"An MCP to access OpenAI's RAG system via API" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceConnect and type "Use Ekaya to make my life easier". Your AI makes personalized applications.
Read your microservice catalog: MICROSERVICE.md files, contracts, and who depends on what.Read your microservice catalog: MICROSERVICE.md files, contracts, and who depends on what. What you can do: - Implement a service from its spec and contracts - Call or consume another service using its real contract - Check the impact of changing an endpoint or event before you make the change - Find a service in your catalog, or resolve it from the Catalog ID line in a repo's MICROSERVICE.md A microservice.md account is required.
Pugi is an AI product team in your chat. Describe a business in a few sentences and Pugi plans, designs, builds and checks a real website, shows a live preview, and puts it live on its own address. Ask for changes in plain words. Pugi also draws four whole logos for a business name with a brand kit, checks any public website or GitHub repository for leaked keys, vulnerable dependencies and risky code, and helps you start from public site templates. Sign in with a Pugi account (OAuth).
Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
Signed, traced record of what an npm package or file attempts when run, network included. No key.
mumo is a remote MCP server for multi-model deliberation. Your agent sends a question to models from different labs — Claude, GPT, Gemini, Grok, DeepSeek, Kimi, and more — and gets back their full responses plus typed cross-model reactions. The participating models react to each other directly and explain, in their own words, what they agree with, challenge, or want to explore further. Agents can run a deliberation with `create_deliberation`, wait for results with `wait_for_round`, and steer follow-up rounds with `append_round` using structured signals like KEEP, EXPLORE, CHALLENGE, CORE, and SHIFT. Built for architecture, plan/spec review, strategy, and pre-launch pressure tests. Free tier available. API key required.
Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.
Free 1-line peer-to-peer (P2P) mobile app cross-promotion for Android (Jetpack Compose), iOS (SwiftUI), Flutter, React Native, and Hybrid WebView apps. Delivers zero-dependency single-file SDKs, audience matching, and integration verification with zero ad spend, zero user tracking, and zero GDPR popups.
Writes your daily standup from GitLab or GitHub merge request state: what's ready, blocked or waiting on your review, and why a pipeline is red, read from the failing job log. OAuth sign-in, no API keys; can post the note to Slack, Discord or Google Chat on a schedule.
Crawl and scrape websites to clean markdown, and track what changed between crawls.
Design quality gate for AI-generated UI: score any URL on 45 deterministic checks, A–F grade.
Coding agents in multi-service codebases routinely rebuild existing helpers, trust stale type definitions, and modify API contracts without knowing who consumes them. Carrick solves this by indexing your entire TypeScript ecosystem across service and repository boundaries. By integrating deeply with the TypeScript compiler, Carrick traces every route, type, and cross-service call while recording function behaviour so agents search by intent rather than name. Delivered via MCP for AI agents and LSP for IDEs, Carrick ensures models see existing endpoints and utilities before generating new code. The scanner is source-available and runs from your CLI or CI pipeline.
Agent-native registry to discover APIs, MCP servers and CLIs, with live health checks.
Hubris is an OpenAI-compatible LLM gateway for the Russian market, billed in rubles. This MCP server gives agents access to the model catalog (400+ models with ruble pricing), account balance, and chat completions with full parity to POST /v1/chat/completions. Tools: models_list, models_search (filter by capability/price/context length), models_get_pricing, balance_get, chat_complete. Resources: hubris://catalog/models, hubris://docs/quickstart. Prompt: compare-models. Docs: https://hubris.pw/
Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.
Claude Code, Cursor, Codex, MCP docs. Needs X-Cohere-Api-Key header, free at dashboard.cohere.com
Upload files and get a share link anyone can open. Organize folders, add passwords, collect files.
Build, validate and deploy workflows as Cloudflare Workers in your own account, with approval.
A vault for .env files and project credentials: one encryption key per project, a second factor before protected values open, an audit row for every reveal, and scoped MCP access for coding agents.
Free premium UI components in plain HTML, CSS and vanilla JS, for AI coding assistants.
Find TypeScript source mods for billing, bookings, teams and other app features. Read product details and setup requirements, compare the published scope with your stack, and prepare a cart for human checkout.
Find and add animated SVG illustrations to your site from your coding agent. A free set, no account.
AI agents and scripts reporting back to your iPhone with Push Notifications and Live Activities.
