours. Nothing at all within ten minutes of sending means the marker was missing.

"Shareable report links are unavailable" — not part of every subscription. Your assistant can still read per-mailbox results directly.

Connecting fails with "API key not recognised" — copy it again from Account → API / MCP; API access has to be enabled on your plan.

Support

Open an issue or email [email protected].

來源:README.md,提交 050ed62

工具

0
該伺服器需要登入,因此 SourceWeft 無法在沒有帳號的情況下讀取其工具,也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v1.0.0最新Sep 29, 2026

評分

已滿足適用檢查項的 85%

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15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分