SnagRelay

com.snagrelay由 snagrelay.com 發布官方發布者v1.0.0更新於 Oct 24, 2026

Bug reports your coding agent can fix: real element, console errors, failing requests with bodies.

已驗證Streamable HTTP可網頁執行開發者工具安全與監控

概覽

AI 產生的概覽

SnagRelay 讓程式開發助理依工單編號取得缺陷證據——出錯的元素、主控台錯誤、含請求主體的失敗請求——以便定位並修復問題。

可以做什麼
  • 依工單編號讀取問題的完整脈絡：出錯元素、重現步驟、含檔案與行號的主控台錯誤、帶請求主體的請求，以及截圖連結
  • 依索引取得單一完整的請求或回應主體，或單筆主控台紀錄
  • 查詢同一畫面或端點上先前已解決的問題，以及修好它們的 PR
  • 在沒有工單編號時列出或搜尋問題，並查看目前登入的帳號、方案與可存取專案
  • 回寫進度（正在編輯的檔案），並以 PR、提交與分支把問題標記為已解決，可選擇通知回報者
適用情境
適合透過 SnagRelay 收集使用者錯誤回報的團隊，讓 Cursor、Claude Code、Codex 等 MCP 用戶端中的助理讀取頁面擷取的證據，並在分支上提出或送出針對性的修正。
執行需求
遠端 Streamable HTTP 端點 mcp.snagrelay.com；透過瀏覽器以 OAuth 登入（不必複製權杖），無介面用戶端可建立 API 權杖並以 Authorization Bearer 標頭送出。需要 SnagRelay 帳號，免費方案包含 MCP 伺服器、網路請求主體與 1 個專案。可選的網址變體能限制為唯讀或僅限單一專案。
安裝前請注意
助理會收到使用者頁面小工具擷取的內容：元素、主控台、網路、重播與截圖，但伺服器會在送出前移除 authorization 與 cookie 標頭、API 金鑰、權杖、密碼等機密資訊。寫入工具會回報進度並把問題標記為已解決，標記已解決時可能寄信給回報者。可用唯讀網址禁止寫入；問題可見範圍受方案歷史視窗限制。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 SnagRelay，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.snagrelay%2Fsnagrelay/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": {
    "snagrelay": {
      "type": "http",
      "url": "https://mcp.snagrelay.com/v1"
    }
  }
}

README

SnagRelay for coding agents

Your users find the bugs. Your agent fixes them. Give Cursor, Claude Code or Codex a ticket key and it reads the evidence a human debugger would open: the broken element, console errors with file and line, failing requests with their request and response bodies, repro steps and a short replay.

This repo is the listing and distribution repo for the SnagRelay MCP server. It holds the plugin manifests for each agent platform, the shared skills and the registry entry. The MCP server itself is hosted by SnagRelay at https://mcp.snagrelay.com/v1.

Connect

Sign-in is OAuth. A SnagRelay page opens in your browser, you click Allow, and there is no token to copy.

ClientInstall
CursorOpen Customize → Marketplace, search SnagRelay, install, then click Needs authentication on the snagrelay MCP server
Claude Codeclaude plugin marketplace add snagrelay/agent-plugin then claude plugin install snagrelay@snagrelay. Run /mcp and authenticate snagrelay
Codexcodex plugin marketplace add snagrelay/agent-plugin then codex plugin add snagrelay@snagrelay. Sign in with codex mcp login snagrelay
LovableSettings → Connectors → search SnagRelay, or add a custom MCP server with the URL below
BoltAdd a custom remote MCP connector with the URL below
ReplitAdd a custom MCP server with the URL below
Anything elsePoint any Streamable HTTP MCP client at https://mcp.snagrelay.com/v1

Lovable, Bolt and Replit guides are being written; the custom-connector route works today.

For CI, scripts and other headless clients, create an API token in SnagRelay (Settings → API tokens) and send Authorization: Bearer <token> to the same URL.

Which URL?

All four share one server and one sign-in. Pick the narrowest one that fits.

URLUse it when
https://mcp.snagrelay.com/v1You work across projects. The default
https://mcp.snagrelay.com/v1/readonlyYou want the agent to read issues but never write. The write tools (report_progress, mark_issue_resolved) are removed and blocked. Good for security-conscious teams and shared machines
https://mcp.snagrelay.com/v1/{projectId}This repo belongs to one SnagRelay project. Hard-scoped, so the agent cannot see other projects
https://mcp.snagrelay.com/v1/{projectId}/readonlyBoth of the above

{projectId} is the number from whoami, or from the project's URL in SnagRelay.

Tools

ToolAccessWhat it does
get_issue_contextreadFull context of one issue by key: the element, repro steps, console errors with file and line, requests with bodies, and a screenshot resource link
get_issue_payloadreadOne full request or response body, or one console entry, by the index from get_issue_context
get_related_historyreadEarlier resolved issues on the same screen or endpoint, with the PR that fixed them
find_issuesreadList or search issues when you have no key
whoamireadSigned-in account, plan and accessible projects
report_progresswriteTells SnagRelay which file the agent is editing
mark_issue_resolvedwriteMarks an issue resolved with the PR, commit and branch. Optionally emails the reporter

One resource: screenshot, the issue's screenshot, read with resources/read.

Every tool carries MCP annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint). None is destructive. The agent is instructed not to call mark_issue_resolved before you have reviewed the fix.

Usage

fix PROJ-123-> get_issue_context("PROJ-123")-> reads the failing request and its response body, the console error with file and line, the repro steps-> get_related_history: has this broken before, and what fixed it?-> proposes a targeted fix on feature/PROJ-123-<summary>

Skills

Six skills, written once in skills/ and used by every client.

SkillWhat it does
fix-issueLoad context and fix a SnagRelay issue on a branch, then stop for your review
open-prBranch feature/{key}-{summary}, PR title [{key}] {type}: {description}, full description
resolve-issueCommit and open a PR if needed, then mark the issue resolved
triageList open issues so you can pick one
connectDiagnose a broken MCP connection
scopeWhen the agent may (and may not) call SnagRelay

Cursor also gets rules/snagrelay-context.mdc, which tells the agent to load an issue's context before proposing a fix.

Claude Code namespaces plugin skills: run /snagrelay:fix-issue PROJ-123. In Cursor and Codex, say fix PROJ-123 or use /fix-issue.

Data and privacy

The agent receives what your users' widget captured on the page: element, console, network, replay and screenshot. Secrets are stripped on the server before anything reaches the agent: authorization and cookie headers, API keys, tokens, passwords, CSRF values, secret-looking query and form parameters, bearer tokens, JWTs and long hex or base64 strings. Issues are visible to the agent only as long as your plan's history window (history_days) allows. See TELEMETRY.md for the full list and SECURITY.md to report a vulnerability.

This repo contains no code that runs on your machine: only manifests, skills, a rule and a remote MCP URL.

Requirements

  • A SnagRelay account. The free plan includes the MCP server, network bodies and 1 project. See pricing
  • Cursor, Claude Code, Codex, or any MCP client that supports Streamable HTTP with OAuth

Links

Website · Docs · Pricing · Support · Privacy · Terms

Contributing

Edit skills/ and rules/, never the manifests by hand: see AGENTS.md. MIT licensed.

來源：README.md，提交 21ecc6e

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Oct 11, 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