"Creating a Framework Design in Draw.io" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
formcarry handles everything after your form is submitted: it emails you, auto replies to the person who submitted, filters spam, and delivers webhooks. You write the HTML form and set its action to a URL formcarry gives you. An agent can create a form, wire the emails and webhooks, and answer questions about the submissions, like how many signups last week.
Go MCP server for GitLab: 2 dynamic tools reach 1000+ REST/GraphQL actions. Free/CE, no paid tier.
Run a GPU job under a hard dollar cap and collect the files it writes.
Discovery registry for AI agents: 660+ APIs, MCP servers and CLIs, each health-checked every 6 hours with real requests — full initialize + tools/list handshakes for MCP, real calls for APIs — plus response-schema validation that catches responses which parse fine but are missing a required field.
Narrated demo and tutorial videos of your web app, from a guide or your coding agent.
LaunchOnIt is a weekly launch platform and discovery directory for modern SaaS, developer tools, and AI startups. This MCP server connects AI assistants directly to LaunchOnIt’s live software catalog, rankings, and launch infrastructure. Search launched products, weekly leaderboards and podium winners, check open launch slots, and submit a product launch for review.
The official hosted MCP server for the Unipile API. Your coding agent reads the exact API contract for LinkedIn (Classic, Sales Navigator, Recruiter), WhatsApp, Instagram, Telegram, Gmail, Outlook, IMAP and Google/Outlook Calendar, writes your integration in your stack, and tests each call on your own connected accounts. Five tools cover every route: search-endpoints, get-endpoint, list-endpoints, list-specs, execute-request. Key: a scoped Account API key in the X-API-KEY header, optional for reading the docs.
Daily 0-5 Pressure readings of the global macro field for AI agents, plus a way to send feedback.
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.
A real cloud Mac with Xcode for your AI agent. Start a macOS VM, run commands (git clone, xcodebuild, simulator tests), read the output and stop it; billed from prepaid credit at $0.80 an hour by the minute. Optional App Store Connect tools upload builds to TestFlight and manage the listing, with previews before any change. OAuth sign-in, nothing to paste.
Deploy your project to a live HTTPS URL from your AI tool; read logs, set variables, resize apps.
Search real-world UI & UX design references for mobile apps, web apps, and websites with Mobbin.
A portable knowledge-graph memory you pass in and get back. No database. 4 of 6 free.
Search 161,000+ free hand-drawn Infyicon icons in four matching styles and fetch ready-to-embed SVG markup or PNG URLs, plus CSS class lookup for the 61,000-glyph Infyicon UI webfont. Free with attribution, no API key required.
Social cards and OG images from designed templates: card from a URL, presets, meta tags, link checks
Check a product CSV, handles, variant matrices and metafield keys. 4 of 6 free.
The elmah.io MCP server allows AI assistants to interact directly with your error logs, deployments, and organization statistics. Debug production issues faster than ever before.
Magery Forge is a security-audit engine for people who ship code fast and don't have a security team. Use cases: • Pre-release security check • Weekly automated security monitoring • Agent-driven security scanning (MCP) • Clearing a shipped product of common vulnerabilities before users hit them
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
Turn a written policy into rules a program can check, and get the same answer every time.
