LinkedIn Ads MCP Server with Full Write Access

An MCP server turns an ad platform's API into typed tools an AI assistant can call. Connect one to Claude or ChatGPT and "pause every LinkedIn campaign with a cost per lead above $120" becomes a command the assistant can verify, propose, and, once you confirm, execute. This page covers PaidSync's LinkedIn surface in full: what the 25 tools do, how the approval gates work, what the server deliberately does not cover, and how it compares against the two other LinkedIn Ads MCP options active in August 2026.

The page is written for both audiences. Marketers who want to manage LinkedIn campaigns from a chat window, and agent builders who want to know exactly what the protocol surface looks like before wiring it into a workflow. Each section is labeled so you can skip to what matters.

What a LinkedIn Ads MCP server does

Three things in practice. It reads, so the assistant can pull impressions, clicks, leads, and cost per result without you exporting from Campaign Manager. It writes, so campaigns, campaign groups, ads, creatives, targeting, and conversions can be created or changed through conversation. And it gates, so nothing the AI proposes runs until a human confirms it. The reading part is available on several LinkedIn MCP options. The depth of the write surface and the honesty of the gating are where they differ.

All 25 LinkedIn tools by category

PaidSync's live server exposes 25 LinkedIn tools (server total 430+ across 13 platforms). Twenty-two are named in the table below; the live count, updated weekly, is fully discoverable from any session via paidsync_context with include_tools:['linkedin_ads'].

Three of these carry the most operational weight. create_linkedin_campaign builds a full campaign against an existing campaign group, with objective, bidding type, daily or lifetime budget, targeting facets, and status set in one call. update_linkedin_campaign_targeting patches the targeting spec on a live campaign, job functions, seniorities, industries, company sizes, and member skills, without rebuilding the campaign. And get_linkedin_performance_by_dimension breaks performance by campaign, creative, geography, job function, company size, member age range, or any combination, so cross-cuts that take clicks in Campaign Manager take one prompt here.

Run LinkedIn Ads from a chat window

A practical week looks like this. On Monday you ask what changed in the last 7 days across LinkedIn campaigns. The assistant pulls spend, leads, and cost per lead from get_linkedin_performance and gives you a plain-number answer. You spot an ad group targeting too broadly, ask for the targeting breakdown, review it, and ask the assistant to tighten seniority to Director and above. It proposes the update_linkedin_campaign_targeting call with the exact change shown; you confirm, it applies.

Because the same server carries Google Ads (140+ tools), Meta Ads (69 tools), GA4 (28 tools), and GTM (37 tools), the follow-up question "did the new LinkedIn creative produce GA4 conversions at a lower CPA" is answered in the same session, not in a separate tab. For teams running cross-channel demand generation, that session continuity is the practical difference between a LinkedIn connector and a paid-media server.

Write access brings an honest concern about safety on live ad accounts. The answer is procedural. Nothing applies without your confirmation step in chat. Most write tools accept a dry_run parameter that returns the planned payload without executing it. Sessions can be revoked at any time from the PaidSync connect panel. Read operations never require confirmation because they change nothing.

The protocol surface behind the 25 tools

PaidSync is one MCP endpoint covering 13 platforms; architecture detail is on the MCP server page. To keep client context small, tools/list returns a lean starter set. The full catalog is discovered at runtime through paidsync_context, which returns the active account, connected platforms, and the grouped tool catalog. Pass include_tools:['linkedin_ads'] to get the exact LinkedIn tool names, signatures, and approval-gate defaults. Then execute any tool through paidsync_exec via await paidsync.call('tool_name', {...args}). That two-call pattern means an agent can enumerate and invoke all 25 LinkedIn tools without a 430-tool schema payload in every conversation turn.

Safety is enforced server-side. Writes are approval-gated, most mutation tools accept dry_run for a no-op preview of the planned change, and sessions can be revoked without touching the OAuth client. For discovery and verification, the domain publishes OAuth authorization-server and protected-resource metadata (RFC 8414 and RFC 9728), an MCP server card, agent-auth.json, security.txt, and a Content-Signal directive, so an agent can establish what this server is and how to authenticate before its first task.

LinkedIn's Marketing API enforces rate limits per application per member, at tighter thresholds than Google or Meta for some account classes. High-volume reporting loops (pulling performance for hundreds of campaigns per minute) will hit those limits. Design polling loops with a back-off and prefer dimensional breakdowns over per-campaign loops where possible.

PaidSync vs Adkit vs Adzviser

Three LinkedIn Ads MCP options exist in August 2026. Adkit expanded to LinkedIn in July 2026. Adzviser has offered a LinkedIn reporting connector since earlier in the year. The comparison below uses each vendor's published pricing and the tool counts verifiable from their public pages as of August 2, 2026.

What this does not do

Stated plainly, because accurate scoping is more useful than overselling.

• Predictive Audiences beta is not exposed. LinkedIn's Predictive Audiences feature, currently in beta for some account classes, is not in the tool set. Standard saved audiences and targeting facets are fully supported.
• Document Ads and certain vertical-specific formats are not documented. If Document Ads are central to your LinkedIn strategy, verify support with the PaidSync team before committing.
• No campaign deletion. Campaigns are paused or archived, not deleted through the API. LinkedIn's own Marketing API design does not surface a bulk delete endpoint; the MCP matches that constraint.
• One object per task. Creating or updating 15 campaigns is 15 confirmed tasks or a structured loop in your agent. There is no single-call bulk mutator.
• No organic page posting or LinkedIn Pages management. PaidSync is paid media only.
• Rate limits apply. LinkedIn's Marketing API enforces per-application rate limits that are tighter than Google Ads or Meta Ads for some account classes and reporting dimensions. High-volume automation loops should build in back-off logic.

Pricing

Every plan includes all 13 platforms and there is no per-account or per-platform charge. The billing unit is tasks: each tool call, read or write, counts as one task. Full detail at paidsync.ai/pricing.

Frequently asked questions