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 33,053 个资源 · 第 35 / 689 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。
v1.0.9
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v1.0.1
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v1.0.1
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v0.0.3
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v0.0.3
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v1.0.5
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v0.0.4
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v2.0.7
Checks AI agents' claims against primary evidence, with no model; observes only what you grant.
v1.0.4
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v0.0.6
x402 paid API for AI agents. USDC on Base. CDP facilitator.
v0.7.65
读取并编辑 Microsoft Access 数据库(.accdb/.mdb)——窗体、VBA、表与查询,仅限 Windows。
v0.9.1
Local CI broker and test-impact ledger for coding agents: queue, lane modes and red-run packets.
v0.1.12
Causal memory and tamper-evident audit log for AI agents: log, why, search, time travel.
v1.0.1
English→Japanese document translation with a certificate. No API key, free quote, fixed ¥980–5,980
v0.1.0
Firecrawl web data: scrape, map, search, crawl, extract, research, and llms.txt.
v2.0.0
Official Sevalla MCP: deploy, debug and manage apps, static sites and databases.
v0.1.0
Perplexity answers: ask, search, reason, and deep research through the Sonar API.
v1.1.0
MCP tools for testing mobile and TV apps on iOS simulators, Android phones, and Apple/Android TV.
v1.1.0
Email infrastructure and authentication for developers: domains, inbox routes, auth apps, deploys.
v0.3.1
One encrypted chat for you, your people and your AI agents: Claude, Codex, Gemini, Goose.
v1.0.8
创建音乐宣发活动、Smart Link、数据分析看板以及音乐发行申请。
v1.55.0
面向 AI 智能体的数据控制平面——通过 MCP 获取、校验、落地并查询数据。
v1.5.0
Google SERP results, keyword volume and ideas, rank tracking, backlinks, site audits. Pay per use.
v1.1.5
VaneUI React component docs and per-component prop tables for AI coding agents.
v3.11.22
面向 AI 智能体的 Git 原生内容治理,通过 stdio 与 HTTP 提供 27 个确定性 MCP 工具。
v1.17.0
SQL validation, formatting, parsing, metadata extraction, linting, and security analysis.
v1.110.0
Shared project memory for Claude Code, Codex and Cursor: decisions, corrections, overlap warnings.
v0.1.0
Read-only codal.ir: search disclosures of Iranian listed companies, read letters and statements.
v0.1.3
Chinese chain-restaurant calories and macros for 103 menu items, no API key.
v0.1.0
Read-only Neshan map of Iran: places, reviews, photos, routes, travel times, zones, air quality.
v0.1.0
Read-only Balad (balad.ir) Iran map: places nearby or on the way, details, reviews, driving routes.
v0.3.6
A portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code
v0.1.0
Find customers who stopped buying, and the revenue at risk, from an orders CSV on your machine.
v3.7.0
在你的 AI 助手中起草、翻译并更新帮助中心文章,并管理 Zendesk 工单。
v0.1.0
Keeps a current picture of your startup so Claude can give your best next move and why.
v0.13.1
Query OTel traces across Jaeger, Tempo, Traceloop, Datadog, Sentry, X-Ray, New Relic, Honeycomb.
v1.39.0
2025 HMDA FHA denial statistics and dated US mortgage rule tables, with verifiable receipts.
v0.1.21
用于 n8n 工作流管理的 MCP 服务器——通过 AI 查看、创建、同步与管理工作流。
v0.1.16
Search and run hosted AI agent skills for Claude Code, Codex, Cursor and Gemini CLI.
v0.17.0
Policy-gated agent spend with signed receipts and rail-extract audit
v0.17.0
Indonesia-ready agents: NIK, phone, Rupiah, regions, postal codes, holidays, and PII masking.
v0.12.2
Read-only gates of autonomous trading agents with deterministic execution: cost, data, validation.
v2.18.0
Work with Redmine issues, projects, time entries, wiki pages and more. Read-only by default.
v1.0.0
Give your AI agent a labeled, key-owned social identity on SocialWTF AI Commons.
v0.7.5
Local, private memory for coding agents: facts, skills and tasks that persist across sessions.
v2.12.33
Score and rewrite AI-assisted prose while preserving names, numbers, quotes, links, and facts.
v0.19.1
OSC 与 MIDI 桥接——覆盖 849 种合成器与 DAW,用 MIDI MCP 和 OSC MCP 控制它们。
v0.2.1
Evidence-first browser QA with read-only MCP server for AI agent debugging.
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。