MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server to track bugs
★ 1 -
MCP server that lets several agents share one git-bug store while the web UI is open
MIT -
MCP server for AI-powered smart contract security analysis. $5 USDC/scan via x402. Drawn from 56,657 Sherlock submissions plus Code4rena, verified acceptance rates from 9,200 exact-reconciled findings. Includes a free, standalone dataset (vulnerability-ac
npm MIT -
MCP server that scans Solidity repos through a 7-gate verification framework (Al-Mizaan) to cut LLM false positives, benchmarked against Slither; free pattern-search from 1,032 reconciled Sherlock findings, paid full scan via x402 (USDC/Base).
MIT ★ 11 -
Pack bug screenshots into AI coding instructions with MCP Server integration
npm MIT -
Universal Bug Triage & Upstream Router for Autonomous Coding Agents
MIT -
MCP server that connects AI assistants to HackerOne for bug bounty hunting
MIT ★ 360 -
Local-first, agent-readable bug capture: annotated screenshots + notes stored locally, synced to issue trackers on your own schedule.
MIT -
AI Pentesting Framework, Bug Bounty MCP Server, SAST/DAST Taint Engine & 12 Offensive Security Skills for Claude Code, Google Antigravity, Codex & Cursor.
MIT ★ 7 -
Heresay by Sibhimanyu: in-app feedback and bug reports for web, iOS and macOS apps. Your team accepts each report; accepted ones go to your coding agent (Claude Code, Cursor, Codex) via MCP. Self-hosted on Firebase.
npm -
Give your AI superpowers for bug bounty hunting. MCP server that turns Claude Code into a structured bug bounty toolkit — recon, live testing, intelligence, and report generation.
MIT ★ 1 -
MCP Server for Meta Hackers, use agents to create FBDL scripts. FBDL is a tool designed to help you quickly and efficiently setup security bug reproduction steps using a standard “bug” description language.
MIT ★ 9 -
CLI and MCP server for Bugpacker bug packages. Give a coding agent the console, network and repro steps from a real bug, without any of it leaving your machine.
npm Apache-2.0 -
Every player who reports a bug hears back. Agent-native, human-approved bug desk for Discord forums: incremental ledger, approval queue, release closure, MCP for Claude Code / Codex / Agents SDK.
MIT ★ 9 -
@aipper/zentao-mcp-servergithub.com/aipper/zentao-mcpupdated this year
A minimal MCP server for ZenTao (token + focused bug workflow tools).
npm MIT -
MCP server for Rebase. Give your coding agent everything a bug report captured.
MIT -
MCP server for MantisBT REST API – read and manage bug tracker issues
npm MIT -
MCP server exposing BugSpotter bug-tracking operations to AI agents (Claude Code, Claude Desktop, Cursor)
MIT -
A modular external attack surface mapping tool integrating tools for automated reconnaissance and bug bounty workflows.
★ 78 -
@cqjjb/zentao-mcp-servergit+http://192.168.1.242:10985/jjb/ai-agent/mcp/zentao-mcp-server.gitactive
MCP server for ZenTao 12.x: auto-login (zentaosid session + form submission) and full bug lifecycle (list/detail/edit/assign/resolve/close/activate/comment) + attachments
npm MIT -
Reproduce a bug in the environment where it was reported, find the cause, and verify the fix. Runs on Solari.
MIT ★ 3 -
QuickCast Screen-to-Action Protocol MCP Server: Automated Bug Reports, Playwright E2E Tests, and SOP Generator from Screen Recordings.
MIT -
mustelgithub.com/mustel-py/mustelupdated this year
Non-AI static analysis layer for AI IDEs and coding agents - bug detection, security scanning, and CVE checking via MCP
pypi MIT License -
MCP tools that help coding agents test web apps systematically, find bugs, and deliver evidence-backed reports and regression tests for supported findings.
MIT ★ 7 -
🛡️ Production-grade Model Context Protocol (MCP) Server for Autonomous AI Security Bug Hunting, Persistent Pentest Memory, Dynamic Checklists, Secret Redaction, and Exploit PoC Generation.
