ZuckerBot — Meta Ads MCP Server

io.github.Crumbedsausage由 GitHub 帳號 Crumbedsausage 發布v0.4.4更新於 Oct 24, 2026

60+ Meta Ads tools for AI agents: audits, campaign management, audiences and CAPI tracking.

已驗證Streamable HTTP可網頁執行資料與分析商業與電商

概覽

AI 產生的概覽

ZuckerBot 是一個 Meta 廣告 MCP 伺服器,讓 AI 助理透過 Meta Marketing API 稽核廣告帳戶、管理行銷活動與受眾,並追蹤轉換。

可以做什麼
稽核廣告帳戶,取得行銷活動、廣告組與廣告層級的成效及帳戶洞察,包含潛在客戶與成本指標,並進行創意分析與政策檢查。建立、預覽、發布、暫停與恢復行銷活動、廣告組和廣告,並可從已上傳素材複製或建立暫停狀態的廣告。建立自訂受眾與類似受眾,重新整理並查看狀態。設定伺服器端轉換追蹤(CAPI),送出測試事件與潛在客戶品質回饋,管理像素。研究競爭對手、評論與市場基準,並從網站或上傳文字擷取業務背景。
適用情境
適合想透過與 AI 助理對話來操作 Meta 廣告、而不使用 Ads Manager 後台的場合:稽核花費、查看成效、規劃並發布行銷活動,或設定轉換追蹤。免費方案為唯讀,適合在付費前做評估與報表。
執行需求
可使用託管的 Streamable HTTP 端點(OAuth 或 bearer API 金鑰),或透過 npx 執行本機 npm 套件(需要 Node.js)。必須提供 ZuckerBot API 金鑰,透過 ZUCKERBOT_API_KEY 環境變數或 bearer 權杖傳入。帳戶相關工具需要已連接的 Meta 廣告帳戶與 Facebook 粉絲專頁。創意生成工具預設關閉,需以 ZUCKERBOT_ENABLE_CREATIVE_TOOLS 啟用。
安裝前請注意
API 金鑰是可存取你 Meta 廣告帳戶的有效憑證,請勿放入共用設定。許多工具會寫入 Meta:可發布、暫停、恢復或複製行銷活動,建立與刪除受眾,送出轉換事件。發布行銷活動會花費真實廣告預算,付費方案除月費外還依廣告花費比例計費。業務背景工具會將網站內容或上傳文字傳送給第三方。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 ZuckerBot — Meta Ads MCP Server,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.Crumbedsausage%2Fzuckerbot/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "zuckerbot-meta-ads": {
      "type": "http",
      "url": "https://zuckerbot.ai/api/mcp"
    }
  }
}

README

ZuckerBot

The Meta Ads toolkit for AI agents.

Audit your ad account in one message. 50+ tools for account auditing, campaign management, creative analysis, audience building, and conversion tracking. One npx command. Works with Claude, ChatGPT, OpenClaw, Cursor, and any MCP-compatible agent.

[npm version] [License: MIT] [MCP Registry] [GitHub stars]

json
{  "mcpServers": {    "zuckerbot": {      "command": "npx",      "args": ["-y", "zuckerbot-mcp"],      "env": { "ZUCKERBOT_API_KEY": "zb_live_your_key_here" }    }  }}

Get API Key (free) · npm · Docs · Website


Why ZuckerBot?

Your agent already writes code, manages files, and searches the web. It should manage your ads too.

ZuckerBot gives any AI agent full Meta Ads capabilities through MCP. No dashboard, no UI to learn, no platform to log into. Your agent installs it, connects your ad account, and gets to work.

What agents can do with ZuckerBot:

  • Audit your ad account in one message — spend flagged for review, creative fatigue, opportunity score, prioritised action items (free tier included)
  • Pull campaign performance and spot what's working
  • Analyse ad creatives and recommend what to test next
  • Build and launch campaigns with targeting and budget
  • Create custom and lookalike audiences
  • Set up server-side conversion tracking (CAPI)
  • Research competitors, reviews, and market benchmarks
  • Generate ad creative briefs and copy

How it works

You ↔ Your Agent (Claude, ChatGPT, OpenClaw, Cursor, etc.)                  ↕            ZuckerBot MCP                  ↕         Meta Marketing API

ZuckerBot handles the Meta API complexity. Your agent handles the conversation. You make the decisions.

