threads-mcp: Instructions file for Codex

AGENTS.md

threads-mcp AGENTS.md is an instructions file for Codex, OpenCode from ramadhanidiwanda-alt/threads-mcp. It costs 512 tokens per session, scanned A, original, MIT.

A repository instruction file for a Threads comment-research server. Meta's Threads is a social platform, and an MCP server lets compatible AI clients call its tools.

In plain words
What is it for?
Use it when working on tools that retrieve Threads posts, replies, conversations, searches, or comments through Meta's API.
Why use it?
It explains the project's structure and conventions so an agent can modify, build, test, and deploy the server consistently.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is ramadhanidiwanda-alt/threads-mcp's own configuration. It tells Codex and OpenCode how to work on threads-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything threads-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ramadhanidiwanda-alt/threads-mcp. 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/ramadhanidiwanda-alt/threads-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ramadhanidiwanda-alt/threads-mcp

Made for: Codex, OpenCode.

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.

agentmods badge for threads-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ramadhanidiwanda-alt/threads-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ramadhanidiwanda-alt/threads-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ramadhanidiwanda-alt/threads-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ramadhanidiwanda-alt/threads-mcp/agents-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.

agentmods 80×15 button for threads-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ramadhanidiwanda-alt/threads-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ramadhanidiwanda-alt/threads-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 512 This file is loaded in full into every session.
When invoked 512 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00512 $0.00512
Opus 5.5 $0.00205 $0.00205
Sonnet 5.5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 2mo ago against content hash ce5f485e0d1e, 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 AGENTS.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.

AGENTS.md · 71 lines

What it actually says

AGENTS.md — threads-mcp

Project Overview

Threads comment research MCP server. AI agents use its tools to discover public sentiment, frustrations, and conversations on Meta's Threads platform. Built as a lightweight, stateless MCP server — deploy once, consume from any MCP-compatible client.

Tech Stack

  • Runtime: Node.js 22 (ESM, TypeScript)
  • Framework: @modelcontextprotocol/sdk (stdio transport)
  • Validation: zod
  • API: Meta Threads Graph API (graph.threads.net/v1.0)
  • Build: TypeScript to dist/
  • Deploy: Docker (node:22-alpine, multi-stage)

Architecture

MCP Client → stdio → threads-mcp → HTTP → Meta Threads Graph API

Pattern: each tool in src/tools/ exports { schema, handler }. Server in src/index.ts auto-registers all tools.

File Structure

src/
├── index.ts          — MCP server entry point
├── tools/            — 5 tool files
│   ├── getPost.ts
│   ├── getReplies.ts
│   ├── getConversation.ts
│   ├── searchThreads.ts
│   └── searchComments.ts
└── utils/
    ├── api.ts        — Threads API client
    └── types.ts      — shared types
tests/
Dockerfile + docker-compose.yml
package.json + tsconfig.json
.env.example
PRD.md, AGENTS.md, README.md, LICENSE

Code Style

  • TypeScript strict mode, ESM
  • Named exports only (no default exports)
  • Tool files export schema and handler
  • Async/await, error responses return isError: true
  • Clean JSON output — flat, minimal fields

Development

  • npm run dev — hot-reload with tsx
  • npm run build — compile to dist/
  • Add tool: create src/tools/yourTool.ts, register in src/index.ts
  • npm test — Vitest tests in tests/

Build and Deploy

npm run build
docker compose up

API Rate Limits

  • General: 4,800 x impressions per 24h
  • Keyword search: 2,200 queries per 24h per user
  • Sensitive keywords return empty array
  • Paginated results — use cursor for full data
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.

  1. 2mo ago First seen · 71 lines · 512 tokens per session scan A ce5f485e0d1e

Subscribe to this mod's changes

threads-mcp AGENTS.md is an instructions file published in the GitHub repository ramadhanidiwanda-alt/threads-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 512 tokens to every session, about $0.0020 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.

Related

threads-mcp AGENTS.md compared with instructions from other repositories

threads-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
threads-mcp AGENTS.mdramadhanidiwanda-alt/threads-mcpInstructions file01mo agoMITA512Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode