How to connect
Add an MCP Client module to a scenario, or an MCP tool from an AI Agent’s configuration, create a connection and set the server URL to https://nilyo.com/mcp with OAuth authentication. A browser window opens to authorize — the same Nilyo sign-in used by ChatGPT and Claude, with no Make-specific account to create.
What becomes available
LinkedIn search, profiles, invitations and messages; WhatsApp, Instagram and Telegram conversations; Gmail, Outlook and IMAP mailboxes with folders, threads, drafts and attachments; calendars and events. Each module names the account it runs on, so one scenario can read one mailbox and write from another.
Iterators are where duplicates come from
Make makes looping easy, which is exactly the risk on accounts that belong to a person. An iterator over fifty prospects with a send module at the end will send fifty messages as fast as the API allows — except it will not, because pacing is enforced per account and the run stops on an explicit limit error. Design for that: a filter, a sleep, or a batch smaller than the daily budget.
Resolve before you write
Chain a resolution module before any send: a profile URL or a name becomes a stable identifier, and when several people match the module returns the candidates rather than choosing. Feeding a display name straight into a send module is how a scenario messages the wrong person at scale.
A concrete scenario
An hour before each meeting, the scenario lists the calendar events in the window, extracts the external guests, looks each one up on LinkedIn, pulls the last emails exchanged and sends you the briefing on WhatsApp. Four accounts, one connection, no per-app authorization.
“An hour before each meeting, brief me on the guests using LinkedIn and my mailbox.”
“When an invoice goes overdue, message the client in the existing WhatsApp conversation.”
Common questions
Does Nilyo have a native Make app?
It connects through Make’s MCP Client module, the supported route for MCP servers, so one connection covers every account instead of one app per provider.
Can an AI Agent in Make use it?
Yes. Add it as an MCP tool from the agent configuration and the agent chooses the operation and the arguments itself.
How do I avoid sending twice?
Turn off automatic retries on write modules and read the state back instead. An ambiguous send is not retried by the tools either — the conversation is re-read.
What are the limits?
LinkedIn carries a daily budget per account including reads; WhatsApp caps brand new conversations per day. Both return an explicit error rather than failing silently.
How LinkedIn works with Nilyo
Connection. Secure hosted sign-in (your LinkedIn credentials go to LinkedIn, never to the agent). Sales Navigator and Recruiter are detected automatically when your account has them.
What your agent can do. People and company search, profile lookup from a name or URL, your network and invitations, private conversations (classic, Sales Navigator, Recruiter inboxes), posts, comments and reactions, job postings and applicants, Recruiter projects.
Pacing and safety. About 100 actions per day per account, profile views and searches included; calls are serialized so an agent can never run LinkedIn requests in parallel.
- Profile URLs are resolved to stable profile IDs before any action.
- Invitations carry an optional note of up to 300 characters.
- Private or restricted profiles return an explicit “not accessible” result instead of a retry loop.
All LinkedIn guides
Related guides
Give Nilyo to your agent.
Paste one setup link. Your agent can guide OAuth, account connection and the first useful action.