Build and change Telegram bots by chatting: create flows, edit them, undo changes, add templates.
Two open-source SEO skill packs (Claude SEO, Illyism SEO Skills) served read-only to any AI agent.
Publishes what an AI made — a page, a markdown or PDF doc, or a whole site — to a live HTTPS link. Runs locally over stdio from the @drop2run/mcp npm package, or hosted at https://mcp.dropto.run/mcp for chats that connect by URL.
Check whether a repo, npm package or website is ready to launch and usable by AI agents, and find agents or MCP servers by what they do. Read-only, no key.
Official Model Context Protocol (MCP) server for **[F2H.io](https://f2h.io)** — instant file hosting, QR code handoff, password-protected sharing, and receive-inbox management for AI assistants and CLI agents. Connect Claude, Gemini, Cursor, or terminal agents (Claude Code, Gemini CLI, Copilot CLI) directly to your F2H account to upload, share, organize, and collect files without leaving your conversation.
Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.
Paste an error from a Supabase, Lovable or Bolt app and get the matching step-by-step fix guide.
Enhanciar is an AI company brain for every team. It reads your Slack, Gmail, Google Drive, Notion, Confluence, Jira, Linear, Zendesk, GitHub code and databases, writes a wiki from them, and answers questions from any MCP client with a link to the source. Tools: query (cited answers), search_wiki, get_page, list_pages, get_graph, get_process_map, impact (what a code change touches), list_repos, list_skills, get_skill, propose_action and list_proposed_actions (tickets, Slack messages, Gmail drafts, Notion pages and calendar holds that a person approves first). Hosted service, bring your own AI key. Plans: Solo $24 a month, Team $100 a month for up to 10 people. Create an API key in Settings at https://enhanciar.in.
Web animation accessibility MCP: GSAP, static CSS checks, prefers-reduced-motion, WCAG 2.2.2/2.3.3.
Use your own Windows, Mac or Linux computer from ChatGPT, Claude, Cursor or Gemini CLI: run commands, read, write and search files, run long processes. Your computer only makes an outgoing connection (no open ports or VPN). Read-only mode, allowed folders, blocked commands and an action log keep you in control. Free plan available.
Supercharge your AI workflows with PromptingEasy! Create structured, ready-to-use prompts for writing, travel, cooking, business, and more. Access 10 specialized prompt generators in 22 languages through a free, public MCP server. Discover generators, explore their options, and create reusable prompts directly from compatible AI assistants and agents. **100% free. No signup, API key, or payment required.** PromptingEasy generates prompt text — it does not execute AI models. Explore all generators: https://promptingeasy.com/generator/
Find open-source GitHub issues to contribute to, matched to your skills; you approve every PR.
Run saved PDF/office file flows, convert HWP/HWPX to Markdown or DOCX, and call data/text APIs.
Run Python, Java, C, C++, C#, Go, Rust and 39 more languages, each run in a fresh, offline sandbox.
Design your mobile app UI with AI, then have your coding agent build the real app from it.
Search and pull 620+ React and Tailwind sections into your project over MCP.
The Excel engine for AI agents: read, check and edit Excel models over MCP.
Discover APIs, inspect schemas and pricing, and call live data through ApiClay’s hosted MCP server. For apps and AI agents. Requires an ApiClay buyer API key as a bearer token. API calls may consume credits.
HefestoAI checks AI-generated code before you ship it.
Check an npm/PyPI package before an AI agent installs it: 5 focused supply-chain tools.
Deploy your project to a live HTTPS URL from your AI tool; read logs, set variables, resize apps.
Validate and generate German e-invoices (XRechnung, ZUGFeRD) against the official KoSIT rules. Every business-rule finding comes with a plain-language explanation of what the rule requires and how to fix it. Validation needs no account; generation uses your NormAPI account via OAuth. Invoices are never stored.
Publish and manage static websites from Claude, ChatGPT or Cursor. SoFast's remote MCP server lets your AI assistant create a site, upload the HTML/CSS it generated, publish it with HTTPS on a free subdomain or your own domain, and pause, rename or update it. OAuth sign-in, no API key. Setup guide: https://www.sofast.host/mcp/
Search animated React components and get their props and source to install with shadcn.
