Moth
Moth 是一个轻量级的 MCP 服务器,用于项目本地的错误修复分析和已验证修复记录存储。
Moth 的功能
Moth 通过 MCP 接收错误输出,屏蔽潜在的敏感信息,标准化故障,检测可能的堆栈,检查项目本地的修复记录,并返回结构化的修复摘要。
Moth 不会编辑代码、运行 shell 命令、抓取仓库、要求后端支持或维护全局错误数据库。
Related MCP server: looplens-mcp
为什么选择 Moth?
错误修复的上下文通常是项目本地的:失败的命令、使用的框架、附近的配置,以及在该仓库中已经成功或失败的修复方案。
Moth 使该工作流保持精简且明确。它分析提供的错误上下文,建议最佳的首选修复方案,并仅在项目本地内存中记录已验证的修复结果。
快速开始
需要 Node.js 18+。
直接运行:
npx -y @stfade/moth moth-mcp或全局安装:
npm install -g @stfade/moth
moth-mcp通用 MCP 配置
{
"mcpServers": {
"moth": {
"command": "npx",
"args": ["-y", "@stfade/moth", "moth-mcp"]
}
}
}使用示例
当在支持的 AI 代理中使用 Moth 时,您可以包含如下简单的提示词以及您的错误信息:
"Use Moth to analyze this error before fixing it."
支持的客户端
客户端 | 状态 | 设置 |
Codex | 本地插件就绪 | |
Claude Code | 本地插件就绪 | |
Cursor | 插件脚手架 | |
Gemini CLI | 扩展脚手架 | |
Gemini Antigravity | MCP 配置就绪 | |
OpenCode | MCP 配置就绪 | |
Generic MCP | 配置就绪 |
“本地插件就绪”意味着集成的包装器已包含在内,可以在本地进行测试。市场提交和审核尚未包含在内。
工具
Moth 仅公开两个 MCP 工具。
analyze_error
在尝试修复之前分析提供的错误输出。
输入字段:
error_outputcommand?cwd?package_context?relevant_files?environment?
输出字段:
analysis_idfingerprintstacklikely_causebest_first_fixverificationprior_project_fixesavoidconfidence
remember_fix_result
记录已验证的项目本地修复记录。
输入字段:
analysis_idfingerprintstackfix_attemptedverification_commandverification_result: "passed" | "failed"notes?
公共的 worked 输入将被拒绝。worked 是从 verification_result 派生出来的。
已验证记录生命周期
analyze_error
→ apply/attempt fix
→ run verification command
→ remember_fix_result仅在以下情况调用 remember_fix_result:
确实尝试了修复/更改
验证命令确实运行了
结果明确为
passed或failed
不要将其用于建议、跳过的更改、缺失验证、模棱两可的结果或猜测。
本地存储
已验证的项目本地修复记录存储在:
.moth/fix-memory.jsonlMoth 在项目外部保留了一个小型 Moth 拥有的分析注册表,以便 remember_fix_result 可以在 MCP 服务器重启后将 analysis_id 映射回正确的项目路径。
技能
Moth 为兼容的代理提供了简洁的技能:
moth-debug-first-fixmoth-source-backed-researchmoth-verify-fix
Moth 服务器本身不执行实时网络研究。当需要外部资源时,兼容的代理可以在 Moth 技能的指导下使用它们自己的搜索工具。
安全性
默认只读
无源代码编辑
无 shell 执行
无全仓库扫描
无后台监视器
无需外部服务
在分析、响应和内存写入之前屏蔽潜在的敏感信息
开发
pnpm install
pnpm test
pnpm build
pnpm dev
npm pack --dry-run许可证
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityCmaintenanceShared debugging memory for AI coding agents. Agents search, report, patch, and verify bug fixes through 5 MCP tools. Verified by proof, not upvotes.1
- AlicenseBqualityDmaintenanceAn MCP server for detecting retry loops and analyzing iteration patterns in agentic coding workflows, providing structured debugging intelligence to improve repair attempts.165MIT
- Alicense-qualityCmaintenanceA deterministic AST evidence engine that forces AI agents to debug using verified execution facts instead of pattern-matching symptoms, enabling hallucination-free debugging for MCP-compatible agents.6Business Source 1.1
- Alicense-qualityBmaintenanceAn MCP server that gives coding agents a persistent, chained memory of debugging investigations, tracking what's been tried, ruled out, and solved across sessions and scopes.8MIT
Related MCP Connectors
Shared debugging memory for AI coding agents
Agent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for
Structured failure knowledge for AI agents — dead ends, workarounds, error chains
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/stfade/moth'
If you have feedback or need assistance with the MCP directory API, please join our Discord server