Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/phazurlabs/install-labsnpx agentmods add skills/phazurlabs/install-labs/mcp-server-packagingWrote 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/skills/phazurlabs/install-labs/mcp-server-packaging)<a href="https://agentmods.dev/skills/phazurlabs/install-labs/mcp-server-packaging"><img src="https://agentmods.dev/badge/skills/phazurlabs/install-labs/mcp-server-packaging.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 | $0.00117 | $0.05335 |
| Opus 5 | $0.00059 | $0.02668 |
| Sonnet 5 | $0.00023 | $0.01067 |
| Haiku 4.5 | $0.00012 | $0.00534 |
Grade A, and why
mcp-server-packaging 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 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.
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 — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Packaging
What Is MCP
Model Context Protocol (MCP) is the open standard for connecting AI systems to external tools, data sources, and services. Developed by Anthropic and adopted across the AI ecosystem, MCP defines a structured interface between an AI host (Claude Desktop, Claude Code, Cursor, Windsurf) and external capabilities.
MCP servers expose three primitive types:
| Primitive | Purpose | Example |
|---|---|---|
| Tools | Functions the AI can call | search_database, create_ticket |
| Resources | Data the AI can read | file://config.yaml, db://users/123 |
| Prompts | Reusable prompt templates | summarize-code, review-pr |
MCP is to AI agents what USB is to peripherals: a universal plug that lets any compliant host talk to any compliant server without custom integration code.
Why MCP Is the #1 Distribution Target
- Claude Desktop, Claude Code, Cursor, Windsurf, Cline, and Zed all support MCP natively.
- A single MCP server works across every compatible host with zero code changes.
- The protocol handles capability negotiation, lifecycle management, and error propagation.
- Registry infrastructure (official registry, Smithery, mcp.so) is maturing rapidly.
MCP Server Architecture
Transport Layers
MCP supports two transport mechanisms. Choosing the right one is the most consequential architectural decision.
stdio (Local Servers)
The host spawns the MCP server as a child process. Communication happens over stdin/stdout using JSON-RPC 2.0 messages, one per line.
- Zero network configuration. No ports, no firewall rules.
- Server lifecycle is managed by the host (started on demand, killed on exit).
- Best for: CLI tools, filesystem access, local development utilities.
- The server MUST NOT write anything to stdout except valid JSON-RPC messages. Use stderr for logging.
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 · 654 lines · 117 tokens per session scan A 6a9498bea304
mcp-server-packaging is a skill published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 117 tokens to every session and 5,335 once invoked, about $0.0006 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 skills, from other repositories
local-ci
Run GitHub Actions workflows locally with pause-on-failure for AI-agent-driven CI iteration.
local-ci
Run GitHub Actions CI locally with Local CI to validate changes before pushing. Use when testing, running checks, or validating code changes.
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
memory
Use durable BB memory when prior project knowledge or cross-project user preferences can improve the current task, and save durable new learning through the bb memory CLI.