Creator MCP Server
Integrates with Google's Gemini API to check how often AI-generated answers mention a brand across prompts for GEO brand visibility, using live Gemini calls when a key is configured and sample fixtures otherwise.
Integrates with the YouTube Data API v3 to research a channel's outlier videos, including views versus channel median, velocity, keyword lift, gap words, and title bigrams; without a key it analyzes a bundled sample channel.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Creator MCP Server š
Give your AI assistant five real creator tools ā no guessing, no invented numbers. YouTube outlier research, transcript repurposing, title ideas, single-page SEO + GEO audit, and AI-search brand checks, as one MCP server for Claude Code, Claude Desktop, Cursor or Codex. Every number comes from a real API response, a real page fetch, or a clearly labelled sample fixture.
Install in one command
claude mcp add creator-mcp-server \
-- /path/to/creator-mcp-server/.venv/bin/python -m creator_mcpNo API key needed to start (sample mode, below). With free keys, add -e YOUTUBE_API_KEY=... -e GEMINI_API_KEY=... before the -- (full form in config/claude_code.md). Verify with claude mcp list.
Related MCP server: Marketing MCP Server
30 seconds, real output
The smoke test talks to the server over the real MCP protocol ā this is its actual output:
== youtube_outlier_search (sample) ==
PASS outlier search ok
PASS outlier mode is sample
PASS median views 12850
PASS 5 outliers
PASS top outlier is Tower of London's Lost Princes
PASS top outlier score 4.86
PASS top outlier velocity matches views/days-since-publish
PASS sample note present
...
51 passed, 0 failed. ALL CHECKS PASSEDAsk your assistant (sample mode, no keys): "Find the outliers for @mysterylane and suggest 5 titles for the top topic." It returns median 12,850 views, top outlier "The Tower of London's Lost Princes ā What Really Happened?" at 4.86Ć, plus 5 scored titles (e.g. "The Lost Princes Mystery, Finally Solved?" ā 84/100). Full tool-call transcript: sample_output/smoke_transcript.json.
The 5 tools
Tool | What it does | Needs a key? |
| A channel's outlier videos: views vs median, velocity, keyword lift, gap words, title bigrams | No ā sample mode |
| One transcript ā blog post, X thread, LinkedIn post, newsletter, chapters, pull quotes | No ā extractive, local only |
| Scored YouTube title ideas (deterministic 0ā100 scoring, formula documented) | No |
| One page audited: title, meta, H1, canonical, Open Graph, alt text, word count, JSON-LD, | No |
| How often AI answers mention a brand across 10 prompts | No ā sample mode |
Every tool returns a JSON string. Failures come back as {"ok": false, "error": "..."} ā never a traceback over the protocol.
Sample mode ā no key needed
Without a key, two tools still work on bundled fixtures and every sample result says so:
youtube_outlier_searchanalyses the fixture channel Mystery Lane (@mysterylane, 24 videos), labelled"mode": "sample". Median 12,850 views, 5 outliers, top outlier 4.86Ć ā the same numbers the Open-vidIQ project verified for this dataset.geo_brand_checkchecks fixture answers for toolenix.com: 4 mentions in 10 prompts = 40.0%. Any other brand without a key is an error, not a fabricated result.
Free keys (both $0): YouTube Data API v3 (10,000 units/day) at https://console.cloud.google.com/apis/library/youtube.googleapis.com ā YOUTUBE_API_KEY; Gemini API (free tier) at https://aistudio.google.com/apikey ā GEMINI_API_KEY.
Quickstart
git clone https://github.com/mrabr381/creator-mcp-server.git
cd creator-mcp-server
python -m venv .venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
python -m creator_mcp # stdio (Claude Desktop / Code)
python -m creator_mcp --transport streamable-http --port 8000 # or over HTTP
python scripts/smoke_test.py # 51 passed, 0 failedClaude Desktop ā full file in config/claude_desktop_config.json (command = your checkout's .venv/bin/python -m creator_mcp, keys empty for sample mode). Cursor ā entry from config/cursor.md in .cursor/mcp.json; confirm 5 tools in Settings ā MCP. The analysis logic is copied into this repo from the sibling projects, so the server runs standalone.
Honest limitations
Sample mode is a fixture, not your channel. Without a YouTube key you always get Mystery Lane; without a Gemini key you always get Toolenix. Check
"mode"in the response.Live Gemini calls were not testable in the build sandbox (it blocks
generativelanguage.googleapis.comā the call fails cleanly with a clear error), and live GEO answers vary run to run ā one call per prompt is a snapshot, not a stable metric.Repurposing is extractive, not written ā the blog/newsletter reuse your own sentences. Deliberate (it cannot invent), but it reads like a draft. Title scores likewise reward a formula (length, hook words, questions, numbers, keywords): high score = "follows proven patterns", not "will go viral".
SEO audit is one page, no JavaScript. For a full-site crawl use the SEO + GEO Site Audit CLI.
Tests
pip install pytest
python -m pytest # outlier maths: median 12850, top 4.86x, gap words
python scripts/smoke_test.py # real MCP protocol test: 51 checksCI runs both on every push (see the badge at the top).
creator-mcp-server/
āāā creator_mcp/ # server.py + 5 tool modules (outliers, youtube, repurpose, titles, seo, geo)
āāā sample_data/ # fixtures: channel + videos, transcript, prompts + answers, test page
āāā sample_output/ # smoke_transcript.json ā real tool-call results
āāā scripts/smoke_test.py # MCP protocol-level test (51 checks)
āāā config/ # Claude Desktop / Claude Code / Cursor setupMIT ā see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP for marketers that gives agents tools for SEO, AEO, socials and ads data. Generous free tier; works in Claude, ChatGPT, Cursor and other MCP clients.
Open-source AI SEO over MCP: audits, ranks, keywords, backlinks + AI visibility (GEO).
100+ MCP tools for AI agents: content metadata, trade intelligence, business-expertise analysis.
5 pay-per-call SEO tools over MCP. Free discovery, tool calls settle in USDC on Base via x402.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAI search intelligence + Ahrefs-class SEO suite as 59 MCP tools. Track your brand across ChatGPT, Google AI Overview, Gemini, Claude, and Perplexity with persona-anchored Brand Radar dispatches.MIT
- FlicenseBqualityDmaintenanceCentralizes 10 marketing APIs into 14 MCP tools for AI assistants to pull data, audit sites, research trends, and manage Google Drive without switching tabs.35-
- AlicenseAqualityBmaintenanceChecks what GPTBot, ClaudeBot, PerplexityBot and 50+ other AI crawlers can read on a site and what its access policy allows, checks whether a page permits search, answers, training or agent use (with a signed receipt), generates llms.txt, robots.txt and JSON-LD, and reads your Answer Analysis. Nine tools for Claude Desktop, Cursor and other MCP clients.9168 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to perform live Google SERP searches, run on-page and full-site SEO audits with prioritized fixes, and check brand visibility in AI answer engines via four MCP tools.MIT