HBCA Meta Ads MCP
A read-only MCP server for querying Meta Ads accounts through Meta's Marketing API. It provides tools to retrieve ad accounts, campaigns, ad sets, ads, and performance insights.
README
HBCA Meta Ads MCP — Render starter
A read-only MCP server that lets ChatGPT query one Meta Ads account through Meta's Marketing API.
Safety design
- Read-only tools only. There are no pause, budget, create, update, or delete tools.
- Meta access token is read only from a Render environment variable.
- The token is sent to Meta in the Authorization header, not placed in request URLs.
- The MCP endpoint uses a random secret path. This is suitable for a private prototype; for broader/shared production use, add OAuth 2.1.
- Uses MCP SDK 1.26.0, which includes the February 2026 cross-client isolation security fix.
- Creates a fresh MCP server/transport per request to avoid cross-client state sharing.
Environment variables
Required:
META_ACCESS_TOKEN— your Meta access token. Paste this into Render only.MCP_PATH_SECRET— a long random secret.render.yamlcan generate this automatically.
Configured by default:
META_AD_ACCOUNT_ID=act_10151727290614507META_API_VERSION=v26.0
Tools
get_ad_accountsget_campaignsget_adsetsget_adsget_insights
Deploy on Render
-
Create a new GitHub repository, for example
hbca-meta-ads-mcp. -
Upload every file in this folder to the repository root and commit.
-
In Render choose New → Blueprint and connect the GitHub repository. Render will read
render.yaml. -
When prompted for
META_ACCESS_TOKEN, paste the token directly into Render. Do not put it in GitHub or ChatGPT. -
Deploy.
-
Open the Render service → Environment and copy the generated value for
MCP_PATH_SECRET. -
Your ChatGPT MCP URL will be:
https://YOUR-RENDER-SERVICE.onrender.com/mcp/YOUR_MCP_PATH_SECRET -
Check health first:
https://YOUR-RENDER-SERVICE.onrender.com/healthIt should return JSON with
"ok": true.
Connect to ChatGPT
In ChatGPT, enable Developer mode, add a custom MCP/plugin connection, and paste the full HTTPS MCP URL including the secret path.
Use No Authentication for this prototype because the endpoint itself contains a high-entropy secret. Do not share the URL. For a team/shared deployment or any write tools, replace this with OAuth 2.1 before proceeding.
Suggested first test prompt:
Using HBCA Meta Ads, show my campaigns and analyze campaign-level performance for the last 30 days. Do not make any changes.
Important Meta token note
The token created in Graph API Explorer can expire. After the connection is proven, replace it with a durable Meta Business/System User token appropriate for your business setup and requested permissions.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。