Install

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "zuckerbot": {      "command": "npx",      "args": ["-y", "zuckerbot-mcp"],      "env": { "ZUCKERBOT_API_KEY": "zb_live_your_key_here" }    }  }}

OpenClaw

Add to your MCP config:

json
{  "mcpServers": {    "zuckerbot": {      "command": "npx",      "args": ["-y", "zuckerbot-mcp"],      "env": { "ZUCKERBOT_API_KEY": "zb_live_your_key_here" }    }  }}

Cursor / Windsurf / Any MCP Client

Same config pattern. ZuckerBot works with any client that supports the Model Context Protocol.

Remote MCP (no install)

Don't want to run anything locally? https://zuckerbot.ai/api/mcp is a hosted Streamable HTTP endpoint serving the same tools.

  • claude.ai — add it as a custom connector (Settings → Connectors → Add custom connector) and authenticate via OAuth, or pass an Authorization: Bearer zb_live_... header.
  • Claude Code:
bash
claude mcp add --transport http zuckerbot https://zuckerbot.ai/api/mcp --header "Authorization: Bearer zb_live_..."
  • Any Streamable HTTP client — point it at https://zuckerbot.ai/api/mcp with your API key as a bearer token.

CLI (for humans)

bash
npm install -g zuckerbot-mcp
zuckerbot preview https://your-business.comzuckerbot meta statuszuckerbot create https://your-business.com --budget 5000 --objective leads

Tools (50+)

Audit & Licensing (2)

ToolWhat it does
audit_accountFull read-only account audit: spend flagged for review against each campaign's objective, creative fatigue, opportunity score (0-100), projected CPL improvement, prioritised action items. Available on every tier — the recommended first call
redeem_licenseRedeem a lifetime licence code (Dealify/AppSumo) and upgrade all API keys on the account

Setup & Account (7)

ToolWhat it does
quickstartGuided setup: check auth, show next steps, recommended tool flow
meta_statusCheck Meta connection status for your API key
list_ad_accountsList available Meta ad accounts and current selection
select_ad_accountConnect a specific ad account
list_meta_pagesList Facebook pages and current selection
select_meta_pageSet active page for ad delivery
get_launch_credentialsVerify all required credentials are set before launching

Campaigns (9)

ToolWhat it does
preview_campaignGenerate ad preview from a URL (no Meta account needed)
create_campaignCreate a campaign draft with strategy, targeting, and creatives
get_campaignGet campaign detail, workflow state, and linked creatives
approve_campaign_strategyApprove tiers and creative angles for an intelligence campaign
suggest_anglesGet proposed creative angles and audience tiers for a draft
activate_campaignTemporarily unavailable; intelligence campaigns remain planning-only
launch_campaignLaunch one or all variants from a draft on Meta
pause_campaignPause a campaign, ad set or ad, including spec-built Meta campaigns
resume_campaignPreview and explicitly activate one existing Meta campaign, ad set or ad
get_performanceReal-time campaign metrics: spend, leads, CPL, CTR, ROAS

Audiences (6)

ToolWhat it does
create_seed_audienceBuild a custom audience from hashed CAPI users
create_lookalike_audienceCreate a lookalike from any seed audience
list_audiencesList all custom and lookalike audiences
refresh_audienceRefresh an audience or sync latest state from Meta
get_audience_statusCheck audience size, status, and readiness
delete_audienceRemove an audience from Meta and ZuckerBot

Creatives (8)

ToolWhat it does
upload_creativeUpload finished assets and provision paused Meta ads
get_creative_statusCheck creative generation progress
creative_analysisAI analysis of ad creative performance with recommendations
creative_qaQuality check creatives against Meta ad policies
generate_briefsGenerate creative briefs based on performance data
generate_creatives*Generate ad copy and images (or AI video)
request_creative*Create a creative handoff package for production

* Creative image/video generation tools (generate_static_ad, generate_video_ad, get_video_ad_status, generate_creatives, request_creative) are disabled by default — enable them with ZUCKERBOT_ENABLE_CREATIVE_TOOLS=1 in your MCP config env (paid add-on coming). All creative analysis tools stay available.

