MCP Dogfooder — Testing & QA agent for Claude Code
Drives the shipped MCP debugger tools as a real user would — launch, breakpoints, stepping, locals, object expansion, evaluation, method calls — against the test targets or a live host, and reports on.
How to install MCP Dogfooder
Installs to ~/.claude/agents/csm101-delphi-visual-studio-code-debugger-mcp-dogfooder.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/csm101/delphi-visual-studio-code-debugger/HEAD/.claude/agents/mcp-dogfooder.md -o ~/.claude/agents/csm101-delphi-visual-studio-code-debugger-mcp-dogfooder.md Restart Claude Code, or start a new session, for it to be picked up.
What MCP Dogfooder does
name: mcp-dogfooder description: Drives the shipped MCP debugger tools as a real user would — launch, breakpoints, stepping, locals, object expansion, evaluation, method calls — against the test targets or a live host, and reports only the DEFECTS with a both-bitness control for each. Use to find what the suite cannot: wrong values that are plausible, missing reasons, and tools that answer confidently when they should refuse. Long and tool-heavy by design; it returns a short list. model: inh
Alternatives in Testing & QA
- Debugger — Debugging specialist for errors, test failures, and unexpected behavior 2.8k ★
- Codex Debugger — Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenA 249 ★
- Test Refactor Specialist.Agent — Improves test code quality and maintainability 225 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Live Evaluator
Phase 3 of the grounded-persona-eval method — drives one persona through a real, live interaction with the pro
IDE Debugger
Autonomous debugging agent that uses IDE bridge debug and terminal tools. Sets breakpoints, evaluates expressi
Scope Drift Detector
Compare the current diff against the active plan.md spec to detect scope expansion. Flags files and features n
Writ Test Writer
Writes test skeleton files with method signatures and assertions based on an approved plan. Use after plan app
Resource Manager
Use BEFORE dispatching any TEST-RUNNING subagent (a builder, a fix-subagent, qa-engineer) to get a GO/HOLD ver
Polisher
Motion engineer + visual QA auditor. Reads .eros/context/motion.md, implements composables, preloader, transit
Related Skills
Debug Skill
Give your AI agent a real debugger — breakpoints, stepping, variable inspection, and stack traces via CLI.
Audit Patterns
Design patterns audit. Analyzes stability (Circuit Breaker, Retry, Rate Limiter, Bulkhead), behavioral (Strate
Agent Debugger
A specialized AI debugging agent using Llama3 (Ollama) that performs root cause analysis, generates minimal co