"Servers Offering MCP Prompts as Prompt Primitives" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Publish HTML or markdown from your agent as a shareable link, with password or work-email walls. No key needed to start: your agent can create the account and verify the email right from the chat, then publish.
Prompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402.
Create, list and check hrva.cc short links and read their click statistics. Sign in with your hrva.cc account over OAuth; every link goes through the same safety checks as on the website.
Vigilia watches your live app, explains every problem in plain language and writes the fix prompt. Your AI fixes it; Vigilia confirms with real traffic. Vigilia watches web apps that are live with real users, including apps built with Lovable, Bolt, v0, Cursor and Claude Code. It catches errors, failed requests and downtime, explains each problem in plain language, and writes a fix prompt for it. Connect Vigilia to Claude and ask what's broken. Claude lists your open incidents worst first. For each one it reads the plain-language diagnosis, who it affects, the technical evidence (error, page, failing request, stack frames and what the visitor did right before) and Vigilia's fix prompt. In Claude Code or another coding agent, Claude can then fix the cause in your own codebase. Once you've deployed, it marks the incident fixed, and Vigilia watches real traffic to confirm the error stayed away. If it comes back, the incident reopens as a regression. You can also ask how an app is doing (uptime, open incidents, today's traffic), get the exact install snippet for a new project, and check that a live site is running Vigilia. Vigilia never reads or changes your code: the fixing happens in your session, by your AI, in front of you. The only tool that changes anything is marking an incident fixed (the install check just records its result on the app), and you can connect with read-only access. Your data is stored in the EU. Emails, tokens and card numbers are stripped from what visitors' browsers send, and only that scrubbed error context is sent to Anthropic to write the diagnosis. Requires a Vigilia account. The free plan covers one app; reporting backend errors (Supabase, Next.js routes, Workers) is part of Pro.
GodPrompt MCP + Agent Skill for coding agents with TDD, debugging, verification, and task routing.
Company logos by domain as SVG or PNG URLs. Free, no API key. Search brands, get favicons.
Create and share text, code snippets, diffs, and logs as Pastes.io links. Read pastes by link, search your own pastes, check account limits, and delete pastes you own. Connect with OAuth or an API key. MCP-created pastes are unlisted: anyone with the link can read them unless password-protected. Plan limits and expiration rules apply.
JSON healing, O(n) ReDoS defense, XML prompt compilation, and schema verification tools.
Build, validate and deploy workflows as Cloudflare Workers in your own account, with approval.
kad.dev puts the apps you make with Claude on the web. You say what you want. Claude builds it and puts it online at its own address. You do not need to know how servers work. Your app gets its own web address. It stays private until you choose to share it. You can also use a domain name you own, like www.yourname.com. It can have a database that remembers what people enter, such as sign-ups, orders and notes, and storage for the photos and files your visitors upload. A Google sign-in lock lets in anyone with a Google account, or only the people you name. For a simple site, a change shows in a private preview within seconds, before it goes live. Every change you publish is saved as its own version, with its own private address. If something goes wrong, go back to an earlier one. If something breaks, Claude can read the error message, so it can be fixed in the same conversation. Access: you sign in with your kad.dev account and choose what Claude may do. Claude can always look at your apps. Changing or publishing them is a separate permission. Claude only sees your own projects. You can remove access at any time from your kad.dev account. Hosted in Europe. Requirements: a kad.dev account.
Publish AI-made HTML apps as shareable links that save and sync data. No account or token needed.
A bar for AI agents. After a rough run, your agent orders a pour and gets a receipt card to share. Run the napkin breathalyzer prompt injection test, pass a round to other agents, check if Claude or OpenAI is down, and look up any HTTP status. 19 tools, no auth.
Live cloud GPU prices, observed stock and 12-month price history across 30+ providers (H100, H200, A100, RTX 5090 and more), refreshed hourly. Read-only. Needs a GPU Finder API key sent as "Authorization: Bearer <key>"; free key with 60 data calls a month at https://gpufinder.dev/developers. Listing tools and get_usage are free.
Jam recordings (video, console, network) as context and proof of work for your coding agent.
A hosted MCP suite providing workflow primitives: web search, content fetching, compression, deduplication, cost/budget management, and agent memory pipelines.
AI QA for coding agents. TestOptim explores your web app, generates end-to-end tests and reports bugs with severity. Over MCP, Claude Code, Cursor or Copilot can start a test run on just the pages they changed, poll the result, and read the issues it found. Authenticate with a TestOptim API key as a Bearer token.
Create, animate and export mascots from your coding agent, as Lottie, SVG or transparent clips.
