verdict
https://github.com/user-attachments/assets/62923912-98aa-4246-8bc8-4adf55ae3ff8
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx verdict-mcp==0.1.0a4Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
VERDICT_PROJECT=<value> claude mcp add io.github.dgotlieb-verdict-mcp -- uvx verdict-mcp==0.1.0a4在終端機中執行。
{ "mcpServers": { "io.github.dgotlieb-verdict-mcp": { "command": "uvx", "args": [ "verdict-mcp==0.1.0a4" ], "env": { "VERDICT_PROJECT": "<value>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history
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.
raw pytest dump: ~40,000 tokens, unstructured, run un-sandboxed on your machine
verdict: ~400 tokens, typed JSON, run in a rootless container, with memory
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.
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.
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:
{
"mcpServers": {
"verdict": {
"command": "uvx",
"args": ["verdict-mcp"],
"env": { "VERDICT_PROJECT": "." }
}
}
}
Cursor — same shape in .cursor/mcp.json.
Optional verdict.toml in your repo root:
[project]
packages = ["your_package"] # for impact selection (auto-guessed if omitted)
[runner]
image = "ghcr.io/you/yourproj-test" # prebuilt env with your deps
setup_cmd = "pip install -e .[test]" # or install on the fly (runs with network; tests don't)
# prefer = "local" # escape hatch if you have no container runtime
[limits]
max_failures = 10
Try it without an agent:
cd examples/demo_project
VERDICT_PROJECT=. verdict-mcp # then connect any MCP client, or use the MCP inspector
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.
verify(scope="all") is always available and verdict says in selection_note whenever it falls back.go test -json adapters are the most-wanted contributions (CONTRIBUTING.md).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.
Apache-2.0
Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history
{ "mcpServers": { "io.github.dgotlieb-verdict-mcp": { "command": "uvx", "args": [ "verdict-mcp==0.1.0a4" ], "env": { "VERDICT_PROJECT": "<value>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數:VERDICT_PROJECT。
Verdict 透過 stdio 在本機執行。
上次檢查時間:2026-11-09。 Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history