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.
-
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 -
MCP server for Rebase. Give your coding agent everything a bug report captured.
MIT -
QuickCast Screen-to-Action Protocol MCP Server: Automated Bug Reports, Playwright E2E Tests, and SOP Generator from Screen Recordings.
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 -
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 -
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 -
Reproduce a bug in the environment where it was reported, find the cause, and verify the fix. Runs on Solari.
MIT ★ 3 -
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 -
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 -
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 -
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-codedocgithub.com/Akshay1018/mcp-codedocupdated this year
Professional AI-driven code documentation & quality audit agent. Scans projects, identifies bugs, and persists reports locally via MCP.
MIT -
Go-only, report-first code scanner exposed as an MCP server. Indexes a module, runs deterministic analyzers, and reports genuine bugs, dead code, stale docs & outdated APIs — never editing your code until you ask.
MIT ★ 2 -
Free, AI-powered PDLC automation for Codex. Routes feature requests, bug reports, and architecture work through structured workflows.
MIT ★ 2 -
Free, AI-powered PDLC automation for Cursor. Routes feature requests, bug reports, and architecture work through structured workflows.
MIT -
Free, AI-powered PDLC automation for Claude Code. Routes feature requests, bug reports, and architecture work through structured workflows.
MIT -
Your agent watches your signed-in Chrome across tabs, sweeps your routes, and hands you the bug report. Local MCP server plus Chrome extension.
npm MIT -
interagentgithub.com/signalclaude/interagentupdated this year
MCP server for inter-agent communication between Claude Code instances. Send bug reports, feature requests, API specs, and status updates between agents.
MIT ★ 2 -
MCP server that fetches and explains syzbot Linux kernel bug reports - KASAN, KCSAN, lockdep, WARNING, hung tasks - with alloc/free stacks, cause commits and reproducers. Polite, cached, rate-limited.
MIT -
Public releases, installers, and issue tracker for MCPGate — an enterprise-grade MCP bridge and agent server. Source is private; download binaries, report bugs, and request features
NOASSERTION -
Let coding agents on different machines work together over an encrypted bridge: Claude Code, Codex, Cursor, Gemini. Backend ↔ mobile/web agents run test cycles: scenarios, test data, bug reports, fixes.
MIT ★ 2 -
Grow on Laravel. Run it with AI. A CMS with an admin editors already know — Filament or Nova, WooCommerce, ACF, MCP for AI agents — and a way in for your WordPress site. Questions, ideas and bug reports.
-
MCP server for Unreal Engine 5.3 to 5.8 and Blender: Claude Code or any MCP client works in the editor through typed commands, and every change is read back. Docs, links and bug reports here; the source is private.
NOASSERTION ★ 1 -
AI browser agent in Chrome's side panel, powered by a model on your own PC (Ollama, LM Studio, llama.cpp, vLLM). No account, no telemetry. Opt-in CAPTCHA solver, scheduled tasks, /test bug reports, and an MCP server for Claude Code.
MIT -
Free your Mi Bands, Garmin watches & Under Armour footpod! OmniBandBridge (OBB) tracks real-time running & walking data (cadence, speed, stride) from your wereable. Use it on Zwift, treadmills, or outdoors. Integrates FTMS speed/incline and HR to compute personalized metabolic power. Join our community to report bugs and suggest features!
★ 1 -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
Pack bug screenshots into AI coding instructions with MCP Server integration
npm MIT -
Universal Bug Triage & Upstream Router for Autonomous Coding Agents
MIT -
Local-first, agent-readable bug capture: annotated screenshots + notes stored locally, synced to issue trackers on your own schedule.
MIT -
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 -
🛡️ Autonomous Offensive AI Framework & Cognitive Multi-Agent Swarm for Red Teams & Penetration Testers. Polyglot Engine (C++20 SIMD, Rust Tokio, Go Prober, Python Swarm) with Zero False-Positive Proof Capsules & MCP Server.
MIT ★ 3 -
Turn a screen recording into annotated keyframes a coding agent can read. MCP server + CLI.
npm MIT -
Annotated screenshots for AI agents: Skitch-style arrows, numbered steps, boxes, labels, solid redaction
pypi AGPL-3.0-or-later -
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 -
Connect a repo to your Heresay so coding agents can install it and fix the reports your team accepts. MCP server, skill and CLI.
npm MIT -
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 -
Read-only agent bridge for QA Wrap: an MCP server (stdio) that reads sessions through Chrome native messaging. Local only, no network.
npm MIT -
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 -
Voice-anchored causal evidence recorder for AI coding agents — talk, point, and get an evidence package your agent can act on. 语音锚定的因果证据记录仪。
MIT ★ 1 -
flowlens-mcp-servergithub.com/magentic/flowlens-mcp-serverupdated this year
FlowLens is an open-source MCP server that gives your coding agent (Claude Code, Cursor, Copilot, Codex) full browser context for in-depth debugging and regression testing.
Apache-2.0 ★ 109 -
A small Mac tool: point at something on your screen and start yapping. Your coding agent gets it all via MCP, including what you pointed at and what you said. Free, open source, local.
MIT ★ 6 -
bugbounty.sa(bbsa): CLI + MCP server for bugbounty.sa — programs, reports (read, draft, submit), finance, leaderboard
pypi Apache-2.0 -
Blitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.
npm MIT ★ 518 -
h1mcpgithub.com/uunw/h1mcpactive
HackerOne MCP server in Rust — full HackerOne API coverage (reports, programs, scope, payouts, hacktivity) + local draft management, exposed as Model Context Protocol tools for Claude Desktop, Claude Code, and any MCP client.
MIT -
Proof-carrying debugger. Executes your code to find a real failing input, verifies the failure three ways before reporting it, generates candidate repairs, and rejects patches that only fit the example that caught them. CLI, MCP server, or programmatic AP
npm MIT