MIT ★ 1 -
Wissensgetriebener, lokaler Pentest-Workspace (CLI) für CTF, Bug Bounty & autorisierte Tests – geführte Recon, Findings/Loot/Reports, Web-Dashboard, lokale KI-Unterstützung & MCP-Server. KI analysiert, führt nie selbst aus.
MIT ★ 1 -
Modular MCP server for programmatic prompt engineering. Provides intelligent prompt assembly for PRD generation, codebase analysis, and bug analysis with support for 31 technology stacks.
MIT ★ 4 -
Meta Global AI Developer Hackathon. Show Tracera a bug. It investigates your code, proposes a fix, verifies it in a sandbox, and shows you what changed.
MIT -
Free, self-hosted bug bounty scope tracker: new programs, new targets, fee and reward changes, repo pushes across HackerOne, Bugcrowd, Intigriti, YesWeHack, HackenProof and Sherlock. CLI, HTTP API, MCP server. No API keys.
MIT ★ 3 -
Revolutionary MCP server that analyzes code evolution, predicts bugs, and provides historical insights about code patterns and development trends
npm MIT -
bugtapeactive
BugTape CLI: connect Claude Code, Cursor, Codex or Grok to your production bugs over MCP. Replay, request, console and stack for every user-reported or silent failure.
npm Apache-2.0 -
High-performance Model Context Protocol (MCP) server for QuickCast Screen-to-Action Protocol: automated bug reporting, Playwright E2E test scaffolding, and SOP generation from QuickCast recordings.
npm MIT -
High-performance, free MCP server for deep coding bug research, Stack Overflow accepted answers, GitHub closed issues, and merged PR git diffs for Claude, Cursor, and Windsurf.
MIT -
buglensgithub.com/dd-jfranjic/buglensupdated this year
WordPress MCP Server for Shared Hosting — connect AI agents (Claude Code, Cursor, Codex, Gemini CLI) to WordPress sites without SSH. 15 MCP tools: file management, code search, WP-CLI bridge, visual bug tracking.
GPL-2.0 ★ 1 -
🪐 AetherScope V2 — SAST 3D WebGL & Serveur MCP (Claude/Antigravity/Cursor). Détection de 150+ CWE & Zero-Day Patterns (Rust, C++, PHP, Node.js, Web3), contrats EARS BLAKE3 et PoC Bug Bounty.
NOASSERTION ★ 2 -
Map every feature and user flow in a codebase from git history and code structure. No Jira, no annotations. Bug hotspots, health scores, symbol-level attribution and an MCP server for AI coding agents.
NOASSERTION -
stacks-aigithub.com/jentrix-au/stacks-aiupdated this year
The universal board for AI agents — one Kanban for tasks, bugs, support, CRM & roadmap, operated by humans and agents via a built-in MCP server. Open-source, self-hostable (Next.js 16, Prisma 7, Auth.js v5).
MIT ★ 3 -
Record your screen, narrate the bug, and hand your AI coding agent structured Markdown - one annotated screenshot per mark. Desktop app, CLI, and MCP server for Claude Code, Cursor, Codex, and Windsurf. On-device Whisper transcription, local-first, MIT.
MIT ★ 85 -
ThinkRun — screen recorder for AI coding agents. Record a bug or session once and hand Claude Code or Cursor structured context it can act on. Real Chrome, your sessions. MCP + CLI + portable agent skills with reproducible trigger evals.
MIT ★ 2 -
Claude-native, governed offensive-OSINT & external attack-surface platform for authorized red-team and bug-bounty. Multi-agent recon across web, identity, cloud, secrets & breach intel under deterministic scope/evidence/approval controls, with human-reviewed findings for hand-off to pen-testing. Not an exploitation framework.
NOASSERTION ★ 15 -
Screen recording your AI can read. Free, open source Mac app: press a hotkey, show the bug, say what's wrong. Luna turns your screen, voice and clicks into a small MP4 plus a prompt any agent can read: Claude, ChatGPT, Cursor, Codex. Works over MCP too.
