Development MCP Servers

Connect Claude, ChatGPT, Cursor or any MCP client to Ybug. Read bug reports with screenshots, console logs and network requests, then triage them in chat.

Live ticket listings, prices and fees from 10 major ticket marketplaces, in real time. Ask your AI assistant about any event and get current inventory with all-in pricing.

KG Agent Exchange, also known as SI Dog Park, is a remote MCP server for publishing, searching, and retrieving information. Connect over HTTPS Streamable HTTP and use publish_information, search_information, and get_information. Every information operation requires x402 v2 payment. Entries can include source URLs, a source update time, and a publisher-provided claim status. That claim is self-reported, not independent verification.

Lets coding agents draw: charts, mermaid, maths, 3D scenes, molecules and infrastructure topologies whose steps play, as PNGs or a live browser page. Fills charts from CSV/JSON files, checks drawings for overlapping or clipped labels, and exports PDF, standalone HTML or GIF. Runs locally; also a Claude Code and Codex plugin.

14-tool MCP for ADEXTO bonding-curve markets on five chains: data, history, quotes, x402 buys, and unsigned launch, stake, and claim transactions.

Sanctions API docs and request validation, with account-linked synthetic sandbox testing.

After your coding agent finishes a task, Atomic Reps asks you questions on the libraries and concepts it used. Works in Claude Code, Copilot, Cursor and Codex.

Trust layer for MCP servers: static and behavioral security scanning, fuzzing, and Ed25519-signed version-pinned badges published to a public git-backed index.

MCP server for React Native and Expo development. It lets your coding agent drive and test your app end-to-end on both iOS and Android. Supports real devices and simulators/emulators.

LiteBin is a self-hosted PaaS for side projects. This MCP server gives coding agents deploy, logs, health checks and runtime secrets as first-class tools over stdio.

UAE trade-licence company search by English/Arabic name, emirate, legal type and registration date.

Public MCP door for Aziel Runtime. Remote streamable HTTP. Already on the official MCP registry as io.github.AzielEliab/aziel-runtime 2.0.0-rc1.

RugSnare - Pin MCP tool contracts by hash; catch silent drift, rug pulls and per-client bait-and-switch after approval with a CI gate and live stdio/HTTP proxies.

Local MIT-licensed AI test harness: risk-based test workflows, evidence, screenshots, confidence summaries and interactive HTML quality reports. No hosted backend required.

Local shadow MCP for HVAC, plumbing, electrical, and sewer. Read-only public door. Not a hosted company OS.

MCP server exposing GovContractScout's US state & local government contracts API to AI agents — search contracts, get details, NAICS lookup, AI match scoring.

Zero-dependency Clean Architecture linter and context generator MCP server for Claude Desktop, Claude Code, and Cursor.

Public read-only discovery of GXEON agent utilities, prepaid request packs from R$0.99, and buying guidance; paid execution uses a separate authenticated endpoint.

Connect an AI assistant to aCelery, describe the app you want in plain words, and it writes the app, creates its database, runs it on your phone, checks for errors and fixes them — while you watch.

Click an element in your running web app or the iOS Simulator and say what should change; your coding agent (Claude Code, Cursor, Codex) gets your comment with the selector, DOM path, styles, component chain, source-file hint and a cropped screenshot. Local only, MIT.

Drop-in read-only replicas of GitHub, Jira, Slack and 18 more, preloaded with one fake company.

AI Powered dummy data generator and API Mocking tool

Read-only MCP for announced Claude Code usage-limit resets, with Codex comparison. Not affiliated with Anthropic.

Explains known developer errors offline and deterministically (CORS, ESM/CommonJS, npm ERESOLVE, ChunkLoadError, Next.js build, Postgres connection and DATABASE_URL errors): documented cause, ranked fixes and the documentation link. One tool (explain_error), no LLM, no network, secrets masked. MIT, zero dependencies. Submitted by the author via an AI agent.

Build and publish full-stack apps from your coding agent: models, rules, pages, auth, per-app MCP.

Search and read Linux manual pages with version-aware lookup, helping AI assistants find accurate documentation for commands, libraries, and configuration files.

Speeds frontend reviews by placing comments directly on a deployed preview environment, which are then resolved by agents. A CI check holds the merge until all comments are resolved and maple's visual lint gates pass.

Laravel schedule and queue monitoring. Catch silent cron, queue, and agent failures before users do.

A compiler-backed coding agent that compiles your codebase into a resolved, queryable map of calls, data flow, control flow and class hierarchy first; then it reads, explains, runs, edits and verifies your code using it.

Free checks that find the one fix on a web page or deployment (Design UX check, Deployment Trust packet), built for AI-built sites and usable by AI agents over MCP and A2A.