Skip to content
Back to search

creator-mcp-server

Creator MCP Server — give Claude Code, Cursor and other AI assistants creator tools: outlier research, repurposing, titles, SEO and GEO checks.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked yesterday
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/mrabr381--creator-mcp-server/badge.svg)](/listings/mrabr381--creator-mcp-server)

HTML

<a href="/listings/mrabr381--creator-mcp-server"><img src="/api/listings/mrabr381--creator-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

claude mcp add creator-mcp-server \
  -- /path/to/creator-mcp-server/.venv/bin/python -m creator_mcp

No 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`](config/claude_code.md)). Verify with `claude mcp list`.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 104 lines
  1. # Creator MCP Server 🔌
  2. [![CI](https://github.com/mrabr381/creator-mcp-server/actions/workflows/ci.yml/badge.svg)](https://github.com/mrabr381/creator-mcp-server/actions/workflows/ci.yml)
  3. [![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org)
  4. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
  5. [![MCP SDK v2](https://img.shields.io/badge/MCP-SDK%20v2-purple.svg)](https://modelcontextprotocol.io)
  6. [![No API key required](https://img.shields.io/badge/API%20key-not%20required-brightgreen.svg)](#sample-mode--no-key-needed)
  7. ![Creator MCP Server — give your AI assistant five real creator tools, no guessing](assets/hero.svg)
  8. **Give your AI assistant five real creator tools — 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.
  9. ## Install in one command
  10. ```bash
  11. claude mcp add creator-mcp-server \
  12. -- /path/to/creator-mcp-server/.venv/bin/python -m creator_mcp
  13. ```
  14. No 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`](config/claude_code.md)). Verify with `claude mcp list`.
  15. ## 30 seconds, real output
  16. The smoke test talks to the server over the real MCP protocol — this is its actual output:
  17. ```text
  18. == youtube_outlier_search (sample) ==
  19. PASS outlier search ok
  20. PASS outlier mode is sample
  21. PASS median views 12850
  22. PASS 5 outliers
  23. PASS top outlier is Tower of London's Lost Princes
  24. PASS top outlier score 4.86
  25. PASS top outlier velocity matches views/days-since-publish
  26. PASS sample note present
  27. ...
  28. 51 passed, 0 failed. ALL CHECKS PASSED
  29. ```
  30. Ask 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 — What Really Happened?"* at **4.86×**, plus 5 scored titles (e.g. *"The Lost Princes Mystery, Finally Solved?"* — **84/100**). Full tool-call transcript: [`sample_output/smoke_transcript.json`](sample_output/smoke_transcript.json).
  31. ## The 5 tools
  32. | Tool | What it does | Needs a key? |
  33. | --- | --- | --- |
  34. | `youtube_outlier_search` | A channel's outlier videos: views vs median, velocity, keyword lift, gap words, title bigrams | No — sample mode |
  35. | `repurpose_transcript` | One transcript → blog post, X thread, LinkedIn post, newsletter, chapters, pull quotes | No — extractive, local only |
  36. | `title_ideas` | Scored YouTube title ideas (deterministic 0–100 scoring, formula documented) | No |
  37. | `seo_audit_page` | One page audited: title, meta, H1, canonical, Open Graph, alt text, word count, JSON-LD, `llms.txt` — 0–100 + fix list | No |
  38. | `geo_brand_check` | How often AI answers mention a brand across 10 prompts | No — sample mode |
  39. Every tool returns a JSON string. Failures come back as `{"ok": false, "error": "..."}` — never a traceback over the protocol.
  40. ## Sample mode — no key needed
  41. Without a key, two tools still work on bundled fixtures and **every sample result says so**:
  42. - `youtube_outlier_search` analyses the fixture channel **Mystery Lane** (`@mysterylane`, 24 videos), labelled `"mode": "sample"`. Median **12,850** views, **5 outliers**, top outlier **4.86×** — the same numbers the [Open-vidIQ](https://github.com/mrabr381/open-vidiq) project verified for this dataset.
  43. - `geo_brand_check` checks 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.
  44. Free keys (both $0): **YouTube Data API v3** (10,000 units/day) at <https://console.cloud.google.com/apis/library/youtube.googleapis.com> → `YOUTUBE_API_KEY`; **Gemini API** (free tier) at <https://aistudio.google.com/apikey> → `GEMINI_API_KEY`.
  45. ## Quickstart
  46. ```bash
  47. git clone https://github.com/mrabr381/creator-mcp-server.git
  48. cd creator-mcp-server
  49. python -m venv .venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
  50. pip install -r requirements.txt
  51. python -m creator_mcp # stdio (Claude Desktop / Code)
  52. python -m creator_mcp --transport streamable-http --port 8000 # or over HTTP
  53. python scripts/smoke_test.py # 51 passed, 0 failed
  54. ```
  55. **Claude Desktop** — full file in [`config/claude_desktop_config.json`](config/claude_desktop_config.json) (command = your checkout's `.venv/bin/python -m creator_mcp`, keys empty for sample mode). **Cursor** — entry from [`config/cursor.md`](config/cursor.md) in `.cursor/mcp.json`; confirm 5 tools in Settings → MCP. The analysis logic is copied into this repo from the sibling projects, so the server runs standalone.
  56. ## Honest limitations
  57. - **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.
  58. - **Live Gemini calls were not testable in the build sandbox** (it blocks `generativelanguage.googleapis.com` — the call fails cleanly with a clear error), and live GEO answers vary run to run — one call per prompt is a snapshot, not a stable metric.
  59. - **Repurposing is extractive, not written** — 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".
  60. - **SEO audit is one page, no JavaScript.** For a full-site crawl use the [SEO + GEO Site Audit CLI](https://github.com/mrabr381/seo-geo-audit-cli).
  61. ## Tests
  62. ```bash
  63. pip install pytest
  64. python -m pytest # outlier maths: median 12850, top 4.86x, gap words
  65. python scripts/smoke_test.py # real MCP protocol test: 51 checks
  66. ```
  67. CI runs both on every push (see the badge at the top).
  68. ```
  69. creator-mcp-server/
  70. ├── creator_mcp/ # server.py + 5 tool modules (outliers, youtube, repurpose, titles, seo, geo)
  71. ├── sample_data/ # fixtures: channel + videos, transcript, prompts + answers, test page
  72. ├── sample_output/ # smoke_transcript.json — real tool-call results
  73. ├── scripts/smoke_test.py # MCP protocol-level test (51 checks)
  74. └── config/ # Claude Desktop / Claude Code / Cursor setup
  75. ```
  76. MIT — see [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.