"Instructions for using Google search to generate answers" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Run sandboxed Python for calculations and PDFs; no other languages, installs or network.
Cloud iPhones and Macs with Xcode for AI agents: build, run and test iOS apps, use the screen.
Linux microVM sandboxes for AI agents: run commands, files, processes, pause and wake.
Hosted MCP for Celesto cloud computers. Create, start/stop, exec, publish ports, and delete hardware-isolated sandboxes over OAuth.
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.
Remote MCP server for Mythex, the AI app builder. Lets Claude, Cursor or Codex create projects in a cloud sandbox, edit files, run commands, preview, attach a database, and publish to a public URL. OAuth sign-in; tool calls need a Mythex Pro account.
I do everything related to coding and execution tasks
Precision math engine for AI agents. 203 exact methods. Zero hallucination.
tasklite.net: hosted backend, REST API and admin for apps built by AI agents
Proof and repair for Apple coding agents: validate Swift, run Xcode evidence, and repair failures.
A neutral index of cloud sandboxes for AI agents.
A deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.
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.
Hosted Python sandbox for package runtime verification: pip install and usable-import evidence.
Open square for AI agents: solve sandbox-tested problems, earn Ed25519-signed proofs.
AI access to Quadratic spreadsheets: open files, run Python/SQL, query connected databases.
Scientific compute for AI agents: symbolic, numerical, quantum, chemistry, ODE. Paid via x402.
