Outcome · Sales

Sales agents for LinkedIn

Find the accounts and people worth approaching, research them properly, and open the conversation without burning the account.

Products
3
From
Free
Capabilities
20 of 22 live
Risk
Medium

How these act

  • Your LinkedIn sessionActs as you, from your connected account, under pacing limits.
  • Human approvesDrafts the action; nothing irreversible happens until a person presses send.

You bring

  • A LinkedIn account the agent may act as — not, ideally, your own.
  • A written ICP. Agents are only as specific as the brief they are given.
  • Sales Navigator, for anything beyond basic people search.

What it takes

The capabilities this job runs on

A capability is one thing an agent can do, and each one names what performs it: a live MCP tool, a skill, or a workflow. 20 of 22 can be performed today.

A day of prospecting, ending at a stop

Medium risk

Budget check, one search, dedupe against the sender's existing connections, research the shortlist, draft an opener each, write them to a file, and stop. The workflow has no send step and the endpoint exposes no tool that could add one.

Performed by a workflow — a sequence of steps, not a single call. · Human approves

Check the remaining LinkedIn budget

Low risk

How many LinkedIn tool calls this workspace has made this month, broken down by tool, plus the rate limit in force. The call an agent makes to pace itself instead of discovering the limit by hitting it.

Runs on get_usage · Read only

Draft a first message

Low risk

Writes an opener grounded in a cited line from the person's profile or a post, in the project's voice, under LinkedIn's 300-character invitation-note limit. It produces text in a file. Nothing in the kit can send it.

Performed by a skill — instructions your AI client follows. · Human approves

Draft a follow-up

Low risk

Writes the next message in a thread from what the person actually replied, including the version that says nothing further is coming. It drafts; a person decides whether it goes.

Performed by a skill — instructions your AI client follows. · Human approves

Find a warm path in

Low risk

Intersects the sending account's first-degree connections with a target's company to tell you whether there is an introduction to ask for. It answers from the sender's network only; it cannot see anybody else's connections.

Performed by a skill — instructions your AI client follows. · Read only

Find people matching an ICP

Medium risk

Runs an ICP description through a connected account's LinkedIn search and returns up to 50 profiles per call. Profiles LinkedIn masks as "LinkedIn Member" because they are out of network are dropped rather than returned with a blank name. Typed Sales Navigator filters are used only when the account has a Navigator seat; otherwise every criterion is folded into one keyword string.

Runs on search_linkedin_people · Your LinkedIn session

List the sending account's network

Medium risk

First-degree connections of the connected sender account, up to two hundred per call. It is that account's network, not the network of whoever is signed into the app — which is exactly the distinction that matters when the sender is a dedicated account.

Runs on list_linkedin_connections · Your LinkedIn session

One person, fully researched

Medium risk

Resolve the profile, read it, read up to ten of their posts, check for a warm path, and produce a dossier with the calls that produced each claim listed underneath it. Four LinkedIn calls per person, and the workflow says so before it starts.

Performed by a workflow — a sequence of steps, not a single call. · Your LinkedIn session

Prove the connection works

Medium risk

Check the tool list, name the account being acted as, read the remaining budget, run one small search, read three profiles, hand back one brief, stop. The shortest sequence that produces something real.

Performed by a workflow — a sequence of steps, not a single call. · Your LinkedIn session

Read campaign performance

Low risk

Every campaign in the workspace with its live funnel counters — invited, connected, replied — and the two rates already rounded to whole percentages.

Runs on list_campaigns · Read only

Read lead lists

Low risk

The lead lists and the leads in them, with whatever enrichment was stored at import. The whole set comes back in one payload: there is no paging or filter argument yet, so a large workspace returns a large response.

Runs on list_leads · Read only

Read one profile in depth

Medium risk

One call returns identity, current role and the date it started, follower count, the premium flag and the latest post. Every enrichment field is best-effort: a profile that hides its activity still returns its identity, with the post fields simply absent.

Runs on get_linkedin_profile · Your LinkedIn session

Read the approval queue

Low risk

The AI-written replies waiting for a person to press send. An agent can read and summarise this queue; it cannot approve anything in it, and that is deliberate — sending is the one irreversible action in the product.

Runs on list_tasks · Read only

Read the unified inbox

Low risk

One thread per lead across every sender account, with full message bodies and — once a reply has been classified — its intent. There is no since or limit argument; the whole inbox comes back.

Runs on get_inbox · Read only

Read the workspace roll-up

Low risk

Senders, campaigns, leads, invited, connected and replied, counted across the whole workspace. The cheapest way to answer "how is outreach going" without walking every campaign.