Conversion Tracking / CAPI (5)

ToolWhat it does
capi_configGet or update server-side conversion tracking config
capi_status7-day and 30-day CAPI delivery and attribution stats
capi_testSend a test event through the CAPI pipeline
sync_conversionSend lead quality feedback to Meta's algorithm
list_pixelsList and select Meta pixels for conversion tracking

Reporting (2)

ToolWhat it does
get_campaign_insightsCampaign / ad set / ad-level Meta performance for any campaign in the account (including non-ZuckerBot ones), with deduped lead metrics
get_account_insightsAccount-wide spend, impressions, CTR, CPM, CPC, and frequency aggregated daily or monthly

get_campaign_insights surfaces three distinct lead figures rather than one collapsed number, each verified against Ads Manager:

FieldMeaning
meta_result / cost_per_meta_resultMeta's authoritative deduped "Results" for any objective (Ads Manager "Results" column), with meta_result_type naming the underlying result (conversion_lead for lead campaigns, offsite_conversion.fb_pixel_complete_registration / purchase for sales). Supersedes the now-deprecated results / cost_per_result
meta_leads / cost_per_meta_leadDeduped on-Meta leads (onsite_conversion.lead_grouped) — matches Ads Manager "Meta Leads"
conversion_leads / cost_per_conversion_leadCRM-qualified conversion leads (from Meta's results indicator conversion_leads:conversion_lead) — matches "Conversion leads". Lead-specific (0 for non-lead objectives)
actions / cost_per_action_typeFull labelled arrays of { action_type, value } (counts) and { action_type, value } (cost in dollars) for every Meta action type
results / cost_per_resultDeprecated. Objective-resolved result that mis-ranks mixed campaigns. Kept for back-compat — prefer meta_result / cost_per_meta_result
leads / cplDeprecated. Inflated surface count (action_type: lead) that double-counts the instant-form lead and its CAPI echo. Kept for back-compat — prefer meta_leads / conversion_leads

Costs are derived as spend / count; Meta's cost_per_action_type is non-additive and is never summed. The same fields roll up in summary as total_meta_result / blended_cost_per_meta_result (with meta_result_type), total_meta_leads / blended_cost_per_meta_lead, and total_conversion_leads / blended_cost_per_conversion_lead (with total_leads / blended_cpl deprecated alongside their per-row counterparts).

Portfolios (5)

ToolWhat it does
create_portfolioCreate an audience portfolio from a template
launch_portfolioTemporarily unavailable; portfolios remain planning/monitoring-only
portfolio_performanceTier-by-tier portfolio performance breakdown
rebalance_portfolioDry-run or apply budget rebalancing across tiers

Research (3)

ToolWhat it does
research_reviewsReview intelligence for any business
research_competitorsCompetitor ad analysis by industry and location
research_marketMarket intelligence and ad benchmarks

Business Context (4)

ToolWhat it does
enrich_businessCrawl a website and cache structured business context
upload_business_contextUpload text content and extract business insights
list_business_contextList uploaded context files and summaries
select_lead_formSelect a lead form for campaign targeting

Typical Agent Flow

0. Audit       →  audit_account (how is this account doing today?)1. Research    →  research_reviews + research_competitors (parallel)2. Preview     →  preview_campaign (show user what ads look like)3. Create      →  create_campaign with mode=legacy (launch-ready draft)4. Review      →  confirm targeting, creative, Meta connection, and budget5. Launch      →  launch_campaign after explicit approval6. Monitor     →  get_performance + creative_analysis7. Pause       →  pause_campaign whenever delivery must stop8. Optimise    →  sync_conversion + audience tools

Every tool returns a _hint field suggesting the logical next step, so your agent always knows what to do next. Shorthand: legacy create -> review -> launch -> monitor. Intelligence activation and portfolio launch are temporarily unavailable; existing Meta objects use the reviewed resume workflow below for spec-built and external campaigns. MCP names include zuckerbot_enrich_business, zuckerbot_upload_business_context, zuckerbot_get_campaign, zuckerbot_activate_campaign, and zuckerbot_create_seed_audience. zuckerbot_duplicate_ad duplicates one supported ad into an existing ad set in the same ad account — dry-run by default, always created PAUSED, and executes only with an explicit idempotency_key so a retry can never create the ad twice. zuckerbot_upload_ad_asset uploads a brand-new image or video file into the connected ad account's library from a hosted https URL (Meta downloads it directly), returning the image_hash or video_id; poll zuckerbot_get_ad_asset_status until a video is processed. zuckerbot_create_ad then builds one new creative + one new PAUSED ad from that asset in any EXISTING ad set — including live campaigns built outside ZuckerBot — with the same dry-run-first, idempotency_key-gated contract as duplication.

