1
Ask
Ask in your assistant
A question or a request, in plain words.
- Client
- Claude
- Workspace
- Chosen at consent
- Request
- Scale the best ad set
MCP server
Meta Ads MCP server
The Adrails MCP server lets Claude, ChatGPT, Claude Code, Codex and other remote MCP clients work on your Meta ad accounts. Sign in with OAuth, choose one workspace and its permissions, then ask. Reads return your figures, and every change comes back as a proposal you approve in Adrails.
Reviewed Oct 3, 2026
Product view
The accounts behind every answer
Your assistant reads the same workspace you open in Adrails. Check a figure in Campaigns or Analysis, and review the change it prepared before it reaches Meta.
Product workflow
From a question in Claude to an approved change on Meta
Your assistant reads through the server, prepares one exact change, and stops. The change reaches Meta only after you approve it in Adrails.
2
Read
Read the account
Read tools return your figures and change nothing.
- Tool
- performance_period
- Level
- Ad set
- Period
- Last 7 days
3
Proposal
Prepare the change
A write tool returns a proposal and its link, nothing more.
- Tool
- campaigns_change_budget
- Daily budget
- $400 to $480
- Status
- Awaiting approval
4
Approval
Approve in Adrails
You review the exact change, signed in as yourself.
- Page
- Review advertising change
- Expires
- 30 minutes
- Applied
- Once, after approval
Illustrative workspace data. Values show the product flow and are not customer results.
MCP tools
The tools your assistant calls on Meta
Each name is the tool your client lists. A read changes nothing. A proposal returns a link, and the change waits for your approval in Adrails.
01
Read Meta results from your assistant
Ask for spend, results, revenue, ROAS, CPA, CTR, CPM, reach and frequency over an exact period, at the account, campaign, ad set or ad level, and compare it with another period. The server reads Meta for that ad account and returns a table your assistant reasons over.
Other tools go past raw figures: they review campaigns against their actual objective, say whether each budget should be kept, raised, cut or investigated, and group ads by the image or video they use to find winners and fatigue.
- performance_period
- Read. Figures for an exact period, at account, campaign, ad set or ad level
- reporting_overview
- Read. Spend, revenue and conversions across the connected accounts
- portfolio_review
- Read. Campaigns checked against their objective, with at most three priorities
- budget_recommend
- Read. Maintain, increase, reduce or investigate each budget owner
- creative_insights
- Read. Ads grouped by the image or video they use, with winners and fatigue
02
Prepare a launch in the conversation
A new Meta launch starts with launch_brief. It takes only what you said or chose and returns what a clean launch still needs, as questions with options: the ad account, objective, pixel and event, countries, budget, dates, Page and copy. Once nothing is missing, campaigns_launch prepares the campaign, ad sets and ads.
After you approve, Adrails sends the images or Google Drive files to the ad account and builds everything paused. Switching the ads on is a second proposal, and it lists every budget that starts spending.
- launch_brief
- Change. What a clean launch still needs, as questions with options
- campaigns_setup
- Read. Pages, pixels and images available in the selected accounts
- targeting_options
- Read. Real IDs of audiences, interests, languages and locations
- audience_estimate
- Read. Meta's reach estimate for the proposed targeting
- campaigns_launch
- Proposal. Campaign, ad sets and ads built paused after approval
- campaigns_launch_activate
- Proposal. Switches a finished launch on, listing every budget that starts
03
Change what runs, one approval at a time
A pause, a resume, a budget change of at most 30%, a duplicate or a split test is prepared as one exact change. The result is marked awaiting approval and carries a link to the Review advertising change page in Adrails, where you choose Approve this change or Decline.
On approval, Adrails reads Meta again and applies the change once, or blocks it if the entity changed in the meantime. A proposal expires after 30 minutes, and an applied change can be undone while Meta still matches what Adrails wrote.
- campaigns_set_status
- Proposal. Pauses or resumes a campaign, ad set or ad
- campaigns_change_budget
- Proposal. Raises or lowers a daily budget, at most 30% at once
- campaigns_duplicate_to_draft
- Proposal. A paused copy, optionally with 3 to 5 copy variants
- campaigns_split_test
- Proposal. A test against a running ad set or ad, one variable at a time
- actions_undo
- Proposal. Reverts an applied change while Meta still matches it
04
Connect once, scoped to one workspace
Add https://adrails.ai/api/mcp to your client. It registers itself and opens Adrails in your browser, where the consent screen asks for the workspace and the permissions. There is no client ID, secret or API key to copy.
Read access is required and covers every ad account in that workspace. Preparing advertising changes is a separate permission that only an owner or admin can grant. Revoke a client at any time under Your connections on the MCP page.
- Claude: Settings, Connectors, Add custom connector
- Claude Code: claude mcp add --transport http adrails https://adrails.ai/api/mcp
- ChatGPT: Developer mode, then a custom MCP server with OAuth
- Codex, or any client with remote MCP and OAuth
FAQ
Common questions
What is a Meta Ads MCP server?
A server that speaks the Model Context Protocol, so an AI assistant such as Claude or ChatGPT can call tools that read and act on Meta ad accounts. Adrails runs one at https://adrails.ai/api/mcp, and your assistant signs in to it with your Adrails account.
Which AI clients can connect?
Claude on claude.ai and in the desktop app, Claude Code, ChatGPT with Developer mode and Codex are documented step by step. Any client that supports remote MCP over Streamable HTTP, with OAuth and dynamic client registration, connects the same way.
Can the assistant change my Meta campaigns on its own?
No. No tool creates, edits, pauses, switches on or rebudgets a campaign, ad set or ad by itself. It prepares a proposal, and only you, signed in to Adrails as an owner or admin, can approve it. The permission prompt in your AI client is not an approval.
Do I need a Meta developer app or an access token?
No. Meta is connected once in Adrails. The assistant signs in to Adrails with OAuth, and tool results never contain provider credentials.
Does a tool call use Adrails credits?
No. Your assistant's model does the reasoning, so a tool call uses no agent credit. The one exception is an automation run that contains an agent step. Preparing a proposal needs an active plan.
Can it work across several Meta ad accounts?
Yes. A connection covers every ad account in its workspace, and a call can narrow to some of them. To work in another workspace, connect again and choose it.