MIT ★ 4 -
One command installs 670+ security tools on Debian/Ubuntu/Kali, Fedora, Arch, openSUSE and Termux. Its authorization-gated MCP server runs them in a disposable Kata Containers VM sandbox for Claude Code, Codex, Gemini CLI, OpenCode and other MCP clients. 872 agent skills for CTF, pentesting, bug bounty, DFIR and red/blue teams.
MIT ★ 97 -
Autonomous game playtesting agent: plays a game, hunts bugs with generic oracles + LLM, writes reproducible reports. Includes seeded-bug eval harness and MCP server.
MIT -
intigriti-company-api-mcpgithub.com/k11h-de/intigriti-company-api-mcpupdated this year
Empowers AI assistants to interact with the Intigriti bug bounty platform's Company API, streamlining program, submission, and budget workflow management for companies running bug bounty programs on the platform.
GPL-3.0 -
Support email becomes Linear bugs, refunds get handled, and fixed bugs get a reply in-thread.
Apache-2.0 -
intigriti-mcpgithub.com/alpernae/intigriti-mcpupdated this year
A Model Context Protocol (MCP) server for interacting with the Intigriti bug bounty platform's Researcher API. This enables AI assistants like Claude to help security researchers manage their bug bounty programs, submissions, and research workflow.
MIT ★ 4 -
AI-powered bug detection and auto-fix pipeline. A user reports a bug through a Chrome extension capturing a screenshot, DOM snapshot, and voice description and an autonomous agent diagnoses the issue, fixes the code in a sandboxed environment, commits the fix, deploys it, and closes the GitHub issue.
-
mcp-code-sanitizergithub.com/notasandy/mcp-code-sanitizerupdated this year
Strict AI code reviewer MCP server powered by Groq — finds bugs, vulnerabilities and security issues
pypi MIT -
gripe-mcpgithub.com/retospect/gripe-mcpupdated this year
Agent complaint box — one-tool MCP for logging bugs and improvement requests
pypi LGPL-3.0-or-later -
Local-first, agent-readable bug capture: annotated screenshots + notes, stored locally, synced to trackers on your own schedule.
pypi MIT -
mcp_exploitdbgithub.com/CyberRoute/mcp_exploitdbupdated this year
Experimental MCP local server for bug hunters to speed up exploits searches
★ 7 -
jura-zentao-mcpupdated this year
禅道(Zentao)MCP Server —— 让 AI 直接拉取禅道需求/Bug/任务/文档
npm MIT -
gripe-mcpgithub.com/retospect/gripe-mcpupdated this year
Agent complaint box — one-tool MCP for logging bugs and improvement requests
NOASSERTION -
AI-driven-test-automation-platformgithub.com/leo159363/AI-driven-test-automation-platformupdated this year
QualityPilot: 基于 MCP + RAG 的智能测试自动化平台 — 测试用例生成、API/UI 自动执行、失败分析、Bug 报告
★ 3 -
embeddedgdbmcpgithub.com/ezulabs/embeddedgdbmcpupdated this year
Debug embedded systems with AI. Find bugs in seconds, not hours.
★ 1 -
面向禅道开源版的 REST v1 优先、Legacy 兜底 MCP 服务,支持任务和 Bug 工作流
npm MIT -
yeswehack-mcpgithub.com/thecyberneh/yeswehack-mcpupdated this year
MCP server for YesWeHack. Let AI agents browse programs, query scopes, filter bounties, authenticate with 2FA, and automate bug bounty workflows.
-
Argusgithub.com/ironclawdevs27/Argusupdated this year
AI-powered QA harness for Claude Code — automated bug detection via Chrome Dev-Tools Protocol, no test scripts required.
npm MIT ★ 5 -
An AI detective for your codebase. Uses LangChain and MCP to hunt down bugs in your Git history and prove exactly what broke.
-
Giime 项目管理系统 MCP Server - 封装后端 API,供 Kiro/Cursor 通过 MCP 协议操作需求、版本、Bug、统计等
npm MIT