DevSpeak is a writing tool for developers, available to your coding agent over MCP. Call `optimize_text` to improve a PR description, commit message, ticket or doc in the language it was written in, or set `correctionsOnly` to fix only spelling, grammar and punctuation. Call `translate_text` to turn rough notes into a technical spec, Jira tickets, an RFC, an API design or a data model for the audience you choose (Junior Dev, Senior Dev, Tech Lead, SRE or Data Engineer). It also translates README files with `translate_markdown`, refines earlier output and lists your history. Requires a DevSpeak API key; a free account includes one key with 50 API requests a month.
Docs, code patterns and device kinds for the Velvet Bluetooth device SDK and Velvet Live API.
Free MCP server of security & dev API tools -- supply-chain, CVE, DNS, WHOIS, OFAC, Cosmos SDK.
Publish static websites (HTML, CSS, JavaScript) to a sofast.website address from your AI assistant.
Which LLM should I use for this task? Ask in plain words and get the models that score best on the matching benchmark board, within your price, context window and open-weights limits. Covers 400+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, Mistral and more, with benchmark scores (coding, agentic, reasoning, math, knowledge, design) and API list prices per million tokens, updated daily. Tools: recommend_model, get_leaderboard, compare_models, get_model, get_prices, list_categories. Free, no API key, data under CC BY 4.0. Docs: https://llmbenchmark.ai/api
Publisle MCP is a hosted, remote MCP server for Publisle, a portable document schema and compiler for developers. Agents can import Markdown or JSON into Publisle's semantic document model, edit it block by block, validate it, and compile the same source to static HTML, PDF, or Markdown, so one document keeps the same meaning everywhere it ships.
Live prices for 111 Chinese models; batch cost calculators for video and images.
The cloud for the age of AI agents: easy deployment and ready-made solutions. Your agent deploys apps, sites, databases, storage, email and domains on Galon, from a free plan.
Keeps the rules, decisions and fixes you explain to your AI, for every session and tool. EU servers.
OpenAny is the B2A (business to agent) marketplace. Add one MCP endpoint, https://mcp.openany.si, and your agent can find and use 3,200+ APIs and 168+ AI models. APIs cover social and content (X, TikTok and more), SEO, search and scraping (DataForSEO, Serper, Tavily), crypto and on-chain data (CoinGecko, DefiLlama, DexScreener, Hyperliquid, Polymarket), company and lead data (Hunter, Crustdata, QCC), finance and macro (FRED, Financial Datasets), and legal (PKULaw). Models include chat and reasoning (GPT, Claude, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax), image (Midjourney, FLUX, Nano Banana, Seedream, GPT Image), video (Veo, Kling, Seedance, Hailuo, Wan) and audio. Searching and checking prices is free with no key. You only need an OpenAny API key to run a call, and you pay per call.
Agent-first hosting: create projects, push code, and deploy to HTTPS URLs from your coding agent.
Check before your agent installs, connects or pays. install_check: before installing an npm or PyPI package, a GitHub repo, a skill, an editor extension or an MCP server, it answers allow / hold / block (known malicious packages from OSV, typosquats of official MCP servers, names that do not exist, install scripts, maintainer changes). check_repo_config: before opening a repository someone sent you, it reads its agent configuration (MCP servers, hooks, editor tasks, instruction files) and runs nothing. check_service and verify_tools: live status of any MCP server or x402 endpoint, real price and payTo vs the catalogue listing, OFAC and stablecoin-freeze screening, tool-set changes, an open Trust Score. find_service finds working services. preflight_payment decides allow / hold / block right before an x402 payment is signed; payment_status prevents paying twice; report_purchase records what a paid call delivered. Verdicts are signed into a public transparency log. Free, no account. Every other tool (evidence packs, agent identities, boards, mail) is at https://alalanet.com/mcp/full; install and MCP-server checks alone are at https://alalanet.com/mcp/guard. Claude Code plugin: alalanet-guard.
Build it. Rehearse it. Own the room. The hosted MCP server for Kadal Deck (deck.kadal.cc), which has your back for the whole talk, from the first idea to the last applause. Connect once with OAuth and your AI agent can list and inspect your decks, read a talk in progress (current slide, who is watching, polls and questions by votes), check analytics, change titles, visibility and passcodes, roll back versions, create share links, and quick-edit and publish decks through the web builder, with conflict-safe publishing that never overwrites newer work. Pair it with the local server (npx @kadal/deck mcp) to write, check and build decks on your machine. Open source.