GitHub
v1.0.6
管理代码库、用户、发布版本,并自动化 GitHub 工作流
使用场景/代码审查与 GitHub
拉取 PR、读 diff、查 Issue、管理仓库。适合 Code Review、发布说明、CI 问题排查。
共匹配 34,632 个资源 · 第 38 / 722 页
GitHub MCP 让 AI 进入你的协作流程:拉取 PR diff 做代码审查、检索 Issue 历史定位已知问题、读取 CI 日志分析构建失败、汇总提交生成 changelog。官方 github/github-mcp-server 通过 GitHub API 或个人访问令牌(PAT)鉴权,Gitee / GitLab 也有对应实现。
Code Review 实践:把团队的评审规范写成 Skill(如「检查竞态、边界、错误处理,按严重度输出」),配合 GitHub MCP 让 AI 先过一遍 PR,人工只看 AI 标出的高风险行——审查耗时通常明显下降,且低級错误漏检更少。
权限建议:使用细粒度 PAT(只授予目标仓库 contents / pull-requests 读写),组织仓库务必开只读起步;让 AI 发布评论或合并前先要求确认,防止误操作污染协作记录。
v0.20.3
Markdown 语法检查工具,可作工作区级 stdio MCP 服务器,也可作为自托管的纯文本远程 MCP 服务器。
v1.0.0
Vietnam coach and private-car catalog plus quote instructions. Read-only; no bookings or payments.
v0.2.0
Builds S1000D data modules from structured drafts, verifies them, applies only unambiguous fixes.
v0.8.0
Read S1000D data and publication modules as structure, with applicability and verification status.
v0.7.0
Validate S1000D data modules: XSD, BREX chain and reference resolution as one verification status.
v1.0.0
Search published Japan property listings and service information. No live vacancy guarantee.
v0.17.0
Detect breaking changes in your TypeScript library's public API and recommend the SemVer bump.
v1.0.1
Sales lists of local businesses in Japan with contacts, website type and contact forms
v1.0.0
Browse travel eSIM plans, device support and public SMS prices. Read-only; no OTP or purchases.
v1.0.0
Discover Tokyo charter coaches, routes and reference fares. Quotations need user confirmation.
v1.0.0
Stops an agent's Trino or Pinot query before it runs if it costs too much or reads outside its grant
v0.2.3
ChatGenius tools: Instagram, Facebook, WhatsApp and SMS inbox, contacts, bookings, flows, posts.
v3.0.0
API Яндекс.Директа v5: кампании, объявления, фразы, ставки, минус-фразы, статистика
v0.1.0
Fleet-wide backup health, failure triage and usage reports for every tenant on your Comet Server
v0.109.0
本地优先、带引用来源的智能体式 RAG:混合检索、重排序与多模态文档检索。
v0.2.40
ArchLang: compile, describe, lint, validate, score, repair, fix, finish, suggest, complete, link.
v1.0.0
One memory for your AI agents and your team: Claude, ChatGPT, Cursor and your agents share it.
v0.1.1
Literature search, GB/T 7714/APA citations and BibTeX via Crossref, OpenAlex, Semantic Scholar.
v0.41.9
Lets your assistant work with the people and agents in your Ziggs workspaces: inbox, chats, tasks.
v3.31.0
Hostinger API 的 MCP 服务器。
v0.2.6
浏览器自动化 MCP 服务器:导航、填写表单、点击、截图与管理标签页。
v1.3.0
Explore XML schemas, validate XML documents, and transform typed document trees.
v0.22.1
Persistent memory for MCP-compatible agents: memory bank, fact cortex, dreams, graph.
v2.37.5
CloudBase MCP: DB, functions, storage, hosting via @cloudbase/cloudbase-mcp
v0.14.0
Delivery-readiness QA and full official + Tapir API access for a running Archicad 29.
v0.43.1
Inspect RudderStack workspaces, pipelines, and schemas, and manage transformations and audiences.
v0.1.3
See which models actually work: probe, rank and recommend across OpenAI-compatible gateways.
v1.0.0
Korean blue chips priced 24/7 from Hyperliquid perps in KRW: pre-open price and arbitrage
v0.1.3
Let AI agents see and operate a real iPhone via an ESP32-S3 USB HID + AirPlay. No jailbreak.
v0.5.0
Market data, SEC filings and risk tools for Webull, Saxo and IBKR. Only you can send an order.
v1.0.1
Email verifier ($0.60/1k), SPF/DMARC/MX facts, URL to Markdown, on your own Apify account.
v2.4.0
Transcribe social videos, selected comments, URL batches and Instagram channels.
v0.2.1
Point at any part of a website and get a prompt that rebuilds it 1:1, or see how it is made.
v2.3.2
Taiwan law MCP server: 22M court judgments, statutes, agency rulings, with citation checks
v0.1.0
Evidence-chain whiteboard for AI research agents: every claim traces back to its run and code.
v0.21.0
Korean tax calculation and tax-audit judgment MCP: 96 tools with statutory citations.
v4.4.2
Favro cards, boards and collections over MCP: read, search, write, and resolve names to ids.
v2.34.0
面向 AI 智能体的中立货运参考与校验层:ADR、HS 编码、UN/LOCODE、货运计算。
v2.0.0
通过 AST 感知的结构化读取,让 AI 阅读代码时最高节省 80% token。
v3.8.6
Read-only SQL queries and schema inspection for IBM Db2 for i over ODBC, JT400 or Mapepire (SSH).
v0.1.0
Read-only vCenter inventory for migration planning: blockers, snapshots, per-core licence exposure
v0.1.1
Records who authorized an AI agent to do what, until when; signed tokens, hash-chained journal.
v1.8.5-1
面向一件代发的官方 DSers MCP:将商品导入、编辑、定价并发布到 Shopify 与 Wix。
v1.2.0
Ask Verse anything with sources, plus code review, translation and more paid per call over x402.
v0.9.1
Deploy websites, PHP apps and WordPress to kapaweb hosting (DirectAdmin, Plesk preview) from Claude
v0.4.35
基于 Chrome CDP 的 AI 浏览器工具:导航、截图、交互,支持多供应商故障切换。
v5.0.0
Lint rendered pages against a design system in a real browser, across six widths, with the fix.
v1.6.6
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
本地 stdio 部署用个人访问令牌(推荐细粒度 PAT)最简单;多用户托管场景才需要 GitHub App / OAuth。环境变量名见资源详情页。
会。它是第一道过滤而非替代:语义类缺陷检出不错,但供应链、越权逻辑仍需专业审计与人工评审兜底。
取决于模型提供方与令牌权限。企业内网可选本地模型 + 只读令牌;令牌务必设置过期与最小 scope,并定期轮换。