Microsoft Ads
→
Anthropic Claude
MICROSOFT ADS connector for Claude (MCP)
Ask Anthropic Claude about your Microsoft Ads data using all available fields — without exporting a single CSV.
- +403 Microsoft Ads fields plus calculated metrics — every dimension and breakdown Microsoft Ads reports.
- Your Microsoft Ads data already lives in Porter. Enable MCP and start asking Claude — no new integrations, no tokens, no servers.
- Cross your Microsoft Ads performance with Google Analytics 4 revenue in one Claude conversation to see real outcomes, not just clicks.
Free forever plan · 14-day full trial · No credit card
Tutorial
How to connect Microsoft Ads to Claude
-
Connect Microsoft Ads to Porter
Log in to Porter with your Microsoft Ads Business account and grant read-only access. Takes 2 minutes — no engineering, no exports.
-
Pick your ad account
Select one or blend multiple ad accounts into a single data source — useful for agencies managing several clients.
-
Add Porter MCP to Claude
In Claude, paste the URL
https://mcp.portermetrics.com/mcpas a custom connector. No JSON-RPC, no local servers. -
Authorize Claude to read Porter
One click. Claude now has read-only access to your Microsoft Ads data through Porter — same scope as your Porter account.
-
Ask in plain English
“Show me Microsoft Ads performance trends over the last 14 days.” Claude returns a filtered table in seconds.
Fields
+403 Microsoft Ads fields, ready for Anthropic Claude
Every field in Microsoft Ads Manager — plus calculated metrics, every attribution window, and creative preview URLs — accessible to Claude on demand.
All Ads Manager fields (and more)
403 fields total — every native Microsoft Ads field plus calculated metrics that aren’t offered natively.
Every breakdown
Segment by campaign, ad set, creative, audience, placement, device, region, hour, date — every breakdown Microsoft Ads supports.
Creative previews and assets
Ad preview URLs plus links to creative assets — Claude can reason over performance + creative in the same answer.
Marketer-friendly naming
Fields named exactly as in Microsoft Ads (e.g. “Cost” not cost_micros). Claude understands them natively.
Full granularity
Hour, day, week, month, year — plus every dimension Microsoft Ads reports.
Cross-channel blending
Same field naming standard across Porter’s connectors — Claude can join Microsoft Ads with GA4, BigQuery, or other sources in one prompt.
Other
- Account Id
- Account Mode
- Account Name
- Account Number
- Ad Description
- Ad Description2
Conversion
- All Conversion Rate
- All Conversions
- All Conversions Qualified
- All Cost Per Conversion
- All Revenue Per Conversion
- Assisted Conversions
Keywords & Search
- Average Position
- Keyword
- Keyword Status
- Query Intent City
- Query Intent Country
- Query Intent County
Visibility
- Absolute Top Impression Rate Percent
- Absolute Top Impression Share Lost To Budget Percent
- Absolute Top Impression Share Lost To Rank Percent
- Absolute Top Impression Share Percent
- Assisted Impressions
- Audience Impression Lost To Budget Percent
Status & Lifecycle
- Account Financial Status
- Account Life Cycle Status
- Account Status
- Ad Group Status
- Ad Status
- Asset Group Status
Cost & Bidding
- Bid
- Budget
- Budget Association Status
- Budget Name
- Budget Status
- Cpc Bid Amount
Ad
- ad group labels Campaign
- ad group labels Client Id
- ad group labels Id
- ad group labels Modified Time
- ad group labels Parent Id
- ad group labels Status
Geography
- City
- Country
- Country Of Sale
- Location Id
- Location Type
- Postal Code
Creative
- Headline
- Headlines Asset Link
- Title
- Title Part1
- Title Part2
- Title Part3
Prompts
Copy-paste prompts for Microsoft Ads × Claude
Add Porter MCP to Claude (paste https://mcp.portermetrics.com/mcp), open a new conversation, and paste any prompt below.
