Pantheon MCP Server

by pantheon Your server? Claim it

answering

Pantheon is answering right now. Last checked 9 min ago. It exposes 23 tools.

Meta ads library, competitor ads, brand voice, avatars and offer briefs from your Pantheon account.

Uptime history 5 days of history

5 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

393 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 7

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 6 November 2026. No other catalogue keeps this.

6 Nov 5 tool descriptions were rewritten get_creative_analysis, get_strategic_avatar, run_magic_tool and 2 more

6 Nov 2 tools changed the parameters they ask for get_job_status, run_magic_tool

Nothing serious here today

Today is the operative word: we check Pantheon every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp --transport http https://mcp.pantheon.ad/mcp

Settings → Connectors → Add custom connector, then paste this address

https://mcp.pantheon.ad/mcp

~/.codex/config.toml

[mcp_servers.mcp]
url = "https://mcp.pantheon.ad/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.pantheon.ad/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.pantheon.ad/mcp"
    }
  }
}

Available tools 23

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

brand

create_brand_voice

Create and save a Brand Voice from a public URL or a text (uses 1 Brand Voice credit, ~1 minute).

list_brand_voices

List the user's Brand Voices (id, name).

run_brand_campaign_analysis

Scrape and analyze the user's own brand Meta campaigns page (uses 1 Brand Campaigns credit). Runs in background: poll get_job_status with the returned id.

competitor

get_competitor_active_ads

Active ads of a competitor the user has analyzed with Competitor Spy.

run_competitor_spy

Scrape and analyze all ads of a competitor's Facebook page (uses 1 Competitor Spy credit). Runs in background: poll get_job_status with the returned id.

offer

create_offer_brief

Create and save an Offer Brief from a public sales page URL or a text (uses 1 Offer Brief credit, ~1 minute).

list_offer_briefs

List the user's Offer Briefs (id, name).

active

get_active_ads_copy

Copy (body, caption, CTA) of currently active ads of the monitored creators.

ads

search_ads_library

Search the user's own Ads Library (ads collected by their searches) and this week's Top Ads by brand, niche, sector or copy. Returns ad ids usable with analyze_ad and run_ad_copilot.

analyze

analyze_ad

Ads Intelligence: full AI analysis of one ad (emotional levers, biases, landing page coherence). Uses 1 Ads Intelligence credit. Runs in background: poll get_job_status with the returned id.

analyzed

list_analyzed_pages

List Facebook pages the user analyzed (competitor, inspiration or brand_campaigns), with status and ad counts.

copilot

run_ad_copilot

Adapt a library ad into 3 copy variants for the user's Avatar, Offer Brief and Brand Voice (uses 1 Ad Copilot credit). Runs in background: poll get_job_status with the returned id.

creative

get_creative_analysis

Saved AI analysis of an ad (awareness, hooks, mechanism, triggers, landing page coherence), if analyze_ad was run on it.

inspiration

run_inspiration_search

Scrape and analyze a page outside the user's niche for inspiration (uses 1 Inspiration Search credit). Runs in background: poll get_job_status with the returned id.

job

get_job_status

Status and results of a background job started by an action tool.

magic

run_magic_tool

Summarize, translate or extract contacts/links from a text (Magic Tools). Summaries and extractions are in the language of the text; translations go to `language` (default Italiano).

market

get_market_creators_data

Aggregated stats of the creators/competitors the user monitors.

persuasion

run_persuasion_analysis

Persuasion analysis of an ad before launch: present and missing cognitive biases (uses 1 Persuasion Analysis credit). Runs in background: poll get_job_status with the returned id.

projects

list_projects

List the user's strategic projects (Avatar analyses) with their ids.

sales

run_sales_psychology

Sales Psychology report for a project's Avatar + an Offer Brief (uses 1 Sales Psychology credit). Runs in background: poll get_job_status with the returned id.

saved

get_saved_ads

The user's swipe file, optionally filtered by competitor name.

strategic

get_strategic_avatar

Avatar research of a project (from list_projects): pain matrix, core wound, desire chain, objections, triggers, language and strategic synthesis.

top

get_top_performing_ads

Top performing (longest running) ads of the monitored creators.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.pantheon.ad/mcp	streamable-http	answering	389 ms	9 min ago

Alternatives to Pantheon

same job, measured the same way

Ad Library Intelligence

by benthepythondev00

Competitor ads from the Meta, Google and LinkedIn ad libraries plus ads.txt sellers. No login.

answering

Atria

by tryatria

Search Atria's ad library, track competitors, and analyze your Facebook and TikTok ad accounts.

answering

DataDive

by datadive

Amazon niche, keyword, competitor and Rank Radar research from your DataDive account.

answering

AYA

by aya

AYA command library as MCP tools: run AYA patterns and commands under your own account.

answering

TrueScrape

by truescrape

Live context for your agent: competitors, mentions and markets, from public data.

1 415 installs/wk 271 tools answering

SharpSyn (your account)

by sharpsyn

Your SharpSyn account: quote requests and answers, price history, library; RFQs on confirm.

answering

AdRadar

by egggy1998

Competitor ad research for AI agents: Meta Ad Library and TikTok ads, scored by hook and angle.

4 tools answering

Mobilna Faktura

by mobilna-faktura

Invoicing, costs, KPiR, VAT and KSeF data from your Mobilna Faktura account (Poland).

answering

Pantheon — questions

Answers built from our own checks of this server.

What can Pantheon do?

It exposes 23 tools, read directly from the server on our last check. Among them: analyze_ad, create_brand_voice, create_offer_brief, get_active_ads_copy, get_competitor_active_ads, get_creative_analysis and 17 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is Pantheon mostly used for?

Its tools cluster around brand, offer and competitor. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is Pantheon working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 393 ms. The bar chart above shows every period we have measured.

How do I connect Pantheon?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Pantheon need an API key?

No. Pantheon completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 23 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Pantheon?

It answers our handshake in 393 ms on average, which is faster than 33% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.