What it is
A restricted LinkedIn account cannot be fixed by changing a setting afterwards, and the signals that come before one are already in what these tools return: checkpoint status, warm-up stage, how much of each daily cap is spent, the shape of the last week's failures. This is the standing review that reads them in a fixed order and ends in a written decision per account — keep going, slow down, or stop.
Who it is for
- Whoever is accountable for the accounts and the spend: an agency running seats for clients, an ops lead behind a sales team, or a founder who is the only person who would notice.
Capabilities
Each of these is one atomic thing the product can do, and each names what performs it. A capability fulfilled by a tool maps onto a tool the MCP endpoint serves today — follow the link and you can read the exact request it makes and what comes back.
Read the credit balance and its ledger
MCP toolLow riskThe workspace balance and the entries behind it, with whether the balance can refuse anything at all reported alongside the number — because enforcement is off by default and a meter read as a spending limit is worse than no meter.
Read only · check_credits
Read what this workspace has run
MCP toolLow riskInstalls, purchases, the hosted seat, credits and the execution ledger over a window: what ran, what succeeded, what failed and the class of failure. The same rows the Executions page shows a person.
Read only · get_platform_usage
Read what this workspace owns
MCP toolLow riskWhat has been installed, where, at which version, and what was paid for it — including removed installs when asked for the full history. The library, read back as rows rather than as a page.
Read only · list_installations
Read the approval queue
MCP toolLow riskThe 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.
Read only · list_tasks
Read campaign performance
MCP toolLow riskEvery campaign in the workspace with its live funnel counters — invited, connected, replied — and the two rates already rounded to whole percentages.
Read only · list_campaigns
Read the unified inbox
MCP toolLow riskOne 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.
Read only · get_inbox
Stop a campaign from sending
MCP toolLow riskThe only tool that writes anything, and it writes to our database rather than to LinkedIn: it stops outbound. There is no resume tool, because restarting a campaign is a deliberate human action in the app.
Read only · pause_campaign
See which LinkedIn identity is available
MCP toolLow riskThe 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.
Read only · list_sender_accounts
Read the workspace roll-up
MCP toolLow riskSenders, campaigns, leads, invited, connected and replied, counted across the whole workspace. The cheapest way to answer "how is outreach going" without walking every campaign.
Read only · get_stats
Check the remaining LinkedIn budget
MCP toolLow riskHow 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.
Read only · get_usage
Plan work against the limits before spending them
AI skillLow riskTurns a piece of work into an arithmetic question against three separate budgets — thirty LinkedIn calls per five minutes per workspace, the monthly allowance the usage report names, and each sender's daily caps — and says what fits, what has to be paced, and what does not fit at all. The point is to discover a limit on paper rather than by hitting it mid-run.
Read only
Judge whether an account is safe to keep running
AI skillLow riskReads sender status, warm-up stage, daily invite and message counters and the health score, and turns them into a decision with a reason: keep going, slow down, or stop. Written down because the failure it prevents — a restricted LinkedIn account — is not reversible by changing a setting afterwards, and because the signals that precede it are visible in what these tools already return.
Read only
The standing review that keeps the machine inside the rails
WorkflowLow riskA fixed pass over the things that go wrong quietly: sender health and checkpoints, how much of each daily cap is spent, the monthly LinkedIn allowance against the calendar, the approval queue's age, the execution ledger's failures by class, and the credit balance. It ends in a written decision per account and, where the answer is stop, the one tool call that stops it.
Human approves
Run a product on a schedule, server-side
Planned — not available yetLow riskNot built yet. install_product records an installation and runs nothing: every workflow in this catalogue runs inside your AI client, when you run it. Nothing here wakes up on a Monday morning and does the week's research on its own, and no product page should be read as saying otherwise.
Read only
One capability is marked planned: nothing fulfils it today. It is listed because the roadmap should be visible, and it does not run when you install this.
A worked example
Lifted from the kit’s own EXAMPLES.md — list_sender_accounts — the first read, every time. Real request and response shapes. Field names are exact; values are illustrative.
