"Hosting Supabase on Your Own Server" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Execution platform for AI agents on Firecracker microVMs in the EU. Interactive Linux sandboxes with root, templates for Python, Node.js, Go, Rust and a headless browser, public HTTPS URLs. Background jobs that outlive the connection, batches of up to 1,000 jobs with dependencies, hard cost caps reserved up front, execution receipts with SHA-256, log digests that fit the context. IPv4, dual-stack or IPv6-only with its own public address, allowlists or no network. WASI runtime for small tasks. Idle sandboxes sleep and keep their files. Also REST API, Python SDK and LangChain.
Lean4 formal proof, delivered per API call as an atom service on Conduit Atoms.
ParallelSandbox lines up your AI's test builds: use one, talk, circle what's wrong, get the next.
Algorithm design implementation, delivered per API call as an atom service on Conduit Atoms.
Linux sandboxes billed by the second from a prepaid balance, and GPU pods on your own RunPod key.
Universal pay-per-call tool API for AI agents. Web search, price feeds, hive memory, LLM routing, code sandbox. Free tier (10 calls/day, no signup). x402 payments on Base + Solana.
Hextrap's MCP Connector protects your LLM coding sessions from installing malicious dependencies, typosquats, unpopular packages, and enforces your strict allow and deny lists. No setup means your LLM uses MCP to configure itself to use Hextrap's proxy's automatically, enforcing your firewall rules immediately. Manage your allow and deny lists right from your favorite LLM.
A deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.
Let your AI assistant build a runnable Symfony 8, Laravel 13 or plain PHP 8.5 project and hand you a shareable link. The code runs in the browser with WebAssembly: no install, no account, nothing stored server-side (the code travels inside the link). Tools: get_starter (starting project, editable paths, Composer packages), create_sandbox (builds the link), read_sandbox (reads the code behind a link). Great for demos, answering questions with runnable code, or turning a bug from your project into
A browser 3D CAD for your AI: it scripts real-size models, uCAD builds them and returns pictures.
AI Sandbox Environments: the site's own MCP server — enquiry (enquiry = a human handoff, not a...
Low on memory? Your bot sends heavy jobs to cloud sandboxes on your own provider keys. Flat fee.
One sentence to a finished animation: your AI writes motion graphics as code and checks real frames.
Hand routine JS/TS tasks to Codemind from your agent. $0.10 per verified build; failures are free.
Docs for hot-module-reload and reactive programming for Python (`hmr` on PyPI)
40+ developer tools from Context7, Code Runner, Python Execute, NPM Sentinel, PlantUML, and Microsoft Learn. Docs lookup, code execution, security scanning. Starts at $0.01/call. Get your API key at app.xpay.sh or xpay.tools
Spin up a complete OpenCode development environment on any Linux box — one agent-driven workflow, six tools, zero secrets.
A persistent workspace for your AI. Connect with OAuth and your AI gets files, a code sandbox, scheduled jobs, webhooks and about 50 tools, with your API keys held in an encrypted vault it never sees.
Provides access to TakeProfit.com's Indie documentation and tooling — a Python-based scripting language for building custom cloud indicators and trading strategies on the TakeProfit platform.
Anima MCP connects your AI coding assistant directly to Anima Playground. It bridges the gap between PM prototypes and production code.
Create, schedule, and run JavaScript jobs, manage files, and inspect runs from your AI agent.
Run, build, and validate firmware on virtual hardware from your AI agent. Hardware knowledge corpus.
Your agents' cloud for individuals and teams. Search, execute, packages, jobs, and credentials.
MCP hosting for AI agents: Claude or Codex writes the code, runs it and sends a live link.
Open-source vibe coding hosting over MCP: your agent builds, previews and publishes web apps.
Run isolated code and manage apps, databases and deployments on Lizard (lizard.build).
Build, run, inspect, and continue AgentScript workflows on connected Super Chrome and Mac clients.
Your AI writes Go trading strategies; kdraigo backtests them on one-minute Binance and Bybit data.
Create, deploy and run serverless JavaScript functions on microfn from any MCP client.
Generate a Flutter app from a JSON spec free; pay only for the compiled APK (USDC on Base).
Run your end-to-end tests, read why they failed, write new tests. Sign in with OAuth.
Cloud Linux VMs for your agent: run code, Docker, files and HTTPS previews in a Sandboxer microVM.
Codex run receipts your reviewer can trust.
GPU compute for agents: run commands on an L4/A100/H100, watch logs, billed per second.
Create AgentUI data apps: define tables, read and write records, and run programs on your data.
Give your agent a persistent workspace: files, a code sandbox and a public URL to publish to.
Real Linux labs your AI agent deploys, routes and runs, with domains, TLS, DBs and an audit log.
Plan, implement, and validate software changes using a virtual computer equipped with a full coding agent, development tools, browsers, and file access. Coding Agent by OpenHelm enables your agent to carry out work such as: • Implementing new features • Fixing bugs • Refactoring codebases • Updating documentation • Creating and validating pull requests
Host the tools your AI builds — small internal tools in isolated microVMs, live for your team.
On-demand GPU nodes for agents: create nodes, run commands, and submit jobs, billed by the minute.
Deploy serverless TypeScript on Val Town: HTTP vals, cron, SQLite, email, OAuth.
An MCP server for Arcjet - the runtime security platform that ships with your AI code.
Hot Module Reload (HMR) for Python with reactive programming and MCP tools