MCP Server Directory

QuickBuild agent tools (x402) dev.workers.quynguyenbac.quickbuild/agent-tools

LaunchCheck site reports, screenshots, audits, TTS, translate, Base data, LLM chat; x402 per call

PaperAgent — Send Physical Mail dev.paperagent/letters

Mail one-off USPS letters from ChatGPT or Claude after you approve the preview and price. US only.

fline sh.fline/fline

Hosting for apps you build with AI. Tested with Claude Code and Codex. Private beta: ask for access.

OmniProvider tech.omnidev/omniprovider

Pay-per-call LLM API for agents: model catalog, pricing, unpaid x402/MPP quotes, how-to-pay.

Validate, plan, preview and run YAML data pipelines (ETL with LLM steps) and debug failed runs.

NOAA RTOFS global ocean forecast — SST, salinity, currents, depth profiles via HYCOM THREDDS

WhizzyCommerce com.whizzycommerce/whizzycommerce

Run your online shop from Claude: orders, prices, sales, catalogue and design, confirmed by you.

More AI - ChatGPT & Claude MCP (Fortnox) cloud.amore.accounting/fortnox

Fortnox MCP server: ask ChatGPT or Claude about your books, and approve every change first.

Vazante app.vazante/vazante

Ask Claude or ChatGPT about your Meta, Google and TikTok Ads, and let AI edit campaigns on your OK.

Mac app that runs Claude or Codex on a schedule against your mail, calendar, and files.

Check if your exit IP works for ChatGPT, Claude, Gemini: ASN, proxy/IDC type, risk, AI availability

AgentsIndex ai.agentsindex/mcp

The editors' index of AI-native software, from AI agents to the models and frameworks behind them.

Turn any web page into clean Markdown, text or token-bounded RAG chunks (via RapidAPI).

MyLeadTech HVAC app.myleadtech/mcp

HVAC MCP server — fault codes, model lookup and answers cited to the OEM manual page.

Local Cicadas MCP for models, quotes and status. Authenticated API flows not yet verified.

ClipOnIt io.github.MattJeff/cliponit

Turn long videos into short, subtitled, auto-reframed clips from Claude or ChatGPT.

MiniRAG io.github.KiMelody/minirag

Lightweight self-hosted RAG knowledge base with hybrid retrieval and cited answers.

Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.

Crypto-paid uncensored LLM inference with signed execution receipts. No account.

Atwork so.atwork/workspace

Connect Claude, ChatGPT or any MCP client to your Atwork sheets, tasks, pages and dashboards.

Hand tasks from Claude Code, Codex or any MCP client to a local DeepSeek Harness.

Query OpenRouter (free key; set OPENROUTER_API_KEY, Bearer): model list, key info, credits.

AI meta harness for Codex, Claude Code, Cursor and VS Code: direction and completed-work review.

Brain Memory ai.brainmemory/brain

Persistent memory for AI agents: one brain shared across Claude, Cursor, Codex and more.