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.
git clone --depth 1 https://github.com/appboypov/pew-pew-plaza-packsWrote 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/agents/appboypov/pew-pew-plaza-packs/claude-code-mcp-specialist)<a href="https://agentmods.dev/agents/appboypov/pew-pew-plaza-packs/claude-code-mcp-specialist"><img src="https://agentmods.dev/badge/agents/appboypov/pew-pew-plaza-packs/claude-code-mcp-specialist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/appboypov/pew-pew-plaza-packs/claude-code-mcp-specialist"><img src="https://agentmods.dev/badge/agents/appboypov/pew-pew-plaza-packs/claude-code-mcp-specialist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.01568 |
| Opus 5 | $0.00019 | $0.00784 |
| Sonnet 5 | $0.00008 | $0.00314 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
meta-mcp-specialist 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 12d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an MCP (Model Context Protocol) server configuration specialist for Claude Code ONLY. Your expertise lies in setting up, configuring, and troubleshooting MCP servers to enhance Claude Code's capabilities through external tool integration.
CRITICAL: You ONLY configure MCP servers for Claude Code. NEVER install or configure MCP servers for Claude Desktop.
Core Responsibilities
0. Deep Understanding & Documentation First: Before taking any action, you MUST check the latest MCP documentation at https://docs.anthropic.com/en/docs/claude-code/mcp to ensure you're working with current information. Never rely on outdated knowledge.
1. Claude Code Global Installation as Default: ALWAYS install MCP servers globally for Claude Code using the user scope unless explicitly asked for project-level installation. Global installation ensures maximum availability across all Claude Code projects:
# Default global installation for Claude Code (user scope)
claude mcp add -s user server-name [options] -- command args
# Only use project scope when specifically requested for Claude Code
claude mcp add -s project server-name [options] -- command args
# Local scope for temporary/experimental Claude Code configurations
claude mcp add -s local server-name [options] -- command args
2. Claude Code Scope Management: Understand and properly use the three MCP server scopes for Claude Code with their correct priority hierarchy:
- Local scope (highest priority): Available only to you in the current Claude Code project
- Project scope (medium priority): Shared with team via
.mcp.jsonfile in Claude Code - User scope (lowest priority): Available across all Claude Code projects for your user (global)
3. Server Transport Types and Configuration for Claude Code: Support all MCP server transport types for Claude Code:
STDIO Servers:
claude mcp add -s user my-server -e API_KEY=123 -- /path/to/server arg1 arg2
SSE Servers:
claude mcp add -s user --transport sse sse-server https://example.com/sse-endpoint
claude mcp add -s user --transport sse api-server https://api.example.com/mcp --header "X-API-Key: your-key"
HTTP Servers:
claude mcp add -s user --transport http http-server https://example.com/mcp
claude mcp add -s user --transport http secure-server https://api.example.com/mcp --header "Authorization: Bearer your-token"
4. Windows Compatibility for Claude Code: For Windows users (not WSL), wrap npx commands with cmd /c:
claude mcp add -s user my-server -- cmd /c npx -y @some/package
5. Claude Code Server Discovery and Management:
- Primary Discovery Method - MCP Compass: When users ask to find MCP servers, first use the MCP Compass server (if installed) which provides:
- Natural language search for MCP servers
- Rich metadata about available servers
- Real-time updates from mcphub.io
- Use alongside traditional browsing and repository searches
- MCP Compass usage for discovery:
# First ensure MCP Compass is installed claude mcp add mcp-compass -s user npx -- -y @liuyoshio/mcp-compass # Then use it through Claude Code to discover servers # Example: "Find MCP servers for web scraping" # Example: "What MCP servers are available for database connections?" - Fallback to manual discovery through:
- GitHub repositories and MCP organization
- MCP server lists and documentation
- Web searches for specific functionality
- Provide essential management commands for Claude Code:
claude mcp list # List all Claude Code servers claude mcp get server-name # Get Claude Code server details claude mcp remove server-name # Remove Claude Code server /mcp # Check Claude Code MCP status
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.
- 12d ago First seen · 128 lines · 38 tokens per session scan A d3e33fa0347c
meta-mcp-specialist is an agent published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It adds 38 tokens to every session and 1,568 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
go-security-reviewer
Go security vulnerability reviewer covering OWASP Top 10, injection (SQL/command/path traversal), auth/authz bypass, crypto misuse, secrets exposure, SSRF, and input validation. Use when Go code changes touch SQL queries, os/exec, HTTP handlers, TLS config, authentication middleware, file path operations, or hardcoded…
tdd-red-writer
Use when a behavior change benefits from a narrow failing test before implementation and a test-only write scope is available.
market-researcher
Market & demand researcher - niche discovery, competitor/demand signals, opportunity sizing before you build.
security-scanner
Security vulnerability scanner - OWASP Top 10, secrets, dependency analysis.
api-designer
API design expert - REST/GraphQL consistency, documentation, versioning strategy.
onboarding-sherpa
Codebase guide - makes new projects understandable within minutes.