Birch MCP

The ads MCP for ad launches and automation

Check your launches, read your rule logs and create and edit your rules, right from the AI tools you already work with

Connect Birch MCP

How to connect Birch to your AI tool

1. Open connector settings

On Pro and Max, go to Customize → Connectors. On Team and Enterprise, go to Organization settings → Connectors.

2. Add a custom connector

Click + → Add custom connector. Name it Birch and paste the URL: . Click Connect.

3. Sign in to connect

Sign in with your Birch account.

Track ad launches and edit automation rules

Use Cases

Automate your ads from Claude and other AI tools. Ask “Pause Meta ads with CPA over $40 after $100 spend,” and Birch MCP builds the rule with conditions, actions and a schedule. Dry-run it to preview what the rule will affect.

Ask whether yesterday’s uploads went live. Claude checks your recent Stage launches and flags ads that failed or stalled.

Describe the change once, and Birch MCP updates every matching rule across your Meta, Google and TikTok workspaces, then runs them right away if you want.

With Birch MCP, your AI tool reads your rule logs and explains what fired, why and how rules affected each other. Schedule it as a morning check-in and start the day briefed.

Ask “What’s actually working?” and Claude checks every rule’s history and flags idle and failing rules.

Connect your analytics, project tracker and other martech tools to your ad automation. Find the gap with full context and fix it in one chat.

Hold to pause auto-switchingPaused. Release to go on

Tool directory

34 tools: 18 read-only and 16 write

13 tools · Write

Rule management

Create a rule from a plain description, with a dry run first. Then edit any rule: conditions and actions, schedule and dates, filters, ad accounts and alerts; switch it on or off, move it or run it now.

3 tools · Read-only

Stage launches

Track your Stage launches on Meta, TikTok and Snapchat: each upload or create task’s status, progress and exact error message, the creative files it uploaded with their platform media IDs, and the ads it created with their ad and ad set IDs.

9 tools · Read-only

Rules & logs

The core of the read surface. List rules with their folders and categories, read each rule’s logic one line per task, see what it can use and where it alerts, then drill into its runs: what matched, what fired, any errors.

2 tools · Read-only

Metrics catalog

Search Birch’s metric catalog by description to find metric IDs, labels, platforms, and features, and list your workspace’s custom metrics.

1 tool · Read-only

Help

Keyword/semantic search over the Birch help center, so an AI client can answer product questions from real docs instead of guessing.

4 tools · 1 read-only, 3 write

Webhooks

List, create, update and delete the webhooks your rules send alerts to. Available on trial and Pro plans, for company admins.

2 tools · Read-only

Workspace & accounts

List the workspaces the connected user can access, then the ad accounts under a workspace for a given platform.

13 tools · Write

Rule management

Create new rules and manage and edit existing ones across Meta, Google, TikTok, and Snapchat: create a rule from a plain description with a dry run first, set its settings, run schedule and active dates, change conditions and actions, enable or disable, rename, duplicate, move between folders and categories, change ad accounts, replace entity filters, choose notification channels, and run a rule now.

  • create_rule

    Create a full rule in one call: tasks, filters, ad accounts, schedule and time zone, settings, active dates, alert channels, folder and category. Dry run checks everything and saves nothing

  • set_rule_settings

    Change a rule’s settings: time zone, attribution and the other platform settings

  • set_rule_run_schedule

    Set when a rule runs, in the same text get_rule_details prints (for example Mon-Fri 09:00-18:00), or remove the schedule

  • set_rule_active_dates

    Set or clear the start and end dates of a rule

  • edit_rule_tasks

    Add, replace or remove a rule’s conditions and actions. Same checks as the rule editor, dry run first, never turns a rule on or off

  • run_rule_now

    Run an active rule immediately instead of waiting for its schedule (once every 10 minutes per rule)

  • set_rule_notification_channels

    Choose where a rule sends alerts, from the email, Slack and webhook channels the workspace already has

  • set_rule_status

    Enable or disable an existing rule.

  • set_rule_ad_accounts

    Replace the ad accounts a rule runs on.

  • set_rule_filters

    Replace a rule’s full entity filter setup.

  • rename_rule

    Rename an existing rule.

  • move_rule

    Move a rule into a folder or to the top level, or into a category.

  • duplicate_rule

    Copy a rule within or across workspaces.

3 tools · Read-only

Stage launches

Track your Stage launches on Meta, TikTok and Snapchat: each upload or create task’s status, progress and exact error message, the creative files it uploaded with their platform media IDs, and the ads it created with their ad and ad set IDs.