{}{
"accounts": [
{
"id": "snd_02",
"name": "Marcus Feld",
"status": "active",
"connected": true,
"warmupStage": 4,
"dailyInviteLimit": 24,
"dailyInviteSent": 11,
"dailyMsgLimit": 40,
"dailyMsgSent": 6,
"health": { "score": 92, "level": "good" }
}
],
"default": "snd_02"
}What is included
- The safety rubric: which signals precede a restriction, and what each one is worth
- A budget arithmetic sheet for three separate limits that are easy to confuse
- The standing review, in a fixed order, ending in a decision you can paste into a log
- A shell runbook for the same checks over the REST API and the CLI, for people who would rather cron it
The files
| File | What it holds |
|---|---|
| README.md | What it is, what it needs, what it cannot do, and what is in the directory. |
| INSTALL.md | The exact commands for Claude Code, Claude Desktop, Cursor and VS Code, plus a call that proves the connection before you trust it. |
| AGENT.md | The agent definition to paste into your client's project instructions: role, tool budget, rules, and where it stops. |
| SKILL.md | The judgement written down — the rubric, what counts as evidence, and what to write when the evidence is not there. |
| WORKFLOW.md | The run step by step, with the exact tool calls, the cost of each, and the human gate it ends at. |
| PROMPTS.md | Prompts to paste, each one naming the tools it will spend. |
| EXAMPLES.md | Real request and response shapes from the endpoint, with illustrative values and the field names that are not. |
| TROUBLESHOOTING.md | The errors this endpoint actually returns, quoted verbatim, and what each one means. |
| .env.example | The values the install asks for, in one place. Nothing in the kit reads it by itself. |
What it cannot do
Printed before you pay, not after you ask for a refund.
- It reads and decides; it does not enforce. The only thing it can stop is a campaign, through the one tool that writes. Daily caps, warm-up and working hours are changed by a person in the app.
- Nothing here runs on a schedule. There is no hosted runner: the review happens when you run it, which is the honest reason the runbook includes a cron line you own.
- It cannot see LinkedIn's own view of an account. Checkpoint status is what the provider reports back to us; a restriction that LinkedIn has decided on and not yet surfaced is invisible to every tool here.
- The credit meter it reads does not refuse anything today. Enforcement is off by a deliberate flag, and the kit reports the balance as a meter rather than a limit.
What a run costs: Zero LinkedIn calls. Every read in this kit is against the workspace and the platform, which are not rate limited — the budget it protects is one it never spends. The endpoint allows a fixed number of LinkedIn calls per five minutes per workspace, which is documented per tool.
Install
No install commands published for this product. The endpoint its tools run on is documented on the Claude setup page, and the tools themselves on the tool reference.
Compatibility
| Target | Supported |
|---|---|
| Claude | Yes |
| Cursor | Yes |
| VS Code | Yes |
| Run here | No — hosted seats are a separate tier |
| Download | Yes |
What you need before it runs
- A TopClozer workspace API key
- An MCP-capable client, or a shell — this kit ships both paths
LinkedIn plan: Irrelevant. Nothing in this kit reaches LinkedIn; it reads what this server already knows about your accounts.
Security and risk
Low risk. Reads only, at human pace. No writes to LinkedIn.
Human approves. Drafts the action; nothing irreversible happens until a person presses send.
The live MCP endpoint is read-only by design, and the outreach engine keeps every irreversible action behind a human approval gate. None of that is LinkedIn endorsing any of this, and nobody can promise your account will not be restricted — least of all a vendor selling you automation. What we store and who can read it is a separate page, and it is the one that answers that question.
Provider: TopClozer — a verified seller: we wrote it, we maintain it, and the support request comes to us.
Pricing
$49 — A skill plus MCP wiring, workflows and the files they read. The whole ladder is on the pricing page.
No payment processor is connected to this site, so nothing here can charge a card — and a button that looked like it could would be the lie this catalogue exists to avoid. What happens instead: the order button writes a real pending purchase against your workspace and hands you its reference, a person invoices you, and marking that order paid is what puts the files in your library. Slower than a card, and every step of it is real.
Version history
v1.0.02026-09-20
First release. Safety rubric, three-budget arithmetic, the standing review and a shell runbook over the REST API and CLI.
Reviews
Nothing here. A review appears on this page only when it is attached to a verified purchase of this product, and none has been published. An empty section is the correct state for a catalogue this young — the alternative is the kind of testimonial that means nothing to the person reading it.
Related products
LinkedIn SDR Kit
From an ICP to approved first messages, with a stop where the send button would be.
Capabilities
$49
LinkedIn Starter Agent
Connect the endpoint and get one real answer in five minutes. Free.
Capabilities
Free
Warm Intro Kit
Your sending account already knows someone there. This finds out who, and writes the ask to them.
Capabilities
$49