How to connect
Add an MCP Client module to the 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 ChatGPT and Claude use, with no Make-specific account to create.
What the official LinkedIn modules cannot do
They publish a share. Reading a profile, searching people, listing connections, sending an invitation or answering a message are not in the marketing API, so no integration built on it can offer them. Acting as the connected account is what makes those jobs possible at all.
The iterator is where scenarios go wrong
An iterator over two hundred prospects with an invitation module at the end will attempt two hundred invitations. It will not succeed: the daily budget of roughly a hundred actions per account, reads included, returns an explicit limit error and the run stops. Design for it — batch under the budget, and put the write behind a filter.
Resolve, then write
Chain a resolution module before any invitation or message: a profile URL or a name becomes the stable identifier the write requires, and several matches return the candidates instead of a guess. A display name fed straight into a send module is how a scenario contacts the wrong person at scale.
A realistic scenario
A search module lists people matching a role, a router filters out anyone already connected or already in a conversation, an AI module ranks the rest, and only the top few reach an invitation module with a personalised note — one per run, not two hundred.
React to a new message instead of polling
Listing LinkedIn conversations on a schedule spends the daily budget on reads that find nothing, and that budget includes reads. A realtime destination delivers each new message to the scenario as it happens, with the identifiers needed to fetch the thread, leaving the budget for the searches and the writes that actually matter.
“Search people matching a role, filter out existing connections, then invite the top few.”
“When a message arrives, read the thread and draft a reply for approval.”
Common questions
Can a Make scenario send LinkedIn invitations?
Yes, on your own account, after resolving the person. The daily budget is enforced server-side, so a runaway iterator stops with an error rather than damaging the account.
Does it replace the official LinkedIn modules?
It complements them: keep those for publishing a company post, use Nilyo for the account’s own inbox, search and network.
Can an AI Agent in Make use it?
Yes, as an MCP tool from the agent configuration, so the agent picks the operation itself.
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.