What is substack_mcp CLAUDE.md?

A CLAUDE.md guide for an MCP server that reads public Substack content. MCP is a standard way for AI assistants to use external tools and data.

Running the project, testing its MCP server, reading Substack posts and profiles, and producing sentiment, readability, keyword, and other content analysis.

It collects the project's setup, testing, architecture, parsing, caching, and analysis instructions in one place. This makes development and server testing more consistent.

substack_mcp CLAUDE.md — Instructions file for Claude Code by dkyazzentwatwa: A CLAUDE.md guide for an MCP server that reads…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/dkyazzentwatwa/substack_mcp/claude-md

Clone the repo

git clone --depth 1 https://github.com/dkyazzentwatwa/substack_mcp

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/dkyazzentwatwa/substack_mcp/claude-md.svg)](https://agentmods.dev/instructions/dkyazzentwatwa/substack_mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dkyazzentwatwa/substack_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dkyazzentwatwa/substack_mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,328 This file is loaded in full into every session.

When invoked 2,328 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.02328	$0.02328
Opus 5	$0.01164	$0.01164
Sonnet 5	$0.00466	$0.00466
Haiku 4.5	$0.00233	$0.00233

Measured 5d ago against content hash a5e134c7d247, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

substack_mcp 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 5d 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 · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

# Environment setup
python3 -m venv .venv
source .venv/bin/activate
pip install -e .[dev]

# Testing
pytest                              # Run all tests
pytest tests/test_analysis.py       # Specific test module
pytest -v                           # Verbose output

# Testing the MCP server
./run_mcp_with_venv.sh             # Run MCP server for Claude Desktop

Architecture Overview

This is a Substack MCP (Model Context Protocol) Server designed for use with Claude Code. It scrapes public Substack content and provides analytics through the MCP protocol.

Core Components

SubstackPublicClient (client.py) - HTTP wrapper with rate limiting (1 second throttle) and TTL caching (15 minutes)
Data Models (models.py) - Pydantic schemas: PostSummary, PostContent, AuthorProfile, Note, ContentAnalytics
Content Parsers (parsers.py) - RSS/Atom feed parsing and HTML content extraction using BeautifulSoup
Analytics Engine (analysis.py) - VADER sentiment analysis, Flesch Reading Ease, keyword extraction (TF-IDF), publishing cadence
MCP Server (server.py) - MCP protocol implementation using stdio transport

MCP Protocol Integration

The server implements the MCP protocol for Claude Desktop/Code integration:

MCP Tools Available:

search - Basic search across publications
get_posts - Fetch recent posts from a publication (limited to ~20)
get_all_posts - NEW: Fetch ALL posts from publication archive with date filtering
search_substack - Intelligent search with auto-discovery of relevant publications
get_content - Smart content retrieval (URLs, publication names, handles)
discover_publications - Discover publications by topic/industry
analyze_trends - Analyze content trends and publishing patterns
get_post_content - Full content of specific posts
analyze_post - Sentiment and readability analysis
get_author_profile - Get author and publication information
get_notes - Fetch recent notes from a publication
search_notes - Search notes by text content
crawl_publication - Comprehensive publication intelligence

Read the full file on GitHub · 266 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.

5d ago First seen · 266 lines · 2,328 tokens per session scan A a5e134c7d247

Subscribe to this mod's changes

substack_mcp CLAUDE.md is an instructions file published in the GitHub repository dkyazzentwatwa/substack_mcp (13 stars, last pushed 8mo ago), licensed MIT. It adds 2,328 tokens to every session, about $0.0116 per session on Opus 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 2026-08-30.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

substack_mcp CLAUDE.md