What is mcp-content-pipeline CLAUDE.md?

Project instructions for an MCP server that analyses YouTube videos and content, with optional connections to X and GitHub. MCP is a way for AI tools to call outside services.

Use it to install dependencies, run tests, start the server, configure service access, and understand where tools, API clients, and data models live.

It gives a coding agent the project’s setup, structure, required keys, and testing commands, so work follows the repository’s documented rules.

How berkayildi/mcp-content-pipeline configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to berkayildi/mcp-content-pipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/berkayildi/mcp-content-pipeline/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/berkayildi/mcp-content-pipeline

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/berkayildi/mcp-content-pipeline/claude-md/github.svg)](https://agentmods.dev/instructions/berkayildi/mcp-content-pipeline/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/berkayildi/mcp-content-pipeline/claude-md"><img src="https://agentmods.dev/badge/instructions/berkayildi/mcp-content-pipeline/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/berkayildi/mcp-content-pipeline/claude-md"><img src="https://agentmods.dev/badge/instructions/berkayildi/mcp-content-pipeline/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 832 This file is loaded in full into every session.

When invoked 832 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00832	$0.00832
Opus 5.5	$0.00333	$0.00333
Sonnet 5.5	$0.00166	$0.00166
Haiku 4.5	$0.00083	$0.00083

Measured 13d ago against content hash f701e16d7da4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-content-pipeline CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-content-pipeline

YouTube video analysis and X feed digest pipeline exposed as MCP tools, synced to GitHub.

Quick Start

uv sync
uv run pytest
uv run mcp-content-pipeline

Architecture

src/mcp_content_pipeline/server.py — MCP server entry point, registers all tools
src/mcp_content_pipeline/tools/ — one file per MCP tool
src/mcp_content_pipeline/config.py — Settings (pydantic-settings, MCP_CP_ prefix)
src/mcp_content_pipeline/services/ — API clients (LLM driver, YouTube transcripts, X, GitHub)
src/mcp_content_pipeline/models/ — Pydantic schemas

Environment Variables

All prefixed with MCP_CP_ and kept in a local .env (gitignored; template in .env.example) — not in MCP client config. server.main() loads MCP_CP_ENV_FILE if set, otherwise the nearest .env from the working directory upwards; real environment variables win over .env. When adding a setting, update config.py, .env.example, this file and the README tables together.

Pipeline driver — required for analyse_video, analyse_x_feed:

PIPELINE_PROVIDER — anthropic | openai (default: anthropic). See services/llm_client.py.
PIPELINE_API_KEY — API key for the selected provider
PIPELINE_MODEL — model name valid for the selected provider (default: claude-sonnet-4-6)

YouTube — transcripts come from public English captions via services/transcript.py, no key needed:

MAX_TRANSCRIPT_TOKENS — optional (default: 100000)

GitHub — required for sync_to_github:

GITHUB_TOKEN
GITHUB_REPO — format: "owner/repo"
GITHUB_BRANCH — optional (default: main)
GITHUB_OUTPUT_DIR — optional (default: content/youtube)
GITHUB_X_OUTPUT_DIR — optional (default: content/x-digest)

X/Twitter — required for analyse_x_feed:

X_BEARER_TOKEN
X_ACCOUNTS — comma-separated default usernames (required unless usernames is passed)
X_TOPICS — optional (default: AI,tech)

Testing

uv run pytest -v --cov=src/mcp_content_pipeline
uv run ruff check src/ tests/

Read the full file on GitHub · 68 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

13d ago Changed · -17 lines · -91 tokens per session f701e16d7da4
1mo ago Changed · +11 lines · +186 tokens per session 55b38f06d19d
2mo ago First seen · 74 lines · 737 tokens per session scan A 27f9a1032078

Subscribe to this mod's changes

mcp-content-pipeline CLAUDE.md is an instructions file published in the GitHub repository berkayildi/mcp-content-pipeline (0 stars, last pushed 13d ago), licensed MIT. It adds 832 tokens to every session, about $0.0033 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents OpenAI API Research anthropic-api google-api mcp x-api youtube-api

mcp-content-pipeline CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-content-pipeline CLAUDE.mdberkayildi/mcp-content-pipeline	Instructions file	0	13d ago	MIT	A	832	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-content-pipeline: Instructions file for Claude Code