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/futuretea/yunxiao-mcp-server/agents-mdgit clone --depth 1 https://github.com/futuretea/yunxiao-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/futuretea/yunxiao-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/futuretea/yunxiao-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/futuretea/yunxiao-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00869 | $0.00869 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
yunxiao-mcp-server 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 6d 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 http://localhost:8080/healthz How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yunxiao MCP Server
Go implementation of an MCP server for the Alibaba Yunxiao (云效) DevOps platform. Defaults to read-only; write tools available with read_only=false.
Quick Start
Build:
make build
Run tests:
make test
make coverage-check # verify 98% threshold
Run locally (HTTP mode):
YUNXIAO_MCP_ACCESS_TOKEN=<your-token> ./bin/yunxiao mcp --port 8080
Health check:
curl http://localhost:8080/healthz
Environment
Primary environment variables:
YUNXIAO_MCP_ACCESS_TOKEN— Yunxiao personal access tokenYUNXIAO_MCP_BASE_URL— API base URL (defaults tohttps://openapi-rdc.aliyuncs.com)
Legacy aliases YUNXIAO_ACCESS_TOKEN and YUNXIAO_API_BASE_URL are also supported. See config.example.yaml for all options.
To test tool calls interactively, use an MCP client (e.g., mcpc) pointed at the server.
Project Structure
cmd/yunxiao/ # Entry point
internal/cmd/ # CLI commands (mcp mode, task commands, tool fallback)
pkg/server/http/ # HTTP/SSE transport
pkg/server/mcp/ # MCP server construction, stdio/HTTP/SSE
pkg/toolset/yunxiao/ # All Yunxiao tool definitions and handlers
*_tools.go # Tool schema definitions (mcp.NewTool)
*_handlers.go # Handler implementations
*_test.go # Handler and helper tests
conditions.go # Conditions JSON builders
helpers.go # Common handler helpers
toolset.go # Toolset registration and filtering
pkg/yunxiao/ # Shared Yunxiao OpenAPI SDK
Key Files
| File | Purpose |
|---|---|
pkg/toolset/yunxiao/toolset.go |
Toolset registration, compactHiddenTools map (59 hidden tools across 4 categories), write-tool gating |
pkg/toolset/yunxiao/*_tools.go |
193 MCP tool schemas across 7 domains (170 read-only + 16 write-capable tools gated behind read_only=false) |
pkg/toolset/yunxiao/projex_enhanced_*.go |
8 enhanced aggregation tools |
pkg/toolset/yunxiao/appstack_enhanced_*.go |
5 AppStack enhanced overview tools |
pkg/toolset/yunxiao/codeup_write_*.go |
6 Codeup write tools |
pkg/toolset/yunxiao/flow_write_*.go |
2 Flow write tools |
pkg/yunxiao/client.go |
HTTP client with auth, pagination, and error handling |
docs/ga-readiness.md |
Release gate checklist and deferred endpoints |
docs/quickstart.md |
Common AI conversation patterns |
docs/conditions-cookbook.md |
Conditions JSON examples |
docs/pagination-guide.md |
Pagination mode reference |
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.
- 6d ago First seen · 84 lines · 869 tokens per session scan A 8965c52a475f
yunxiao-mcp-server AGENTS.md is an instructions file published in the GitHub repository futuretea/yunxiao-mcp-server (4 stars, last pushed 1mo ago), licensed MIT. It adds 869 tokens to every session, about $0.0043 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.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.