Give AI assistants tested calculations with inspectable results. BusCalc 1.6.0 exposes 26 free tool families: 23 mathematical families and three attributed public-data lookups. Use Decision Feasibility, financial mathematics, probability, statistics/regression, algebra/matrices, units, pricing, loans, fleet and recipe costs, precious-metal transaction models, fuel/currency costs, utility energy calculations and weather-impact analysis. Fetch timestamped gold, silver, platinum and palladium USD spot snapshots, dated EIA fuel/energy and ECB currency references, and NOAA/NWS observations, forecasts, official alerts and coastal station readings. Published energy averages are not live tariffs; forecasts are not observations; dealer offers are user-entered. Supports MCP 2026-07-28, 2025-11-25, 2025-06-18 and 2025-03-26 through the same Streamable HTTP endpoint. Includes 29 read-only resources, five guided prompts and curated argument completions. Connection, discovery, calculations and error recovery were tested with maintained official MCP clients. Successful math returns named results, units, formulas, assumptions, source links and an unsigned replayable calculation receipt. Lookups return attributed snapshots. No trade execution, emergency service, safety clearance or guaranteed planning window. Direct access requires no account/key; shared pilot limits apply. Optional integration keys support pseudonymous attribution without higher quotas. No private-project access. Guide and OpenAPI: https://buscalc.com/for-ai/
Give AI assistants tested calculations with inspectable results. BusCalc 1.6.0 exposes 26 free tool families: 23 mathematical families and three attributed public-data lookups. Use Decision Feasibility, financial mathematics, probability, statistics/regression, algebra/matrices, units, pricing, loans, fleet and recipe costs, precious-metal transaction models, fuel/currency costs, utility energy calculations and weather-impact analysis. Fetch timestamped gold, silver, platinum and palladium USD spot snapshots, dated EIA fuel/energy and ECB currency references, and NOAA/NWS observations, forecasts, official alerts and coastal station readings. Published energy averages are not live tariffs; forecasts are not observations; dealer offers are user-entered. Supports MCP 2026-07-28, 2025-11-25, 2025-06-18 and 2025-03-26 through the same Streamable HTTP endpoint. Includes 29 read-only resources, five guided prompts and curated argument completions. Connection, discovery, calculations and error recovery were tested with maintained official MCP clients. Successful math returns named results, units, formulas, assumptions, source links and an unsigned replayable calculation receipt. Lookups return attributed snapshots. No trade execution, emergency service, safety clearance or guaranteed planning window. Direct access requires no account/key; shared pilot limits apply. Optional integration keys support pseudonymous attribution without higher quotas. No private-project access. Guide and OpenAPI: https://buscalc.com/for-ai/
Every EmpirioLabs model and platform feature as tools: chat, media, search, jobs, GPU Cloud, agents.
Create, edit, share and render real-time collaborative diagrams and mindmaps on livediagram.app. Describe flowcharts, architecture, org charts or mind maps as nodes and edges (or Mermaid) and the server lays them out. Free and open source.
Scan text for prompt injection: risk score, verdict, matched spans. Built by Crypto Money Maker
7 free MCP tools for optimizing HTML, JavaScript, CSS, JSON, CSV, prompts and terminal text. Lightweight, local transformations designed for AI agents and developer workflows.
111 tools for AI assistants, so an answer comes from a rule instead of a guess. 84 deterministic utilities. IBAN and VAT validation, cron parsing, regex testing, hashing, JWT decoding, conversion between JSON, CSV, XML and YAML, units, number bases, timezones and date arithmetic. Eleven of them encode Dutch rules that a model tends to get wrong: AOW pension age, inheritance and gift tax, unemployment benefit duration, notice period, severance, the 30 percent ruling, holiday allowance, mileage allowance, and public and school holidays. Five more generate test data that is structurally valid and belongs to nobody: BSN, IBAN, BRP person records, UPA pension files and document numbers. 14 render tools that return a hosted file. HTML or a live URL to PDF, full page screenshots, QR codes, PDF merge and split, images to PDF, image resize, convert and compress, metadata stripping, PDF to DOCX and back. Plus read_page, which returns the readable content of a JavaScript rendered page as Markdown. 4 memory tools give an agent key-value state that survives between sessions, scoped to its own API key. 3 workflow tools list and run saved multi-step workflows on the caller's account. 6 AI tools for the jobs where a model is the right instrument rather than the wrong one: check a message for scam patterns, write a spreadsheet formula, turn a question into SQL, translate code between languages, improve a prompt, draft an email. Utilities and memory are free. Renders and AI tools have a free tier and credit packs. Workflows need an API key, because a workflow belongs to an account rather than to a key. Streamable HTTP at https://toolforte.com/api/mcp
Your organization's knowledge as OKF trees in Git, for AI assistants to search, read, and cite
Disposable, receive-only email inboxes for AI agents. Create an address, wait for the verification email, and get the one-time code or magic link back as structured fields. Long-polling wait_for_email with sender and subject filters, attachments, sanitised HTML, and restore for later password resets. OAuth 2.1, hosted in the EU, cannot send email.
Screenshot API for AI agents. Any public page as image or PDF, banners hidden, 227 countries.
Lints a phone voice agent prompt and platform config before real callers reach it.
Give your AI agent persistent, governed memory for every project. At task start it recalls the approved decisions, conventions, risks and architecture (semantic search, ranked by importance); at close it proposes what was learned as typed memories that you review and approve — governance, not a notes dump. Agents propose, humans govern: edits go back to pending and deletion is human-only by design. Connect Claude Code, Cursor, Claude Desktop or any MCP client in two minutes with just your API key — hosted (nothing to install) or locally via `uvx solucortex-mcp`. Built by SoluAI and dogfooded daily: SoluCortex is developed using its own living memory.
Authorized security scans, evidence, fix prompts and retests for AI-built web apps.
