x-mcp AGENTS.md

x-mcp AGENTS.md is an instructions file for Codex, OpenCode from kandotrun/x-mcp. It costs 313 tokens per session, scanned A, original, MIT.

Repository instructions for x-mcp, a read-only server that lets coding agents search and retrieve public X/Twitter content. They describe operating rules and checks to run before committing or deploying.

In plain words
What is it for?
Keeping the server read-only, protecting environment files and credentials, checking the code, testing deployment, and verifying its health and MCP search tools.
Why use it?
They help prevent accidental write actions, leaked secrets, and unverified changes while maintaining this TypeScript Cloudflare Worker.

Instructions file for CodexOpenCode

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/kandotrun/x-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/kandotrun/x-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 x-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kandotrun/x-mcp/agents-md.svg)](https://agentmods.dev/instructions/kandotrun/x-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kandotrun/x-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kandotrun/x-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 313 This file is loaded in full into every session.
When invoked 313 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00313 $0.00313
Opus 5 $0.00156 $0.00156
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00031 $0.00031

Measured 5d ago against content hash 163c8323a827, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

x-mcp AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS https://x.mcp.2-38.com/health
AGENTS.md · 32 lines

What it actually says

AGENTS.md

This repo contains x-mcp, a public read-only Streamable HTTP MCP server for X/Twitter search and retrieval via twitter.2-38.com. The implementation is a TypeScript + Hono Cloudflare Worker.

Operating rules

  • Keep the MCP read-only. Do not add write actions such as post, like, repost, follow, DM, notifications, or authenticated timeline access without explicit Kan approval.
  • The Worker endpoint is https://x.mcp.2-38.com/mcp.
  • The upstream proxy base is https://twitter.2-38.com/api/fx.
  • Do not commit wrangler.jsonc, .dev.vars, .env*, Cloudflare account secrets, OAuth tokens, or API keys.
  • Keep wrangler.example.jsonc safe and placeholder-based except public route/vars.
  • Keep README and docs/agent-install-prompts.md bilingual when changing user-facing onboarding.
  • Keep skills/x-mcp/SKILL.md focused on how agents should install/configure/use the MCP.

Verification before commit

Run:

npm run check
npm run deploy:dry

For remote smoke testing after deployment:

curl -sS https://x.mcp.2-38.com/health
curl -sS https://x.mcp.2-38.com/.well-known/mcp.json

Then verify MCP tools/list and search_posts using an MCP client or the SDK.

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. 5d ago First seen · 32 lines · 313 tokens per session scan A 163c8323a827

Subscribe to this mod's changes

x-mcp AGENTS.md is an instructions file published in the GitHub repository kandotrun/x-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 313 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.