Meta Ads Mcp Scaleforge
@Mike25app
About Meta Ads Mcp Scaleforge
Control Facebook & Instagram Ads from Claude, ChatGPT, Cursor, or any MCP-compatible agent. Direct Meta Graph API v24.0 wrapper with 32 tools — no backend required, just bring your own Meta access token. Auto-batches bulk ops, pre-flight ads_volume checks, PBIA auto-provisioning,
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"scaleforge-mcp-meta-ads": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@getscaleforge/mcp-meta-ads",
"--client",
"claude"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Meta Ads Mcp Scaleforge?
Meta Ads Mcp Scaleforge is an MCP server that wraps Meta Graph API v24.0, giving MCP-compatible agents (Claude, ChatGPT, Cursor, etc.) 32 tools to control Facebook and Instagram Ads. No backend is required—just a Meta access token. It bakes in solutions for common Meta API pains: rate limits, token expiry, deprecations, image hash account scoping, and the 250-ads-per-Page cap.
How to use Meta Ads Mcp Scaleforge?
Install via npm (npx -y @getscaleforge/mcp-meta-ads) or use the Smithery-hosted endpoint. Configure your MCP client with META_ACCESS_TOKEN (user or system user token). The README covers Smithery one-click setup, Claude Code CLI, Claude Desktop JSON config, Cursor, and local inspector testing.
Key features of Meta Ads Mcp Scaleforge
- 32 tools across 10 categories (accounts, campaigns, ad sets, ads, creatives, media, insights, batch ops, Page-Backed Instagram Accounts, ads volume)
- Auto-batching via
pause_campaigns_batch,activate_campaigns_batch,update_bids_batch(up to 50 ops/request, auto-chunked) - Pre-flight
ads_volumecheck before bulk activations to avoid the 250-ad-per-Page silent cap - Enhanced error messages with actionable links for token expiry and rate limits
- PBIA auto-provisioning (
get_pbia) for Instagram placement setup - Uses v24.0 field names (e.g.,
instagram_user_id, nodegrees_of_freedom_spec)
Use cases of Meta Ads Mcp Scaleforge
- Automatically create, update, pause, and delete campaigns, ad sets, and ads from an AI agent.
- Bulk pause or activate campaigns across multiple ad accounts while respecting rate limits.
- Check ad volume per Page before activating new ads to avoid the 250-ad cap.
- Upload images and videos, then build creatives and launch placements (including Instagram via PBIA).
- Pull campaign, ad set, and ad-level insights with breakdowns for analysis and optimization.
FAQ from Meta Ads Mcp Scaleforge
What access token do I need and which permissions are required?
You need an access token with ads_management, ads_read, business_management, pages_read_engagement, and pages_manage_ads. For stable production use, generate a never-expiring System User token inside Meta Business Manager.
How does the MCP handle Meta's rate limit (error code #17)?
Batch tools (pause_campaigns_batch, activate_campaigns_batch, update_bids_batch) use the Meta Batch API with up to 50 ops per HTTP request and automatic 2-second gaps between chunks, reducing the chance of hitting the rate limit.
Why do image hashes fail when I switch ad accounts?
Image hashes are per‑ad‑account. You must re‑upload an image to each target account; video IDs are global. The MCP documents this on the upload_image and create_ad_creative tools.
How do I provision Instagram placement without an Instagram login?
Use the get_pbia tool. It creates a Page‑Backed Instagram Account (PBIA) on demand and returns the instagram_user_id needed for object_story_spec.
Does the MCP send data to a third-party backend?
No. The MCP is a local translation layer—every call goes directly from your machine to graph.facebook.com/v24.0. It does not cache, proxy, or phone home.
More AI & Agents MCP servers
Intervals.icu MCP Server
mvilanovaModel Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
Perplexity Ask MCP Server
ppl-aiThe official MCP server implementation for the Perplexity API Platform
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
Comments