
Verdict Mcp
io.github.Dgotlieb由 GitHub 帳號 Dgotlieb 發布v0.1.0a4更新於 Oct 24, 2026
Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history
概覽
一個本機 MCP 伺服器,為編碼代理在沙箱中執行 Python 測試、lint 與型別檢查,回傳帶失敗指紋與歷史紀錄的精簡型別化結論。
- 可以做什麼
- 在隔離容器中執行受變更影響的 pytest 測試,回傳帶指紋與 preexisting 標記的型別化失敗,或以 scope all 強制完整執行。依需求取得單一失敗的完整 traceback。查詢指紋的首次出現、最近出現與出現次數,區分回歸與長期存在的失敗。執行 ruff 與 mypy 檢查,並正規化為同一結論結構。
- 適用情境
- 適用於編碼代理在 Python/pytest 儲存庫中驗證變更時,希望取得簡短的結構化結果而非大量原始測試輸出,並能區分新引入的回歸與原本就存在的失敗。
- 執行需求
- 以 verdict-mcp 套件透過 stdio 在本機執行(uvx、uv tool install 或 pip install)。需要 Python 與容器執行環境,優先 podman,退回 docker;沒有容器執行環境時需明確設定本機退回模式。VERDICT_PROJECT 指定專案路徑,預設為目前工作目錄。選用的 verdict.toml 可設定套件、執行映像、安裝指令與限制。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Verdict Mcp,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
verdict
https://github.com/user-attachments/assets/62923912-98aa-4246-8bc8-4adf55ae3ff8
[CI] [PyPI] [Python] [License]
Structured, sandboxed verification feedback for coding agents.
An MCP server that replaces your agent's pytest shell-outs with something built for the agent inner loop: impact-selected tests, run in an isolated environment, returning compact typed verdicts instead of 40,000 tokens of raw runner output — with failure fingerprints that tell the agent whether a failure is its regression or was broken all along.
Why
The highest-frequency tool call in agentic coding is verification — and it's the least structured. Agents re-run whole suites when one module changed, burn context parsing ANSI-coded tracebacks, run arbitrary code directly on your machine, and routinely misdiagnose pre-existing breakage as their own regression (then "fix" code that wasn't broken). verdict fixes all four.
Tools
Every failure carries a fingerprint: a stable hash of the normalized failure signature (volatile tokens — addresses, tmp paths, ids, durations — collapsed). Same logical failure, same fingerprint, across runs and refactors. Fingerprints are what give verdict memory.
Quickstart
No install step needed — uvx fetches it on first use. (Or uv tool install verdict-mcp / pip install verdict-mcp for a permanent verdict-mcp command.)
Claude Code — .mcp.json in your project root:
Cursor — same shape in .cursor/mcp.json.
Optional verdict.toml in your repo root:
Try it without an agent:
Sandbox posture (v0.1)
Checks run in an ephemeral container (podman preferred, docker fallback): worktree mounted read-only at /src, copied to a writable /work inside the container, --network=none for the check run. Your host environment is never mutated by a test run. If setup_cmd is configured, that step runs with network before the check; prefer a prebuilt image for a tighter posture. No container runtime → explicit prefer = "local" fallback runs checks against a temp copy of your worktree (still never in place). See SECURITY.md for the full threat model and known limitations.
Troubleshooting: if a verdict says container engine 'podman' could not start the check, run the suggested podman pull <image> by hand — the engine's own error is the answer. One known trap on macOS: a "credsStore": "gcloud" line in ~/.docker/config.json makes podman call the gcloud credential helper for every registry, including docker.io; an expired gcloud login then breaks all pulls. Fix with gcloud auth login or remove that line.
Honest limitations
- Impact selection uses the static import graph — approximate by design. Dynamic imports, fixture-by-name resolution, and data-driven tests can be missed;
verify(scope="all")is always available and verdict says inselection_notewhenever it falls back. - Python/pytest only today, plus ruff/mypy. The adapter interface is small and documented — vitest and
go test -jsonadapters are the most-wanted contributions (CONTRIBUTING.md). - Flake detection and coverage-map-based selection are v0.2 (roadmap).
Roadmap
v0.2: coverage-based impact maps (precise selection), flake detection via fingerprint alternation, devcontainer.json support, result cache keyed on (tree hash, check, image digest). Later: vitest/jest, go test, cargo test adapters; per-repo verdict daemon mode.
License
Apache-2.0
來源:README.md,提交 aea7c65
工具
0版本歷史
1- v0.1.0a4最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
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25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 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