ZuckerBot vs alternatives

ZuckerBotPipeboardAdAmigo.aiSupermetrics
What it isMeta Ads toolkit for agentsBasic Meta MCPFull ad management agentData extraction
Tools50+~20N/A (platform)N/A (connectors)
Creative analysis✅ AI-powered❌✅ Platform-only❌
CAPI support✅ Full pipeline❌Partial❌
Audience builder✅ Seed + LAL❌✅ Platform-only❌
Works with any agent✅ MCP standard✅ MCP standard❌ Locked to platform❌
PriceFree tier availableFree$349/mo/account$39-299/mo

Pricing

TierMonthlyAPI CallsTools
Free$01,000/moRead-only (performance, analysis, research, account audit)
Pro$49 + 0.1% of ad spend50,000/moAll tools including campaign management
Scale$149 + 0.05% of ad spend500,000/moAll tools + multi-account + priority rate limits

Free tier gets you started. Pro pays for itself with one optimised campaign.

Get your API key

Lifetime deal

Grabbed a ZuckerBot lifetime licence on Dealify? Codes look like ZB-XXXXX-XXXXX-XXXXX and stack on one account:

CodesTierAd accountsAPI calls
1Lifetime Tier 112,500/mo
2Lifetime Tier 2310,000/mo
3Lifetime Tier 31030,000/mo

Redeem straight from your agent with the zuckerbot_redeem_license tool ("redeem my ZuckerBot code ZB-...") or in the browser at zuckerbot.ai/start.html. Redeeming upgrades every API key on your account — and if you don't have a key yet, one is minted for you (shown once, so save it).

Example conversation

You: How are my Meta campaigns doing this week?

Agent calls get_account_insights + creative_analysis

Agent: You spent $2,340 across 4 campaigns this week. Your LAL campaign is crushing it at $28 CPL — that's 40% below your account average. But your broad targeting campaign is at $95 CPL and burning budget. The "customer testimonial" creative has a 3.2% CTR vs 1.1% for your product shots. I'd recommend pausing the broad campaign and shifting that budget to the LAL.

You: Do it.

Agent calls pause_campaign + (budget adjustment)

Development

bash
git clone https://github.com/DatalisHQ/zuckerbot.gitcd zuckerbotnpm installnpm run buildnpm start

License

MIT

Activate a PAUSED spec-built campaign

Use zuckerbot_resume_campaign (POST /v1/meta/resume) with the real Meta campaign_id (spec-built or external campaigns, not managed ZuckerBot drafts), optional business_id, and entity_level (ad, adset, or campaign). For an ad or ad set, include its entity_id.

  1. Call with dry_run: true (default). Review the returned hierarchy, account currency, budgets, campaign spend cap and ad-set end dates with the user. Amounts are minor currency units; a daily budget is not a total spend cap.
  2. After explicit approval, send the same target with dry_run: false, confirm_spend: true, the returned preview_hash and a unique idempotency_key (8–128 letters, digits, dots, underscores, colons or hyphens).
  3. For a new spec build, repeat for each intended ad, then ad set, then the campaign last. Obtain a fresh preview for each operation. Activation never cascades to other paused objects and preserves all spend controls.
  4. Use zuckerbot_pause_campaign to stop any of these objects. Campaign-level pause accepts the real Meta campaign ID; pass business_id if needed.

Retry the exact request/key after a transport failure. An uncertain outcome requires live status inspection (or pausing) before further activation. A stored successful response describes that operation; replay does not reactivate an object paused afterwards. ACTIVE is configured status; Meta review, schedules, and parent/child status can still prevent delivery. Campaigns with more than 100 ad sets or 100 ads require Ads Manager for this preview workflow.

The hosted MCP receives this tool when its API deployment ships. Installed local MCP clients require a package release containing the tool. The legacy draft launch tool is not used for activating objects created by the spec builder.

Local ad asset uploads

Run the stdio MCP or CLI on the machine containing the files. zuckerbot_upload_ad_asset accepts exactly one of asset_url, an absolute file_path, or files: [{ file_path, label? }] (up to 20). Local files may be JPG/JPEG/PNG (30 MB maximum) or MP4/MOV (4 GB maximum). The client validates all files before a batch starts, transfers them privately in bounded chunks, and returns per-file results in order. No manual public hosting step is needed. Images include image_hash, original width, height, and name; videos retain the existing processing status/polling flow. A failed batch entry does not undo previous library uploads. Hosted MCP cannot access local paths: use a local client or asset_url. Library uploads do not create ads or enable delivery.

來源:README.md,提交 b4b5334

工具

0
該伺服器需要登入,因此 SourceWeft 無法在沒有帳號的情況下讀取其工具,也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

版本歷史

1
  1. v0.4.4最新Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分