Weekly Budget Pacing & Burn-Rate Check
Show me every campaign where Month To Date Spend is above 75% of Monthly Budget, or where Daily Spend has exceeded Daily Budget on more than 3 days in the last 14 days. Include Campaign Name, Daily Budget, Daily Spend, Spend, Month To Date Spend, and Monthly Budget. Sort by highest burn-rate (Month To Date Spend / Monthly Budget). Flag any campaign projected to exceed its Monthly Budget before month-end based on the last 7-day Daily Spend average. Last 14 days, active campaigns only. Output as a ranked table.Ad Copy Quality Score Component Audit
List all keywords where Quality Score is below 6 or where Historical Quality Score dropped by more than 1 point in the last 90 days. Include Campaign Name, Ad Group Name, Keyword, Quality Score, Historical Quality Score, Ad Relevance, Expected Ctr, and Landing Page Experience. For each flagged keyword, tell me which component score dropped and whether I should rewrite the ad, improve the landing page, or adjust the keyword match type. Last 90 days, active keywords only. Output as a table with an action column.Conversion vs All-Conversions Attribution Comparison
Compare Conversions vs All Conversions for every campaign. Include Campaign Name, Conversions, All Conversions, Conversion Rate, All Conversion Rate, Cost Per Conversion, All Cost Per Conversion, and Assisted Conversions. Calculate the gap (All Conversions minus Conversions) and flag campaigns where the gap is more than 25% of All Conversions. For those campaigns, explain whether the assisted conversions suggest a longer consideration cycle or a targeting issue. Last 30 days, all campaign statuses. Output as a ranked table with a narrative summary.Video Funnel Drop-Off Diagnosis
For every video campaign, show Video Views At25Percent, Video Views At50Percent, Video Views At75Percent, Video Completion Rate, and Average Watch Time Per Video View. Calculate the drop-off between each quartile. Flag campaigns where the drop from 50% to 75% is steeper than 40%, or where Video Completion Rate is below 15%. For each flagged campaign, tell me which quartile loses the most viewers and suggest whether the issue is the hook (0-25%), the middle message (25-50%), or the CTA placement (50-75%). Last 30 days, active campaigns only. Output as a table plus a brief diagnosis per flagged campaign.Search Query Intent Geography Tuning
Rank cities by Query Intent City impressions where Conversion Rate is below the account average. Include Query Intent City, Query Intent State, Query Intent DMA, Impressions, Clicks, Conversions, and Conversion Rate. Flag DMAs where Impressions are high but Conversion Rate is more than 30% below the account median. For each flagged metro, tell me whether I should add geo-bid adjustments, create location-specific ad copy, or exclude the area from targeting. Last 45 days, active campaigns only. Output as a ranked table with a recommendation column.Low-Quality Traffic Budget Drain Audit
Find campaigns where Low Quality Clicks Percent exceeds 15% or where Low Quality Conversions is more than 10% of total Conversions. Include Campaign Name, Low Quality Clicks, Low Quality Clicks Percent, Low Quality Conversions, Low Quality Impressions, Spend, and Conversions. Calculate the estimated budget wasted (Spend multiplied by Low Quality Clicks Percent). Flag the top 5 campaigns by estimated waste and suggest whether the issue is broad match keywords, display network placement, or audience targeting. Last 60 days, exclude paused campaigns. Output as a ranked table with a waste estimate and action column.Impression Share Lost Diagnosis & Action Plan
Show campaigns where Absolute Top Impression Share Lost To Rank Percent is above 30% or where Absolute Top Impression Share Lost To Budget Percent is above 20%. Include Campaign Name, Absolute Top Impression Share Lost To Budget Percent, Absolute Top Impression Share Lost To Rank Percent, Absolute Top Impression Share Percent, Top Impression Share Lost To Rank Percent, and Top Impression Share Lost To Budget Percent. For each campaign, tell me whether the priority action is raise bids (if budget loss is higher), improve ad relevance or landing page (if rank loss is higher), or both. Last 30 days, active campaigns only. Output as a table with a clear action priority column.Multi-Account Quality Score Health Dashboard
Build a cross-account health summary. For each Account Name and Account Id, calculate the average Quality Score, average Historical Quality Score, and the percentage of keywords with Ad Relevance or Expected Ctr or Landing Page Experience below Average. Include total Spend and total Conversions per account. Rank accounts by worst Quality Score trend (Historical Quality Score minus current Quality Score). Flag any account where more than 30% of keywords have a component score below Average. Give me a one-paragraph diagnosis per flagged account and a prioritized fix list. Last 30 days, all active campaigns. Output as a summary table plus narrative diagnoses.Search Query to Keyword Intent Gap Analysis
List the top 20 Search Queries by Impressions that are not exact matches to their assigned Keyword. Include Search Query, Keyword, Match Type, Query Intent City, Query Intent State, Impressions, Clicks, Conversions, and Conversion Rate. For each query, flag whether it has higher Conversion Rate than its parent Keyword — if yes, suggest whether I should add it as an exact match keyword or use it for organic content. Also map Query Intent City and Query Intent State for queries with high Impressions but zero Conversions to identify geo-targeting gaps. Last 45 days, active campaigns only. Output as a ranked table with keyword-expansion and content recommendations.Weekly Executive Performance Summary
Generate a weekly executive summary for my Microsoft Ads account. Include total Spend, total Conversions, average Conversion Rate, average Cost Per Conversion, Return On Ad Spend, total Impressions, total Clicks, Ctr, and Absolute Top Impression Share Percent. Compare each metric to the previous 7-day period and flag any metric that changed by more than 15%. List the top 3 campaigns by Return On Ad Spend and the bottom 3 by Conversion Rate, with one sentence explaining each. End with a 3-bullet "Actions for next week" list based on the biggest opportunity and risk. Last 7 days vs. prior 7 days, all campaigns. Output as a structured exec summary with a headline, metric table, campaign highlights, and action bullets.
