
Condux error monitoring
ai.condux由 condux.ai 發布官方發布者v1.0.0更新於 Oct 24, 2026
Read your Condux issues, events and stack traces (deminified with source maps). Triage optional.
概覽
Condux 錯誤監控的遠端唯讀 MCP 端點,讓助理檢視專案的 issue、事件與經 source map 還原的堆疊資訊。
- 可以做什麼
- 列出並讀取 Condux 專案中的 issue,包含經 source map 還原的堆疊、標籤面向與麵包屑(未公布工具清單,實際工具名稱未知)。分頁瀏覽某個 issue 的多次發生紀錄,以檢視個別事件。運用這些資料協助分診與排查正式環境錯誤;此端點本身不提供寫入工具。
- 適用情境
- 適合讓助理依據 Condux 監控應用程式的真實正式環境錯誤進行除錯,例如排查缺陷時讀取分組後的 issue 與堆疊。適合已將錯誤回報至 Condux、希望 AI 用戶端直接在對話中檢視這些資料的團隊。
- 執行需求
- 位於 app.condux.ai 的遠端 MCP 端點,使用 streamable HTTP。需要 Condux 帳號,以及從專案 MCP 分頁取得的專案層級 MCP 權杖,以 Bearer 權杖形式放在 Authorization 標頭中。每個權杖只對應一個專案。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Condux error monitoring,將其新增到工作區。
- 連接 Authorization token 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
- 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/ai.condux%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。其他 MCP 客戶端
把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"condux-error-monitoring": {
"type": "http",
"url": "https://app.condux.ai/api/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
Condux
Condux is a source-available error monitoring platform with a built-in AI fix engine.
[An issue in Condux, with its stack trace, source context, volume chart and triage actions]
SDKs report errors to a stateless ingest relay, which authenticates the DSN, applies per-plan rate limits and quotas, and scrubs PII before buffering through Redpanda. A consumer fingerprints and groups events into issues, writes time series to ClickHouse and issue state to PostgreSQL. A Next.js dashboard reads that back as grouped issues with stack traces, breadcrumbs, tag facets and per-hour charts, and alerting fires on new and regressed issues to email, Slack, Discord and webhooks.
The Conductor
The fix engine takes an issue to a draft pull request. It assembles a scoped, scrubbed context from the stack trace and the project's code mappings, sends it to Claude or to a model the organisation supplies, and applies the returned changes on a new branch as a draft pull request. Fixes are never merged automatically.
Repository access is a GitHub App with short-lived installation tokens; the model is not given the token. After a fix PR merges, a verification loop compares the issue against its subsequent event counts and resolves it once it stays silent for a configured window.
Open Dependabot findings on a connected repository can be turned into dependency-bump draft PRs through the same engine.
Each run is metered against the organisation's monthly allowance and a spend ceiling, with per-run cost derived from recorded model token usage.
Compatibility
Ingestion accepts the Sentry envelope and store formats, so an existing Sentry SDK reports to Condux by changing its DSN. OTLP/HTTP logs are also accepted, which lets an OpenTelemetry-instrumented application report without an SDK.
First-party SDKs are published for JavaScript/Node, browser, edge, Next.js, Python, Go, Ruby, PHP, JVM and .NET, with framework adapters for React, Express, Flask/Django/FastAPI, Rails, ASP.NET Core and Spring Boot. The SDKs are Apache-2.0; the server is FSL.
MCP endpoint
A read-only Model Context Protocol endpoint lets an AI agent debug against real production errors. Point Claude, Cursor or any MCP client at a project with a scoped token and it can list issues, read stack traces and page through occurrences. There are no write tools, and a token resolves to exactly one project.
Architecture
.NET 10 services and a Next.js / React / TypeScript dashboard.
Valkey backs rate limiting and monthly quotas. The relay holds no state. Raw events expire per plan through a column-driven ClickHouse TTL rather than a scheduled job.
Repository layout
Requirements
- .NET SDK 10.0 or later
- Node 22 or later, with pnpm
- Docker and Compose
Running it
The dashboard is at http://localhost:3200 and the API on 8080.
Building and testing from source:
Integration tests start real datastores through Testcontainers and bind the same ports as the Compose stack, so run them with that stack stopped.
Deployment
deploy/docker-compose.yml runs the whole platform on a single host. deploy/charts/condux is a Helm
chart that deploys the services against externally managed PostgreSQL, ClickHouse and a Kafka-API
broker rather than running datastores in the cluster. Its README.md
covers the values, including config.ingestHost, which is required because every DSN the control plane
mints points at it. You build and push the service images yourself; the chart does not ship any.
Security
Report suspected vulnerabilities privately by email as described in SECURITY.md, rather
than in a public issue or pull request.
License
Condux is source-available under the Functional Source License (FSL-1.1-ALv2). It may be read, self-hosted and modified for any purpose other than offering a competing commercial service, and each release converts to Apache-2.0 two years after it is published.
See LICENSE for the terms and LICENSING.md for a plain-language summary.
The SDKs under sdks/ are Apache-2.0.
來源:README.md,提交 746fc37
工具
0版本歷史
1- v1.0.0最新Oct 13, 2026
評分
已滿足適用檢查項的 75%
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
請在儲存庫或註冊中心條目中宣告授權條款。