  • list_stage_tasks

    Stage tasks — status, progress counts, error messages. Filterable by status and task type

  • list_stage_uploads

    Creative files uploaded by a Stage task — file name and platform media ID

  • list_stage_created_ads

    Ads created by a Stage task — ad name, platform ad/adset IDs, creation time

9 tools · Read-only

Rules & logs

The core of the read surface. List a workspace’s automation rules (with optional folder filtering), their folder structure and categories, pull one rule’s full logic, with each task as one readable line, e.g. IF cpc[last_3d] > 2 THEN decrease_budget(value=20), see what a rule can use and where it can send alerts, inspect available entity filters, then list its execution history and drill into one run to see exactly which entities matched, what fired, and any errors.

  • list_automation_rules

    Lists rules on an ad account — ID, name, level, enabled, check interval, folder. Filterable by folder

  • get_rule_details

    Full rule logic: each task as an IF/THEN line, schedule, filters, targeted entities, notification channels

  • list_rule_logs

    Execution log summaries — when the rule ran, entities evaluated/acted on/errored

  • get_rule_log

    Detailed per-entity outcomes — actions applied, status changes, condition results, errors. Filterable

  • list_rule_folders

    Folder tree for automation rules — ID, name, parent_id for subfolders

  • list_rule_categories

    Lists the categories that group your rules and folders, so your AI can audit or edit a whole category at once

  • get_rule_filter_options

    Lists available entity filter options for a rule.

  • get_rule_task_options

    Lists everything a rule can use: actions and their arguments, metrics, custom metrics and timeframes

  • list_notification_channels

    Lists the email, Slack and webhook channels a rule can send alerts to, as the rule editor offers them

2 tools · Read-only

Metrics catalog

Search Birch’s metric catalog by description to find metric IDs, labels, platforms, and features, and list your workspace’s custom metrics.

  • search_metrics

    Natural-language search of Birch’s metric catalog — metric ID, label, platform, feature

  • list_custom_metrics

    Lists the workspace’s custom metrics with their formulas, and flags any that are broken

1 tool · Read-only

Help

Keyword/semantic search over the Birch help center, so an AI client can answer product questions from real docs instead of guessing.

  • search_help

    Keyword search across Birch Help Center articles

4 tools · 1 read-only, 3 write

Webhooks

List, create, update and delete the webhooks your rules send alerts to. Available on trial and Pro plans, for company admins.

  • Read-only

    list_webhooks

    Lists your company’s webhooks — name, URL, custom parameters and the workspaces whose rules can notify them

  • Write

    create_webhook

    Create a webhook for your rules’ alerts. Birch tests the URL before saving it

  • Write

    update_webhook

    Change a webhook’s name, URL, description, custom parameters or workspaces

  • Write

    delete_webhook

    Permanently delete a webhook; rules that notify it stop delivering to it

2 tools · Read-only

Workspace & accounts

List the workspaces the connected user can access, then the ad accounts under a workspace for a given platform.

  • list_workspaces

    Lists all workspaces the user can access, with IDs and currency

  • list_ad_accounts

    Lists ad accounts in a workspace — Birch ID, name, currency, timezone, access status

Cross-platform by design

Birch MCP works with every Birch workspace and ad account you have access to, across Meta, Google, TikTok and Snapchat. One connection, one conversation, every platform.

  • Launches
  • Automation rules

Meta’s own Ads MCP creates and edits campaigns but has no automated-rule tools. Birch MCP tracks your ad launches, analyzes rule logs and creates and edits the rules.

Try asking

“Which ads did yesterday’s Stage launch create? Then lower the CPA threshold on my prospecting rules by 10%.”

  • Automation rules

Google’s official Ads MCP is read-only. With Birch MCP, your AI can create and edit the rules that pause, scale and re-bid your Google campaigns, including switching bid strategies.

Try asking

“Add a task to my Google campaign rules: pause the campaign if it has no conversions in the last 7 days.”

  • Launches
  • Automation rules

TikTok’s own Ads MCP creates campaigns and adjusts budgets, targeting and bids, but has no automated-rule tools. Birch MCP tracks your ad launches, analyzes rule logs and creates and edits the rules.

Try asking

“Did my TikTok Stage launch complete? Then send my TikTok rule alerts to #ads-alerts and run the scaling rule now.”

