Meta ads library, competitor ads, brand voice, avatars and offer briefs from your Pantheon account.
接入你的智能体
發布者自己的 URL。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
https://mcp.pantheon.ad/mcp上方的 Claude 按鈕會開啟 Claude,並填好名稱和 URL。你仍需在那裡確認。
claude mcp add --transport http ad.pantheon-mcp https://mcp.pantheon.ad/mcpRun in a terminal.
{ "mcpServers": { "ad.pantheon-mcp": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.pantheon.ad/mcp" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
尚未爬取 README。 未登記儲存庫。
Meta ads library, competitor ads, brand voice, avatars and offer briefs from your Pantheon account.
{ "mcpServers": { "ad.pantheon-mcp": { "url": "https://mcp.pantheon.ad/mcp", "headers": {} } }}23 個工具
常見問題
| List the user's Offer Briefs (id, name). |
| list_analyzed_pages | List Facebook pages the user analyzed (competitor, inspiration or brand_campaigns), with status and ad counts. |
| search_ads_library | Search the user's own Ads Library (ads collected by their searches) and this week's Top Ads by brand, niche, sector or copy. Returns ad ids usable with analyze_ad and run_ad_copilot. |
| get_market_creators_data | Aggregated stats of the creators/competitors the user monitors. |
| get_top_performing_ads | Top performing (longest running) ads of the monitored creators. |
| get_active_ads_copy | Copy (body, caption, CTA) of currently active ads of the monitored creators. |
| get_saved_ads | The user's swipe file, optionally filtered by competitor name. |
| get_strategic_avatar | Avatar research of a project (from list_projects): pain matrix, core wound, desire chain, objections, triggers, language and strategic synthesis. |
| get_competitor_active_ads | Active ads of a competitor the user has analyzed with Competitor Spy. |
| get_creative_analysis | Saved AI analysis of an ad (awareness, hooks, mechanism, triggers, landing page coherence), if analyze_ad was run on it. |
| get_job_status | Status and results of a background job started by an action tool. |
| run_competitor_spy | Scrape and analyze all ads of a competitor's Facebook page (uses 1 Competitor Spy credit). Runs in background: poll get_job_status with the returned id. |
| run_inspiration_search | Scrape and analyze a page outside the user's niche for inspiration (uses 1 Inspiration Search credit). Runs in background: poll get_job_status with the returned id. |
| run_brand_campaign_analysis | Scrape and analyze the user's own brand Meta campaigns page (uses 1 Brand Campaigns credit). Runs in background: poll get_job_status with the returned id. |
| run_ad_copilot | Adapt a library ad into 3 copy variants for the user's Avatar, Offer Brief and Brand Voice (uses 1 Ad Copilot credit). Runs in background: poll get_job_status with the returned id. |
| analyze_ad | Ads Intelligence: full AI analysis of one ad (emotional levers, biases, landing page coherence). Uses 1 Ads Intelligence credit. Runs in background: poll get_job_status with the returned id. |
| run_persuasion_analysis | Persuasion analysis of an ad before launch: present and missing cognitive biases (uses 1 Persuasion Analysis credit). Runs in background: poll get_job_status with the returned id. |
| run_sales_psychology | Sales Psychology report for a project's Avatar + an Offer Brief (uses 1 Sales Psychology credit). Runs in background: poll get_job_status with the returned id. |
| create_brand_voice | Create and save a Brand Voice from a public URL or a text (uses 1 Brand Voice credit, ~1 minute). |
| create_offer_brief | Create and save an Offer Brief from a public sales page URL or a text (uses 1 Offer Brief credit, ~1 minute). |
| run_magic_tool | Summarize, translate or extract contacts/links from a text (Magic Tools). Summaries and extractions are in the language of the text; translations go to `language` (default Italiano). |
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 http 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Pantheon 透過 HTTP 存取。
上次檢查時間:2026-11-12。 Meta ads library, competitor ads, brand voice, avatars and offer briefs from your Pantheon account.