Security
Microsoft Ads MCP safety
Porter authenticates to Microsoft Ads with the read-only scope you already approved for your reports. Anthropic Claude queries Porter — not Microsoft Ads directly — so every conversation is rate-limited and cached at Porter side. No new permissions, no ban risk.
- Caching. Porter caches recent query results for 15 minutes per (account, field set) so repeated Claude prompts don’t hit the API again.
- Batching. Multiple field requests are merged into a single API call when possible (max 300 methods per batch request).
- Backoff & retry. Exponential backoff on 429 responses (1s → 2s → 4s → 8s).
- Per-account quotas. Porter tracks per-account daily usage and pauses queries before hitting 80% of the 20,000,000 daily method call quota.
- Read-only enforcement. Although `msads.manage` is technically a read-write scope, Porter’s integration only executes read operations (report downloads, account metadata retrieval). No write operations (campaign creation, budget changes, ad edits) are ever performed, so even compromised tokens cannot modify campaigns, budgets, or ad copy.
- Audited tools. The MCP exposes 6 read-only methods:
get_blend_id,list_accounts,list_categories,list_data_sources,list_fields,query_data.
GDPR compliant · 1,600+ marketers trust Porter with their Microsoft Ads data.
Pricing
Start free. Pay per data source account
- +403 Microsoft Ads fieldsEvery native field plus calculated metrics — accessible to Claude in plain English.
- All attribution windowsCompare 1d-click, 7d-click, 28d-click and 1d_click+1d_view side by side from one connection.
- Same plan, every destinationSend to Anthropic Claude, ChatGPT, Looker Studio, Google Sheets, BigQuery and Slack — one subscription.
- Unlimited usersNo extra cost per team member or seat.
Monthly
Annual Save 17%
Number of Microsoft Ads ad accounts
$12.5
/mo
Billed annually · $12.5/account
Destinations included
Start for free →
Unlimited 14-day free trial + Free forever plan
Explore more
Other connectors & destinations
Porter supports 15+ data sources and 10+ destinations. Mix and match in one subscription — no extra seats or hidden per-destination fees.
Data sources15+ available
Destinations10+ available
FAQ
Questions about Microsoft Ads + Anthropic Claude
What is MCP and how does it connect Microsoft Ads to Claude?
MCP is an open protocol — Model Context Protocol — that lets Anthropic Claude talk to Porter’s API. Porter exposes Microsoft Ads data as read-only tools Claude can call. Paste one URL into Claude’s MCP settings and the connection is live.
Do I need technical skills or coding to set this up?
No. Paste one URL into Anthropic Claude’s MCP settings. No API tokens, no JSON-RPC, no local servers. If you can copy and paste, you can connect Microsoft Ads to Claude.
Will connecting my Microsoft Ads account get it banned?
No. Porter reads from its own already-authorized infrastructure. No new OAuth scopes, no third-party app reviews. Read-only access — Claude cannot modify campaigns, budgets, or settings.
What Microsoft Ads metrics can I analyze in Claude?
All 403 fields across 21 categories. Key metrics include Amount spent, Purchases, Purchase ROAS, and Cost per purchase. Plus creative fields like Hook rate, Hold rate, and Ad preview URLs; attribution windows including Purchases (1 day click), Purchases (7 days click), and Purchases (28 days click); and video play curves at 25%, 50%, 75%, and 95%.
Can I create or edit campaigns from Claude, or is this read-only?
Read-only. Anthropic Claude can query, analyze, and summarize. It cannot pause campaigns, change budgets, edit ad copy, or modify targeting. This is by design for safety.
I already use Porter for Microsoft Ads reporting — do I need to reconnect?
No. Your existing Microsoft Ads connection in Porter feeds Anthropic Claude automatically. Enable the MCP add-on in one click. Same data, new interface.
How much does the Microsoft Ads MCP integration cost?
Included in your Porter plan. No extra charge for Anthropic Claude, ChatGPT, or Slack AI access. Pay per ad account, not per destination.
Chat with your Microsoft Ads data in Claude
Your Microsoft Ads data already lives in Porter. Enable MCP and start asking Claude about campaigns, creatives, and ROAS — no new integrations, no tokens, no servers. Get live, conversational access to all 403 Microsoft Ads fields including creative previews, every attribution window, and multi-account blends.
Free forever plan · 14-day full trial · No credit card