Meta Ads MCP vs Proofsource

A side-by-side look at the Meta Ads MCP and Proofsource MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Meta Ads MCP logoMeta Ads MCPMarketing · Local subprocess (stdio)MCP server for Meta Marketing API v25.0 — 123 tools for Facebook & Instagram ad campaigns, audiences, creatives, insights, catalogs, and automated rules.68GreatAuth: api key requiredProofsource logoProofsourceMarketing · Remote HTTP/SSEAI 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.68GreatAuth: oauth 2.0

Verdict: choose Meta Ads MCP for marketing work as a local process; choose Proofsource for marketing over a hosted endpoint. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Meta Ads MCP logoChoose Meta Ads MCP when

  • You need dedicated capabilities in the Marketing domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: API key required.
  • You have the keys it needs: META_ADS_ACCESS_TOKEN, META_AD_ACCOUNT_ID.
  • You want tools like list_campaigns, get_campaign, create_campaign.
Explore Meta Ads MCP

Proofsource logoChoose Proofsource when

  • You need dedicated capabilities in the Marketing domain.
  • You prefer a remote HTTP/SSE transport.
  • Its auth model fits you: OAuth 2.0.
  • You want tools like list_brands, list_topics, get_visibility.
Explore Proofsource

Feature & specification comparison

Rows where the two servers differ are marked.

SpecMeta Ads MCP logoMeta Ads MCPProofsource logoProofsource
CategoryMarketingMarketing
Quality signal68/100 · Great68/100 · Great
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Remote HTTP/SSE
AuthAPI key requiredOAuth 2.0
PricingBYOK (pay the provider)Freemium
Required env varsMETA_ADS_ACCESS_TOKENMETA_AD_ACCOUNT_IDNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars910
Directory activity 2 views 0 installs 0 upvotes 2 views 0 installs 0 upvotes
Tools13414

Tools & capabilities

Meta Ads MCP tools 134

  • list_campaignsList campaigns in the ad account. Supports filtering by status and objective. Returns paginated results.
  • get_campaignGet details of a specific campaign by ID.
  • create_campaignCreate a new ad campaign. Defaults to PAUSED status. Requires name and objective. Budget can be set at campaign or ad set level.
  • update_campaignUpdate an existing campaign. Only provided fields will be modified.
  • delete_campaignDelete a campaign. This action is irreversible.
  • copy_campaignCopy an existing campaign. Creates a duplicate with optional name override. Copies structure including ad sets and ads.
  • get_campaign_adsetsGet all ad sets belonging to a specific campaign.
  • get_campaign_adsGet all ads belonging to a specific campaign.
  • get_campaign_leadsGet leads generated by a specific campaign. Requires leads_retrieval permission.
  • list_adsetsList ad sets in the ad account. Optionally filter by campaign or status.
  • get_adsetGet details of a specific ad set by ID.
  • create_adsetCreate a new ad set. Requires name, campaign_id, budget, optimization_goal, billing_event, and targeting. Defaults to PAUSED status.
  • +122 more on the listing page

Proofsource tools 14

  • list_brandsThe brands this workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.
  • list_topicsThe topics and buyer questions this workspace asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt needs.
  • get_visibilityHow 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_competitorsThe 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_citationsThe 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.
  • get_changesWhat 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_opportunitiesThe 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_verificationEach 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_promptAdds a buyer question to a topic so it is asked 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_shippedRecords 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_brandStart 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). It 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_statusProgress 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 on the listing page

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Meta Ads MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "mikusnuz-meta-ads-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@mikusnuz/meta-ads-mcp"
      ],
      "env": {
        "META_ADS_ACCESS_TOKEN": "YOUR_META_ADS_ACCESS_TOKEN_HERE",
        "META_AD_ACCOUNT_ID": "YOUR_META_AD_ACCOUNT_ID_HERE"
      }
    }
  }
}

Proofsource

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "proofsource": {
      "command": "npx",
      "args": [
        "-y",
        "proofsource"
      ]
    }
  }
}

Frequently asked questions

Meta Ads MCP is categorized under Marketing and uses a local stdio subprocess. Proofsource belongs to Marketing and uses a remote HTTP/SSE transport. Pick Meta Ads MCP for marketing work and Proofsource for marketing.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Meta Ads MCP is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. Proofsource is listed as freemium — a free tier with paid plans. Auth: oauth 2.0. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add mikusnuz-meta-ads-mcp and proofsource as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Meta Ads MCP has a quality signal of 68/100 (Great) with 2 views, 0 installs and 91 GitHub stars. Proofsource has 68/100 (Great) with 2 views, 0 installs and 0 GitHub stars.