io.github.Dgotlieb/verdict-mcpai

verdict-mcp

Verified · today

Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history

Install

claude mcp add verdict-mcp -- uvx verdict-mcp

Requires: VERDICT_PROJECT

Our take

A developer-focused server for running tests in a sandbox and returning compact, typed results with failure fingerprints and history. It is best suited to coding agents, CI-style automation, or tooling that needs structured execution feedback instead of raw logs. The concept is clear and specialized, and the PyPI package helps, but public adoption signals are still minimal.

reviewed by hand · 2026-08-26

Something wrong or dead here? Report it

Verification record

last verified
today
github stars
0
last commit
today
archived
no
license
Apache-2.0
in registry since
2026-08-25

github.com/Dgotlieb/verdict-mcp

More in ai

browse all →
claude-flowai

claude-flow

Verified · 8 days ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed68k starschecked 8 days ago

tldrawai

tldraw

Verified · 10 days ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 10 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 2 days ago

Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed40k stars11k dl/wkchecked 2 days ago

openmetadata-mcpai

OpenMetadata

Verified · 22 days ago

Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.

hand-reviewed15k starschecked 22 days ago

mobilerunai

mobilerun

Verified · 11 days ago

Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.

hand-reviewed9.1k starschecked 11 days ago

praisonaiai

PraisonAI

Verified · 2 days ago

AI Agents Framework with Self Reflection and MCP support

hand-reviewed8.9k starschecked 2 days ago