cogny clipaid socialfirst 15 calls free
linkedin ads from your shell.
Pull LinkedIn campaign analytics, break performance down by job seniority or company size, list campaigns and creatives, and flip status or budget — all from Bash over the LinkedIn Ads MCP. No Campaign Manager exports, no Marketing API client.
- 1. sign up, free for the first calls (uses your git email)
npx @cogny/cli init --agent claude-code - 2. see every LinkedIn Ads tool
cogny tools list - 3. call any tool from bash, no MCP wiring
cogny tools call mcp__LinkedIn_Ads__tool_get_analytics --input '{…}'
Today you click through Campaign Manager, build a demographics report, and export each pivot to CSV by hand. The CLI returns the exact pivot — including MEMBER_SENIORITY or MEMBER_COMPANY_SIZE breakdowns — as JSON in one call. Connect LinkedIn Ads once in Cogny Solo and let your coding agent, or a scheduled loop, do the querying for you.
Start SoloSign yourself up with one command. The CLI issues a key, wires nothing, and exposes every LinkedIn Ads tool over JSON-RPC. The first 15 calls are free.
npx @cogny/cli init --agent claude-code
real LinkedIn Ads tools.
Tool names as the LinkedIn Ads MCP serves them. Send --input JSON, get JSON back. The payloads are illustrative.
- mcp__LinkedIn_Ads__tool_get_analytics
Performance metrics for campaigns, pivoted by any LinkedIn dimension.
cogny tools call mcp__LinkedIn_Ads__tool_get_analytics \ --input '{"ad_account_id":"510123456","start_date":"2026-05-01","end_date":"2026-05-31","pivot":"MEMBER_SENIORITY","fields":["impressions","clicks","costInLocalCurrency"]}'
example response
[ { "pivot_value_names": [ "Senior" ], "impressions": 184320, "clicks": 1102, "costInLocalCurrency": "3421.80" }, { "pivot_value_names": [ "Director" ], "impressions": 92110, "clicks": 744, "costInLocalCurrency": "2890.55" } ] - mcp__LinkedIn_Ads__tool_get_campaigns
List campaigns with status, objective, and budget.
cogny tools call mcp__LinkedIn_Ads__tool_get_campaigns \ --input '{"ad_account_id":"510123456","status_filter":["ACTIVE"],"limit":2}'
example response
{ "elements": [ { "id": "198765432", "name": "ABM — Tier 1 Accounts", "status": "ACTIVE", "objective": "WEBSITE_VISITS" }, { "id": "198765433", "name": "Thought Leadership — Sponsored", "status": "ACTIVE", "objective": "ENGAGEMENT" } ], "next_page_token": null } - mcp__LinkedIn_Ads__tool_update_campaign_status
Pause, activate, or archive a campaign.
cogny tools call mcp__LinkedIn_Ads__tool_update_campaign_status \ --input '{"ad_account_id":"510123456","campaign_id":"198765432","status":"PAUSED"}'
example response
{ "campaign_id": "198765432", "status": "PAUSED", "success": true }
the rest of the surface.
A sample of the other LinkedIn Ads tools. Run cogny tools list --json for every tool and its input schema.
- mcp__LinkedIn_Ads__tool_list_ad_accounts
- mcp__LinkedIn_Ads__tool_get_campaign_groups
- mcp__LinkedIn_Ads__tool_get_creatives
- mcp__LinkedIn_Ads__tool_get_audience_counts
- mcp__LinkedIn_Ads__tool_search_targeting_entities
- mcp__LinkedIn_Ads__tool_update_campaign_budget
- mcp__LinkedIn_Ads__tool_update_campaign_targeting
- mcp__LinkedIn_Ads__tool_create_campaign
- mcp__LinkedIn_Ads__tool_get_conversions
calls from a script. verdicts from cogny.
Every write is logged with who authorised it. Launches your agent makes (a new campaign, a new ad) become measured tickets automatically; for other changes, your agent offers to register them. Cogny measures each in your own data, three days later for ads and seven for content and SEO, and closes it as worked, partial, didn't work or inconclusive.
- worked
Moved the number. Every measured win has a share card.
- partial
Some of it did.
- didn't work
On the record anyway, so it isn't proposed again.
- inconclusive
Not enough data to call.
questions.
- Is this an official LinkedIn Ads CLI?
- No — it is the Cogny CLI calling the LinkedIn Ads MCP over the cogny-mcp-proxy. You authenticate once via Cogny (OAuth handled for you) and then call every tool from Bash. No Marketing Developer Platform app or access token to manage.
- Can I get demographic breakdowns from the command line?
- Yes. tool_get_analytics accepts a pivot like MEMBER_SENIORITY, MEMBER_JOB_FUNCTION, MEMBER_INDUSTRY, or MEMBER_COMPANY_SIZE, and resolves the URNs to human-readable names in the response.
- Can my coding agent use this without MCP setup?
- Yes — that is the point. `npx @cogny/cli init --agent claude-code` issues a key, then `cogny tools call mcp__LinkedIn_Ads__tool_get_analytics --input ...` works from any shell. No /mcp wiring or restart needed.
Building an agent? The full tool map for every server is one fetch: /cli/llms.txt