MCP connector
Connect your AI.
Choose your AI, add Ahel, and sign in.
Your apps, skills, and knowledge stay with your Ahel account.
Connect
Choose your AI
Connect Ahel to Claude
Add Ahel once, then sign in to authorize access.
First-time setup
- Add a custom connector and name it Ahel.
- Use this server address:
https://mcp.ahel.ai - Choose OAuth, connect, and approve the Ahel sign-in.
Claude currently requires this initial setup. Opening it here does not create a connection.
Using Claude Code?
Run this once to add Ahel:
claude mcp add --transport http ahel 'https://mcp.ahel.ai'In Claude Code, open /mcp, select Ahel, and approve the browser sign-in.
Secure browser sign-in. No API keys to paste.
Part of a team on ahel? This address connects your AI to the workspace you were invited to. In more than one? Your AI in the app has a link for each.
Technical details and questions
The protocol
How does MCP work?
The Model Context Protocol gives agents one standard way to call tools. A connector is an address that answers those calls. Most connectors serve one product; this one serves your account, so the same link means something different for every person who signs in: their gateway, their servers, their credentials.
The tools
What the link serves today
These are the 14 tools to use, and a client will also list 5 older names for the same jobs, still served so existing connectors keep working. That is the whole list, and it never changes: the hosted MCP servers on your gateway and the sandboxed local servers are served through this same link, reached through tools and use rather than added to the list. Enabled skills are served too, as MCP prompts and through skill_read.
| Tool | What it does |
|---|---|
| explore | Ask for what you want your AI to do. Answers with ONE offer, the app, skill or knowledge that can do it now, and quiet alternatives. |
| install | Install one capability by id. It is added and made available to your AI clients in a single call; there is no separate enable step. |
| installed | What your account has installed, and whether each one is on, off, needs setup, or is unavailable. |
| switch | Turn an installed capability on or off. Off keeps it installed but removes its tools and prompts from your AI clients. |
| status | Per capability: its state and the names of any credentials still missing. Status only: values never leave. |
| tools | The tools one installed server offers, with their schemas. This is how a server's tools are read without the gateway's own list ever changing. |
| use | Run one tool of an installed server, credential attached server-side. The result comes back unchanged. |
| list_actions | What your AI can do on connected apps with your own key: ranked actions for an ask, or one service's full list. |
| run_action | Run one action on your own account of that app. ahel injects the stored key; no key ever appears in chat. |
| raw_request | One HTTP request to a connected app's own API host, for endpoints no listed action covers. Pinned to that host. |
| run_script | A short Node script in a locked sandbox pod that holds no key; it acts through the same server-side injection. |
| skill_read | The full instructions of any installed skill that is on. The same content also arrives as an MCP prompt, which Claude Code surfaces as a slash command. |
| search | The ChatGPT connector contract: search the catalog, get id, title and url per result. |
| fetch | The ChatGPT connector contract: read one catalog record in full by id. |
The boundary
What it deliberately does not do
Your agent can
- Search the whole catalog from inside a conversation.
- Add servers to your gateway and switch them on or off; that only ever changes your own link.
- Call the tools of every server you serve, credentials attached server-side.
It never can
- Read, write, or reveal a stored credential. No tool on this link touches a key, and a credential never crosses back to the client.
- Reach another account. The link answers only as the person who signed in.
- Seal a new credential. That stays in the app, at ahel.ai.
Questions
Everything else.
What is MCP?
The Model Context Protocol is the open standard AI agents use to reach tools and data. An MCP connector is an address an agent reads capabilities from. ahel's connector serves your whole account at one address.
How does the ahel MCP connector work?
It is a remote MCP server over streamable HTTP. After the client is configured, OAuth signs you in and each authorized call reaches your gateway. Setup steps depend on the client.
Which agents does this work with?
The supported setup paths cover Claude, Claude Code, ChatGPT, Codex, Cursor, and VS Code with Copilot. They authenticate through browser OAuth.
Does it work with ChatGPT?
Yes. A ChatGPT connector needs a search and a fetch tool; the link serves both, so ahel can be added under Settings, Connectors, with the same address. Custom apps must be enabled by your plan and workspace.
Why does the tool list never change?
Install a hundred servers and your client still sees the same tools: installed servers are reached through tools and use, never added to the list. A tool list that grows with every install breaks prompt caching, bloats every request, and makes clients that read the list once at connect time show stale tools. The 2026-07-28 MCP revision recommends a deterministic tool list for exactly this reason.
What can my agent actually reach?
Only what your account can already reach: your gateway, the catalog, and the tools of the hosted MCP servers you have enabled. Credential values never cross the link. Nothing more, and nothing from anyone else's account.
Can it spend money?
The link's own tools cannot: they only read the catalog and edit your gateway. But a call proxied to a server you enabled does whatever that server does, with your credential attached, so a paid vendor call spends money the moment your agent makes it.
Add the missing link.
One link, and every agent you use reads the same tools.