OP tasks, your presets and the public workflow gallery, billed to your API key. Connect the official OP Inference MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.
Free to start · No credit card · No hosting needed
Pick your client. Copy, paste, done — or let gate handle sign-ins and policies for you.
claude mcp add --transport http op-inference https://api.opinference.com/v1/mcpRun in your terminal, then restart Claude Code. The client will open the vendor's sign-in the first time you use it.
OP Inference · https://api.opinference.com/v1/mcp
Real prompts you can type the moment it's connected — no setup, no docs to read.
“What can OP Inference do for me?”
“Show me the tools OP Inference exposes.”
Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how OP Inference holds up.
Operated by OP Inference (opinference.com) at its documented MCP endpoint — not a third-party mirror or community re-host.
You grant access from your own OP Inference account and can revoke it there at any time. gate never sees your password.
gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.
If OP Inference adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.
OP Inference's server requires OAuth, so it can't be scanned anonymously — connect it in gate and the same scan runs automatically before it goes live.
Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.
Choose OP Inference in the gate directory. Sign in to your OP Inference account to grant access.
OP Inference's tools are live in every AI client you've connected — with rules and logging built in.
Free to start · No credit card · No hosting needed
https://api.opinference.com/v1/mcpYes — OP Inference operates its own remote MCP server at api.opinference.com. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.
Add gate's gateway URL to your AI client once, then pick OP Inference in the directory. You sign in to OP Inference via OAuth to grant access. From then on, OP Inference's tools are available in every client you've connected to gate.
No. OP Inference runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.
It's the vendor's official endpoint, and gate scans its tools for prompt injection and hidden instructions before it goes live, re-checks it whenever it changes, and lets you allow, block, or require approval for every single tool.
Yes — you can get started with gate for free and connect OP Inference in minutes. No credit card required.
Every server below works through the same gateway URL — connect once, add tools anytime.
Set up OP Inference in: Claude · Claude Code · ChatGPT · Cursor · VS Code