In-depth architectural comparison of the Proofsource and Vibeads MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Proofsource
Marketing · Remote HTTP/SSE
Quality: 69/100 (Great) | Auth: OAuth 2.0
Vibeads MCP
Marketing · Local stdio
Quality: 57/100 (Good) | Auth: No auth required
Verdict Summary: Choose Proofsource if you need specialized Marketing tools running via a hosted cloud SSE transport. Choose Vibeads MCP if your workspace requires Marketing integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
P
Choose Proofsource when:
You need dedicated capabilities in the Marketing domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: OAuth 2.0 (Paid Service).
The brands this Proofsource workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.
list_topics
The topics and buyer questions Proofsource asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt needs.
get_visibility
How often ChatGPT, Perplexity, Claude and Google AI mention the brand when buyers ask about its category. by=engine (default): mention rate, share of voice, average position, citation share and sentiment per engine, with the change from the previous period. by=question: each buyer question's mention rate and rank.
get_competitors
The competitors AI answers name for the brand's buyer questions, per engine, with each one's share of voice against the brand and how it changed over the window.
get_citations
The websites AI answers cite for the brand's buyer questions, ranked by share of citations and by how many answers cite them, and where the brand's own site ranks.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Proofsource is categorized under Marketing and uses a remote streaming HTTP/SSE transport. In contrast, Vibeads MCP belongs to Marketing using local stdio subprocess. Select Proofsource when you need capabilities focused on marketing and Vibeads MCP when you require tools for marketing.
What moved over the window: the daily mention-rate trend, how much the engines' answers changed, notable changes on competitors' websites, and new pages about the category.
list_fix_opportunities
The gaps that keep AI engines from citing or recommending the brand, each with its evidence and the suggested fix. Gives the gap_id mark_fix_shipped needs.
get_fix_verification
Each fix marked shipped for the brand with its mention rate before and after and a verdict: moved (beyond normal answer churn), within_noise, or awaiting_samples. Fixes marked "Not a fix" are left out; auto-detected page changes carry source auto_detected.
create_prompt
Adds a buyer question to a topic so Proofsource asks it on every engine in the plan from the next run. Counts toward the plan's question limit. Calling again with the same text returns the existing question, never a duplicate.
mark_fix_shipped
Records that a fix shipped, against a gap_id from list_fix_opportunities or a published content_draft_id, so get_fix_verification can measure whether it moved the brand's mention rate. Calling again with the same fix and description returns the existing record.
add_brand
Start measuring a brand: does ChatGPT, Perplexity, Claude or Google AI mention it, and who does AI recommend instead? Give the brand's website (or its app store, Google Maps, YouTube or Instagram link). Proofsource reads the site, picks the buyer questions, and starts the first scan across the AI engines. Reading the site takes 1-2 minutes; if it is still running, call again with the same link and it picks up the same run, never a second one. Returns the brand_id; then use get_scan_status.
get_scan_status
Progress of a brand's first scan after add_brand: the stage, how many AI answers are in out of how many expected, per engine, and when it should finish. Once complete, use get_visibility for the results.
+2 more tools listed on main page
Vibeads MCP Tools (29)
list_campaigns
Your campaigns in VibeAds (published, imported and drafts) with status, budget and category. Campaigns only in your Google Ads account are listed by `find_campaigns_to_import
get_campaign_details
Deep dive on one campaign: metrics, ad groups, targeting, landing pages, diagnostics
get_account_health_score
0-100 score + letter grade across 6 dimensions, optionally per-campaign
get_search_term_analysis
Wasted spend + winners from each campaign's latest synced search terms, which cover the 7 days before that sync (configurable cost threshold)
get_diagnostics
Latest agent-optimize diagnostics with severity + recommended fix (up to 50)
find_campaigns_to_import
Before importing: the campaigns in your Google Ads account, read from Google Ads, each marked with whether it is in VibeAds (VibeAds manages only the campaigns in it). Called `list_google_ads_campaigns` in 0.2.15
get_performance_report
One campaign's or a whole account's figures for a period you choose (a preset or two dates, up to 90 days), read live from Google Ads, optionally by day, device, hour, ad group, keyword or location. Money in the account's currency. VibeAds builds every query; the assistant only picks the period and…
audit_google_ads_account
An audit of one connected Google Ads account, read live from Google Ads: up to 25 Search campaigns over the last 30 days, whether or not they are in VibeAds, with a 0-100 health score and grade for the account and each campaign, the issues grouped by check with what fixes each in Google Ads, and ea…
list_keywords
One published campaign's ad groups, keywords and negative keywords, read live from Google Ads: match type, status, max CPC and 30 days of clicks, cost and conversions
research_keywords
Keyword ideas from Google's Keyword Planner for seed keywords, a web page or both, in the places you name: average monthly searches, competition and top-of-page bid range. Pro/Max, 2 credits (a repeat within 90 days is free)
list_google_ads_accounts
Every connected Google Ads account, switched on or not, with the manager account (MCC) each client account sits under
list_google_recommendations
Google's own recommendations for an account (its Recommendations page), with Google's estimate and whether each can be applied from the chat
AI visibility for your brand: which buyer questions name you in ChatGPT, Perplexity, Claude and Google AI Overviews, which competitors AI recommends instead, which sources it cites, and what to fix. Remote server with OAuth sign-in.
Manage Google Ads from Claude: read metrics, draft campaigns, publish with human approval.