loading…
Search for a command to run...
loading…
A debugging workflow plugin for AI coding agents. Turns terminal failures into source-backed fixes via MCP and structured skills.
A debugging workflow plugin for AI coding agents. Turns terminal failures into source-backed fixes via MCP and structured skills.
Moth is a lightweight MCP server for project-local bug-fix analysis and verified fix memory.
Moth receives error output through MCP, redacts likely secrets, normalizes the failure, detects the likely stack, checks project-local fix memory, and returns a structured fix brief.
Moth does not edit code, run shell commands, crawl repositories, require a backend, or maintain a global bug database.
Bug-fix context is often local to a project: the command that failed, the framework in use, nearby configuration, and fixes that have already worked or failed in that repo.
Moth keeps that workflow small and explicit. It analyzes provided error context, suggests a best first fix, and records only verified fix outcomes in project-local memory.
Requires Node.js 18+.
Run directly:
npx -y @stfade/moth moth-mcp
Or install globally:
npm install -g @stfade/moth
moth-mcp
{
"mcpServers": {
"moth": {
"command": "npx",
"args": ["-y", "@stfade/moth", "moth-mcp"]
}
}
}
When using Moth with a supported AI agent, you can include a simple prompt like this along with your error:
"Use Moth to analyze this error before fixing it."
| Client | Status | Setup |
|---|---|---|
| Codex | Local plugin-ready | Setup |
| Claude Code | Local plugin-ready | Setup |
| Cursor | Plugin scaffold | Setup |
| Gemini CLI | Extension scaffold | Setup |
| Gemini Antigravity | MCP config-ready | Setup |
| OpenCode | MCP config-ready | Setup |
| Generic MCP | Config-ready | Setup |
“Local plugin-ready” means the integration wrapper is included and can be tested locally. Marketplace submission and approval are not included yet.
Moth exposes exactly two MCP tools.
analyze_errorAnalyzes provided error output before a fix is attempted.
Input fields:
error_outputcommand?cwd?package_context?relevant_files?environment?Output fields:
analysis_idfingerprintstacklikely_causebest_first_fixverificationprior_project_fixesavoidconfidenceremember_fix_resultRecords verified project-local fix memory.
Input fields:
analysis_idfingerprintstackfix_attemptedverification_commandverification_result: "passed" | "failed"notes?The public worked input is rejected. worked is derived from verification_result.
analyze_error
→ apply/attempt fix
→ run verification command
→ remember_fix_result
Call remember_fix_result only when:
passed or failedDo not call it for suggestions, skipped changes, missing verification, ambiguous results, or guesses.
Verified project-local fix memory is stored at:
.moth/fix-memory.jsonl
Moth keeps a small Moth-owned analysis registry outside the project so remember_fix_result can map analysis_id back to the correct project path after an MCP server restart.
Moth includes concise skills for compatible agents:
moth-debug-first-fixmoth-source-backed-researchmoth-verify-fixThe MCP server itself does not perform live web research. Compatible agents may use their own search tools, guided by Moth skills, when external sources are needed.
pnpm install
pnpm test
pnpm build
pnpm dev
npm pack --dry-run
MIT
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"moth": {
"command": "npx",
"args": []
}
}
}Web content fetching and conversion for efficient LLM usage.
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolProvides auto-configuration for setting up an MCP server in Spring Boot applications.
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzНе уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai