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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.