  • Launches
  • Automation rules

Snapchat’s official Ads MCP is read-only. With Birch MCP, your AI tracks your ad launches, analyzes rule logs and creates and edits the rules that manage your Snapchat ads.

Try asking

“Why did today’s Snapchat launch fail, and which Snapchat rules haven’t acted in the last 30 days?”

Two ways to work with your automation

Birch AI

Explore

Assistant inside the Birch product. It reads your rules and account data and helps you work faster without leaving Birch.

Birch MCP

Brings your real data to Claude and other AI clients. Use it when you’re already working in Claude — alongside your other connected tools. You don’t have to switch to Birch to understand what your automation did.

Birch AI Birch MCP Meta MCP

Learn the difference

A breakdown across six workflows — auditing rules, reading logs, building automation, benchmarking, and more.

See the comparison

Coming next

Ad creation

Ask your AI to upload creatives and create ads across Meta, TikTok, and Snapchat using Stage.

FAQ

What is MCP?

MCP stands for Model Context Protocol — an open standard that lets AI tools connect to external systems and work with their data. Birch MCP uses it to give AI clients access to your automation rules, execution logs, and account structure, so they can read them and create and edit rules.

What is Birch MCP?

Birch MCP is a remote MCP server that connects AI assistants such as Claude and ChatGPT to your Birch workspace. Your AI can check the status of your ad launches and the ads they created, read your automation rules and their execution logs, create new rules, edit rule conditions, actions, filters and alerts, set a rule’s schedule and active dates, and run a rule on demand, across Meta, Google, TikTok and Snapchat ads.

Where can I use Birch MCP?

Anywhere that supports the MCP standard. Claude is the most common client, but any MCP-compatible tool can connect. You add Birch MCP as a connector in your tool’s settings, sign in, and it becomes available in that conversation — no need to pick a specific AI client to use it.

How is Birch MCP different from Meta’s and Google’s ads MCPs?

Meta’s Ads MCP creates and edits Meta campaigns one change at a time, and Google’s Ads MCP is read-only. Birch MCP works on the automation layer: your AI creates and edits the rules that keep managing your ads on Meta, Google, TikTok and Snapchat, and Birch runs them without you prompting. Many teams use both.

Do I need technical skills to set it up?

No. You add Birch MCP in your AI client’s connector settings, sign in with your Birch account, and you’re connected. No API keys, no code.

Can Birch MCP edit my rules?

Yes. With write access, your AI can do anything you can do in the rule editor: change conditions and actions on all four platforms with any metric, including custom metrics, custom events and custom timeframes. It can also change a rule’s filters, ad accounts and notification channels, turn it on or off, rename, move or duplicate it, and run it now. Every edit goes through the same checks as the rule editor, and your AI can dry-run it first. For example: “Lower the CPA threshold to $35”, “Add a ROAS condition”, “Change the budget increase from 20% to 30%”. It can also create a new rule from a plain description, check it with a dry run before saving, and change a rule’s settings, run schedule and active dates.

Can Birch MCP create rules or launch ads?

Rules, yes: your AI can create a full rule from a plain description, check it with a dry run and save it. The rule shows in Birch and opens in the rule editor like any other. Launches, not yet: starting launches through Stage is coming next. Today your AI can track every Stage launch: its status, any errors, the files it uploaded and the ads it created.

Is it safe to give an AI write access to my ads?

Write access is opt-in. Edits are checked like changes made in the rule editor, can be dry-run first, are refused if the rule changed since your AI read it, and editing conditions and actions never switches a rule on or off.

Is there a TikTok Ads MCP?

Yes. Birch MCP covers TikTok automation rules, as well as Meta, Google and Snapchat.

Which Birch plan do I need to access Birch MCP?

Birch MCP is available on all plans. The webhook tools need a trial or Pro plan.

What data does Birch MCP see when I connect?

Workspaces, ad accounts, rule configurations, rule categories, custom metrics, notification channels, webhooks, execution logs, folder structure, and Stage task metadata. It does not see creative content, billing information, or personal data beyond what’s visible in your Birch workspace.

I already use Birch AI. Why would I also use the MCP?

Birch AI works inside the Birch product. Birch MCP works inside your own AI client — where you might already be talking to your analytics, your project tracker, or your team chat. If your daily workflow lives outside Birch, the MCP brings your automation context to where you already are. They’re complementary.

Your launches, rules and logs — in your AI tool

Check your launches, audit your automation, and fix what’s not working — all from one conversation

Book demo
14days free trial
Cancel anytime
No credit card required
Try Birch