What is threads-mcp-crawler CLAUDE.md?

Project instructions for developing a Threads scraper MCP, which collects information from the Threads social network for an AI agent. They describe its architecture, parsing, caching, throttling, and sentiment analysis.

Use them when changing the Threads scraper, its browser automation, parsers, selectors, settings, or caching.

They explain the project's design choices and important implementation details, helping developers preserve reliable and considerate scraping behavior.

How dkyazzentwatwa/threads-mcp-crawler configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dkyazzentwatwa/threads-mcp-crawler. 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/dkyazzentwatwa/threads-mcp-crawler/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dkyazzentwatwa/threads-mcp-crawler

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/threads-mcp-crawler/claude-md/github.svg)](https://agentmods.dev/instructions/dkyazzentwatwa/threads-mcp-crawler/claude-md)

Your own site

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

Per session 4,049 This file is loaded in full into every session.

When invoked 4,049 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	$0.04049	$0.04049
Opus 5.5	$0.01620	$0.01620
Sonnet 5.5	$0.00810	$0.00810
Haiku 4.5	$0.00405	$0.00405

Measured 2mo ago against content hash 81d8f77cbe0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

threads-mcp-crawler 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 2mo 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 · 568 lines

How it starts

The opening of the file, as written. The whole thing — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threads Scraper MCP - Developer Guide

Internal documentation for developers working on threads_scraper_mcp.

Architecture Overview

Design Philosophy

Robustness over cleverness: Dual parsing (JSON + HTML) ensures resilience
Centralized selectors: All CSS selectors in one ThreadsSelectors class
Graceful degradation: Return partial data rather than failing completely
Ethical scraping: Built-in throttling and caching, no circumvention attempts
Proven patterns: Architecture mirrors successful substack_mcp implementation

Tech Stack

Python 3.9+: Modern type hints (| union, Optional, generics)
Pydantic v2: Type-safe data validation
Playwright: Headless Chrome browser automation (bypasses login wall)
BeautifulSoup + lxml: HTML parsing (fallback)
VADER: Sentiment analysis for social media
MCP SDK: Model Context Protocol for AI integration
cachetools: Thread-safe TTL caching

Module Responsibilities

`settings.py`

Environment-based configuration via @dataclass
RuntimeSettings.from_env() factory pattern
Global SETTINGS instance
Env vars: THREADS_THROTTLE, THREADS_CACHE_TTL, THREADS_SESSION_COOKIE, etc.

`cache.py`

Copied verbatim from substack_mcp (proven implementation)
Thread-safe TTLCache with RLock
@cached decorator for function memoization
clear_cache(prefix) for selective invalidation
256-item limit, 10-minute TTL default

`models.py`

Pydantic v2 models for type safety
Core models: Profile, Thread, Reply, EngagementMetrics
Analytics models: SentimentBreakdown, KeywordScore, ProfileAnalytics
All fields use Optional for graceful degradation
raw: Dict[str, Any] field preserves original data for debugging

`parsers.py`

CRITICAL FILE: Most likely to need updates when Threads changes HTML
ThreadsSelectors class: Centralized CSS selectors
Dual parsing system:
1. Primary: JSON from __NEXT_DATA__ script tag
2. Fallback: HTML selectors
Helper functions: _extract_next_data(), _parse_datetime(), _parse_engagement_from_json(), etc.
Main parsers: parse_profile(), parse_thread(), parse_profile_threads(), parse_replies(), parse_search_results()

Read the full file on GitHub · 568 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.

2mo ago First seen · 568 lines · 4,049 tokens per session scan A 81d8f77cbe0b

Subscribe to this mod's changes

threads-mcp-crawler CLAUDE.md is an instructions file published in the GitHub repository dkyazzentwatwa/threads-mcp-crawler (10 stars, last pushed 9mo ago), licensed MIT. It adds 4,049 tokens to every session, about $0.0162 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.

automation crawler mcp social-media

threads-mcp-crawler CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
threads-mcp-crawler CLAUDE.mddkyazzentwatwa/threads-mcp-crawler	Instructions file	10	9mo ago	MIT	A	4,049	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

threads-mcp-crawler: Instructions file for Claude Code