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.
npx agentmods add instructions/axt-team/uapi-mcp/agents-mdgit clone --depth 1 https://github.com/AxT-Team/uapi-mcpWhat 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 | $0.00929 | $0.00929 |
| Opus 5 | $0.00464 | $0.00464 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
uapi-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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — uapi-mcp
This file tells AI coding agents (Codex, Claude Code, Cursor, OpenCode, Gemini, etc.) what this repository is and how to wire up the UAPI MCP server.
What this repo is
The official MCP (Model Context Protocol) server for the public API platform uapis.cn. It exposes 100+ UAPI endpoints — network lookups, text utilities, image processing, social-platform queries, translation, search, weather, time, OCR — as MCP tools that any MCP-aware AI agent can call directly.
Hosted server (recommended)
A managed Streamable-HTTP MCP server is already running. Most agents only need this one URL:
https://uapis.cn/mcp
Discovery shortcuts:
- Server card: https://uapis.cn/.well-known/mcp/server-card.json
- WebMCP descriptor: https://uapis.cn/.well-known/webmcp
- Agent card: https://uapis.cn/.well-known/agent-card.json
Wiring it into common agents:
// Claude Desktop / Claude Code (claude_desktop_config.json)
{
"mcpServers": {
"uapi": {
"transport": "streamable-http",
"url": "https://uapis.cn/mcp"
}
}
}
// Cursor (.cursor/mcp.json)
{
"mcpServers": {
"uapi": {
"url": "https://uapis.cn/mcp"
}
}
}
For paid endpoints, set the UAPI key once via the X-API-Key header
(MCP servers may forward mcpAuth.bearer to this header — see the
server card for details).
Local install (npm)
The same server is published on npm and runs over stdio for local agents:
# Run directly (no install)
npx -y uapi-mcp start --mode dynamic
# Or install globally
npm i -g uapi-mcp
uapi-mcp start --mode dynamic
Stdio config example:
{
"mcpServers": {
"uapi": {
"command": "npx",
"args": ["-y", "uapi-mcp", "start", "--mode", "dynamic"]
}
}
}
Build from source
git clone https://github.com/AxT-Team/uapi-mcp
cd uapi-mcp
npm install
npm run build
node ./bin/mcp-server.js start --mode dynamic
Available tools
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.
- 2d ago First seen · 131 lines · 929 tokens per session scan A 1605e24cbf4d
uapi-mcp AGENTS.md is an instructions file published in the GitHub repository AxT-Team/uapi-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 929 tokens to every session, about $0.0046 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 2026-08-31.
Other instructions, from other repositories
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
crust AGENTS.md
Instructions for chenxin-yan/crust, covering tests, documentation, changesets, agent skills and issue tracker.
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.