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/call518/mcp-ambari-api/copilot-instructionsgit clone --depth 1 https://github.com/call518/MCP-Ambari-APIWrote 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/call518/mcp-ambari-api/copilot-instructions)<a href="https://agentmods.dev/instructions/call518/mcp-ambari-api/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/call518/mcp-ambari-api/copilot-instructions.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 | $0.00908 | $0.00908 |
| Opus 5 | $0.00454 | $0.00454 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
MCP-Ambari-API copilot-instructions.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 4d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for MCP-Ambari-API
Language Guidelines
- Code & Development: Use English as the default language for all code, comments, documentation, and technical implementations unless explicitly requested otherwise by the user
- User Communication: Use Korean as the default language for conversations and interactions with users through Copilot chat interface
- Documentation: Technical documentation should be in English, while user-facing help and explanations should be in Korean
Architecture & Transport Selection
This MCP server supports dual transport modes with flexible configuration via CLI args and environment variables:
- stdio mode: Default for local usage (
uvx mcp-ambari-api) - streamable-http mode: For Docker/server deployment (
--type streamable-httporFASTMCP_TYPE=streamable-http)
Priority: CLI args > Environment vars > Defaults. The main() function in src/mcp_ambari_api/mcp_main.py (~2181 lines) handles transport selection and runs the FastMCP server.
Core Patterns
- Tool Definition: Every Ambari operation is an async function with
@mcp.tool()+@log_tooldecorators - API Abstraction: All Ambari REST calls go through
make_ambari_request()infunctions.pywith automatic auth, error handling, and timing - Environment Configuration: Ambari connection via
AMBARI_HOST,AMBARI_PORT,AMBARI_USER,AMBARI_PASS,AMBARI_CLUSTER_NAMEenv vars - Unified Tool Pattern: Modern tools like
dump_configurationsreplace multiple specialized tools (supersededget_configurations,list_configurations) - Error Handling: Structured
{"error": "..."}responses with HTTP status codes and timing info - Logging: The
@log_tooldecorator provides uniform timing, argument preview, and result categorization (SUCCESS/ERROR/EXCEPTION)
Development Workflows
- Local Testing: Use
run-mcp-inspector-local.sh(notscripts/) with uv to test tools interactively - Docker Development:
docker-compose up -dstarts full stack (OpenWebUI + MCP server + MCPO proxy) - Build & Deploy: Version-specific Docker images via
build-mcp-server-docker-image.shandbuild-mcpo-server-docker-image.sh - Package Structure: Entry point is
mcp-ambari-apiconsole script →mcp_ambari_api.mcp_main:main - Environment Setup: Use
PYTHONPATH=./srcfor local development, packaged resources inmcp_ambari_api/prompt_template.md
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.
- 4d ago First seen · 52 lines · 908 tokens per session scan A e65484e771d8
MCP-Ambari-API copilot-instructions.md is an instructions file published in the GitHub repository call518/MCP-Ambari-API (1 stars, last pushed 1mo ago), licensed MIT. It adds 908 tokens to every session, about $0.0045 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
iotdb CLAUDE.md
Claude Code instructions for apache/iotdb, covering claude.md, project overview, build commands, full build (skip tests) and build a specific module (e.g., datanode).
hunter-community CLAUDE.md
Claude Code instructions for agentpit-io/hunter-community, covering claude.md — hunter-community, 铁律:严禁 mock 兜底 · 空的比假的好, 严禁的模式, why and 落地方法.
grok-keysmith AGENTS.md
AGENTS.md instructions for Jia-Ethan/grok-keysmith, covering repository agent guide, scope, release and external state, change boundaries and documentation rules.
hier_config AGENTS.md
AGENTS.md instructions for netdevops/hier_config, covering hierconfig — agent & contributor guide, project overview, build & test commands, full lint + test suite (what ci runs) and tests only (95% coverage required).
branchbox CLAUDE.md
Claude Code instructions for branchbox/branchbox, covering claude.md, architecture deep dive, core library architecture (core/src/), cli architecture (cli/src/) and key design patterns.
defang CLAUDE.md
Claude Code instructions for DefangLabs/defang, a project described as: Defang CLI. Develop Once, Deploy Anywhere. Take your app from Docker Compose to a secure and scalable deployment on your favorite cloud in minutes.