Development MCP Servers

Type-safe Python client for Valorant esports data from VLR.gg.

thumbs gives Claude Code or any MCP client an iPhone to see, tap and type on, through one remote URL (https://mcp.usethumbs.com/mcp) with Google sign-in. Early access runs on the iOS Simulator; free, waitlist, allowlist-only for now.

Director lets you record polished demos of your web app from one sentence, with auto-zoom, a smooth cursor, narration and captions, and turn its product map into help articles and more.

Hash anchoring and proof-of-existence on chain for AI agents and apps. Free with an API key.

Post-quantum readiness for government and contractors: checks sites for quantum-safe TLS, scans code, and builds signed EO 14409 / OMB M-26-15 packages with a CycloneDX CBOM. Free.

One remote MCP server for about 370 ready-to-use APIs: validate emails and phone numbers, look up IPs, DNS, WHOIS and SSL certificates, get exchange rates, stock and SEC data, decode VINs, generate PDFs and screenshots, and more. OAuth or API key.

Access versioned skills and Binders from AI assistants. Requires a Bindry account and workspace API key.

Deterministic developer utilities as MCP tools: UUIDs, passwords and tokens, hashing and HMAC, Base64 and URL encoding, JWT decoding, cron next-runs, timestamps, JSON formatting, diffs, regex testing and text counts. Runs entirely on your machine: no network calls, no telemetry, no API key.

Lets AI coding agents read the errors, logs, and traces of the projects you approve, so they can find what broke in production and check their fix. Hosted, read-only, OAuth. Free plan: 50 GB of logs a month.

Zero-dependency, RAM-only HTTP diagnostic proxy and MCP server in Go. Replaces credentials with salted SHA-256 correlation tags so AI agents can debug auth flows without secrets touching disk or entering LLM context.

Validate Mermaid syntax, get error details, and export diagrams through MCP and REST.

App Store + Google Play data API and remote MCP server: apps, reviews, keywords, rankings, top charts and competitors for Claude, ChatGPT and Cursor.

Ask your agent how your mobile apps are doing: live activity, App Store, Google Play and RevenueCat reviews and sales, ads, and why a number moved. Read-only.

Checks websites for WCAG 2.2 AA accessibility (European Accessibility Act, ADA). Free, no account: search and explain any axe-core rule or WCAG criterion, with fixes for code, Shopify, WooCommerce, PrestaShop and Shoptet. Signed in with OAuth or a Pandus API token: list your sites, see what to fix first, open a problem, start a check and compare results. Automated check, not a full audit, not legal advice.

Per-customer API usage analytics for small B2B APIs. Counts requests by customer, endpoint and plan; MCP tools create_account, get_ingest_snippet, get_usage, export_usage. Free tier 250K requests/month. Remote endpoint (Streamable HTTP): https://api-meter-lab.pages.dev/mcp

Let your Agent fix, test and automate native iOS and Android apps on cloud real devices: tap, type, swipe, debug and inspect, no setup needed.

Free MCP server built into AI Engine, a WordPress plugin with 90k+ installs. Claude and ChatGPT connect with OAuth: no account, no daily cap, no API key, no relay. Manage posts, pages, media, terms, comments and users. Official ChatGPT app and Claude directory listing.

Uptime and incident monitoring for apps built with coding agents. Ask your agent what's broken: it reads status, uptime, response times, incident evidence and SSL and domain expiry. It can scan an app, set up its checks, status page and cron heartbeats in one call, add a monitor, pause monitors, and draft an incident update for you to publish. Sign in with OAuth or use a workspace API token.

Remote MCP server for the Mythex AI app builder: Claude, Cursor or Codex create projects, edit code and run bash in a cloud sandbox, preview, add a Postgres database and publish to a live URL.

Publish browser games made with AI just by asking: your AI uploads, tests and shares the game on Asobiai (leaderboards, comments, online multiplayer, game jams).

Typed AI decisions for agents: classify, route, screen evidence, score and batch-label text.

Convert, lint and generate LLM tool schemas across OpenAI, Anthropic, Gemini and MCP. Free tier (5 calls/hour), then pay per call via x402 (USDC on Base). Built with AI assistance.

EVM smart-contract AI risk screening MCP server — Ethereum Mainnet, payable per call with x402 micro-payments in USDC on Base.

Thunderstore mod search, dependency checks and r2modman export. Not affiliated with Thunderstore.

Leadpages MCP connects AI assistants like ChatGPT, Claude, and Cursor to Leadpages, enabling users to create, edit, and publish landing pages, websites, and sales funnels using natural language. Built for developers, marketers, and founders, it supports lead generation, marketing automation, landing page SEO, and conversion optimization through AI-powered workflows.

Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.

GitHub Trending boards, AI-written project reviews, and trending history for AI assistants. Search open-source projects by topic and access monthly reports through six tools. Free API key available.

Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

Open-source proxy that sits in front of any MCP server and gates tool calls by whether their effect can be undone: reads pass, reversible changes are rolled back if the run fails, irreversible calls wait for a human to approve the exact request.

Translates MCP tool errors into next actions — Solo $9, Fleet $19 /mo + $0.002/check