Runs on get_stats · Read only

Read what someone has posted

Medium risk

Up to twenty recent posts by one member, newest first, with reposts flagged. An empty array — not an error — is the normal answer for a senior buyer who does not post, and a workflow has to handle that as a case rather than as a failure.

Runs on get_linkedin_posts · Your LinkedIn session

See which LinkedIn identity is available

Low risk

The accounts this workspace can act as, each with status, warm-up stage, how much of today's invite and message budget is spent, and a health score. Reads our own database, so it costs nothing against the LinkedIn rate limit and is the cheapest first call an agent can make.

Runs on list_sender_accounts · Read only

Sort replies by intent

Low risk

Classifies an inbox into the same seven intents the app itself uses — meeting, interested, question, objection, not_now, not_interested, neutral — so the queue is read in the order that matters instead of newest-first.

Performed by a skill — instructions your AI client follows. · Read only

Turn an offer into search filters

Low risk

Converts a written offer and a few existing customers into the arguments search_linkedin_people actually takes — keywords, location, industry, company, exclude_company — and says which of them LinkedIn will treat as a typed filter versus fold into keywords.

Performed by a skill — instructions your AI client follows. · Read only

Write a brief on one person

Low risk

Compresses a profile and its posts into a one-screen brief in which every claim names the call that produced it. Anything the tools did not return is written as "not visible" rather than inferred, because an invented detail in a first message is worse than a missing one.

Performed by a skill — instructions your AI client follows. · Read only

Not built yet

These are declared in the registry so a product page can say “not yet” instead of implying it. Nothing performs them today:

  • Read who engaged with a postNot built yet. Reaction and comment counts come back on a post, but the people behind them do not, so "everyone who commented on this" cannot be turned into a list.
  • Write a researched lead into a CRMNot built yet. Research comes out as files you own. There is no CRM write path, so the last step is still a copy-paste or an import.

The products

3 products do this job

Each card is a real catalogue row: its price, its risk level and how it acts are the fields the product itself declares, not marketing written per page.

LinkedIn Starter Agent

AgentVerified

Connect the endpoint and get one real answer in five minutes. Free.

FreeMedium riskYour LinkedIn session

Uses Read one profile in depth, Find people matching an ICP, Write a brief on one person, Prove the connection works, Read campaign performance, See which LinkedIn identity is available, Read the workspace roll-up, Check the remaining LinkedIn budget

LinkedIn SDR Kit

Pro kitVerified

From an ICP to approved first messages, with a stop where the send button would be.

$49Medium riskHuman approves

Uses List the sending account's network, Read what someone has posted, Read one profile in depth, Find people matching an ICP, Write a researched lead into a CRM, Draft a follow-up, Turn an offer into search filters, Draft a first message, Write a brief on one person, Sort replies by intent, Find a warm path in, One person, fully researched, A day of prospecting, ending at a stop, Read the approval queue, Read the unified inbox, Read lead lists, See which LinkedIn identity is available, Check the remaining LinkedIn budget — 1 of these is planned, not live.

Prospect Research Kit

Pro kitVerified

One screen on one person, with every claim traced to the call that returned it.

$49Medium riskYour LinkedIn session

Uses List the sending account's network, Read what someone has posted, Read one profile in depth, Find people matching an ICP, Write a researched lead into a CRM, Read who engaged with a post, Turn an offer into search filters, Write a brief on one person, Find a warm path in, One person, fully researched, See which LinkedIn identity is available, Check the remaining LinkedIn budget — 2 of these are planned, not live.

What it costs

Only the tiers this outcome actually uses

FreeFree1 product
The starter agent and the hosted MCP endpoint. No card, no seat.
Pro kit$492 products
A skill plus MCP wiring, workflows and the files they read.

There is no payment processor connected yet. Checkout records a real order against your workspace and tells you exactly what happens next — nothing is charged, and no card is asked for. The whole ladder is on pricing.

What it risks

The part most sites leave out

Volume is the part of this job that gets accounts restricted, and it is the part software makes easy. Everything sold here keeps sending behind a human approval step by default; that is a deliberate ceiling on how fast this can go wrong.

Medium risk
Acts through your own session or writes with a human approving each action. Restriction is unlikely but not impossible.

LinkedIn does not endorse, certify or sanction any of this, and nobody — including us — can promise an account will not be restricted. What we can do is keep the irreversible actions behind a person, cap the pace, and tell you which side of that line a product sits on before you buy it. The mechanics are on security.